arXiv:2510.23472v2 Announce Type: replace
Abstract: Chip placement is a vital stage in modern chip design, and black-box optimization (BBO) has been applied to it for decades. Early BBO efforts, however, were limited by immature problem formulations and inefficient algorithm designs, leading to worse efficiency, quality, and scalability than mainstream analytical methods. Recent advances in BBO have shown strong potential, but a unified, BBO-specific benchmark for thoroughly assessing various problem formulations and BBO algorithms is lacking. To fill this gap, we propose BBOPlace-Bench, the first benchmark tailored for evaluating and developing BBO algorithms for chip placement. It integrates three BBO problem formulations and offers a modular, flexible framework that enables users to seamlessly implement, test, and compare their own algorithms. It aggregates representative modern chip cases and standardizes their formats, providing uniform and comprehensive information to support BBO optimization. Moreover, it integrates representative BBO algorithm families, including simulated annealing, population-based search (including GA, CMA-ES, and PSO), and Bayesian optimization, and systematically evaluates their performance across different problem formulations using key chip-placement metrics. We position these experiments primarily as illustrative case studies under a shared evaluation protocol, including common benchmark instances, metric definitions, evaluation pipeline, and search budgets. Under this protocol, some BBO configurations (e.g., GA under the mask-guided optimization formulation) are competitive with representative analytical and reinforcement learning baselines. BBOPlace-Bench not only facilitates the development of efficient BBO-driven solutions for chip placement but also broadens the practical application scenarios urgently needed by the BBO community.
Science Journals
arXiv:2605.31581v2 Announce Type: replace
Abstract: The same arguments often need to be evaluated under different external regimes. An agent with influence over the regime has a strategic lever that standard formalisms do not directly capture. We introduce context-dependent argumentation frameworks (CDAFs), an extension of Dung's theory in which a defeat function determines, per context, which attacks succeed. Blocked attacks are inverted rather than deleted, so extensions stay conflict-free with respect to the attack relation. A perspective-labeled specialisation derives the defeat function from a relevance set $\rho$ and a priority $\pi$. The relevance set is the agent's action space. In a small worked example, the agent's target argument is rejected under every full-relevance priority, yet accepted under a partial activation whose outcome no VAF audience can mirror. We define the corresponding decision problem, ACTIVATION-MANIPULATION, and record baseline complexity bounds. For grounded semantics with mandatory perspectives the problem is NP-complete, and the hardness comes from the activation choice itself.
arXiv:2606.00242v2 Announce Type: replace
Abstract: Bound quantum states such as atoms can be torn apart by strong oscillating fields. A natural expectation is that stronger fields lead to more certain destruction. In contradiction to this intuition, some theories predict a striking reversal: that as the field intensity is raised above some threshold, bound state wavefunctions can spatially bifurcate and become increasingly stable with increasing field intensity. This ``strong field stabilization'' was predicted decades ago in the context of atoms in pulsed laser fields, but has resisted experimental observation due to extreme laser intensity requirements and theoretical controversy. We report the experimental observation of strong-field stabilization of a ground state, using trapped neutral atoms to emulate the dynamics of atomic electrons in an extremely strong laser field. We directly image the predicted wavepacket bifurcation, measure an ionization rate non-monotonic in field amplitude, and map out the regime of stabilization as a function of laser pulse parameters. We observe that stabilization persists down to surprisingly low drive frequencies, near and below the scale of the lowest-energy excitations of the bound state. These results confirm and extend a long-standing prediction of extreme quantum dynamics, and showcase a complementary tool for probing strong-field phenomena near and beyond the frontier of current laser technology.
arXiv:2606.00680v3 Announce Type: replace
Abstract: Offline reinforcement learning (RL) aims to optimize policies from pre-collected datasets. A bottleneck of this paradigm is managing epistemic uncertainty, which arises from limited data coverage (sample-level) and the ambiguity in identifying transition dynamics from finite data (model-level). To provide a unified quantification of these uncertainties, Bayesian RL has been proposed by treating the dynamics model as a random variable and maintaining a corresponding belief. Despite its theoretical appeal, policy optimization in Bayesian RL remains computationally challenging as it requires solving composite objectives with expectations. Prior methods either employ search-based techniques with poor computational scalability or impose restrictive posterior assumptions that sacrifice the adaptability of Bayesian RL. To address these limitations, we propose Posterior Hybrid Bayesian Belief (PhyB), which reformulates the expectation as a convex combination over a subset of dynamics models. Theoretical analysis demonstrates that the objective discrepancy induced by this approximation remains bounded. Based on PhyB, we develop an iterative regularized policy optimization algorithm that provides metric-agnostic guarantees for monotonic improvement until convergence. Empirical results demonstrate that PhyB achieves state-of-the-art performance on various benchmarks.
arXiv:2606.01375v2 Announce Type: replace
Abstract: Large language models (LLMs) are increasingly entering students' learning practices, but their educational value depends on whether they support reasoning or enable task completion without engagement. This study examines guided LLM use in an undergraduate Probability and Statistics course, focusing on the gap between assigned access and actual interaction quality. In a four-week quasi-experimental summer program, students were organized into three balanced conditions: no LLM access, unrestricted LLM access, and guided LLM access. The guided condition used the same LLM platform as the unrestricted condition, but students received explicit training and rules promoting reasoning-focused help-seeking, stepwise hints, verification, and ethical use. All quizzes and the delayed final exam were completed without LLM or external assistance, allowing us to distinguish AI-supported practice performance from independent learning. Results show that guided use was associated with clearer learning-oriented interaction patterns than unrestricted access, especially in prioritizing reasoning over final answers and requesting stepwise support. Guided-LLM students showed stronger no-help quiz performance during the intervention phase, whereas unrestricted access appeared more useful for assisted practice completion than for consistently improving independent performance. Available time measures did not support a simple duration-based explanation, and self-assessment calibration suggested better alignment between perceived and demonstrated understanding in the Guided-LLM condition. Overall, LLM access alone appears to be an incomplete educational intervention. For Artificial Intelligence in Education (AIED), the central design challenge is to scaffold how students use LLMs so that these systems function as partners in reasoning rather than answer-getting tools.
arXiv:2606.02002v3 Announce Type: replace
Abstract: Blind image quality assessment (BIQA) predicts perceived image quality without access to a pristine reference and is fundamental to applications such as image compression, transmission, and restoration. Recent BIQA methods increasingly rely on large vision-language models (VLMs). Although frozen VLMs provide an efficient alternative to computationally expensive full fine-tuning, it remains unclear how much performance is sacrificed by not adapting the backbone and, more importantly, under what conditions such adaptation is truly beneficial. Answering this question, however, is complicated by the widespread use of image-level splitting on synthetic-distortion benchmarks, where distorted versions of the same reference image can appear in both training and test partitions. This content overlap artificially inflates the apparent performance of frozen representations, masking their true generalization ability and potentially leading to incorrect conclusions about the value of backbone adaptation. We therefore address these two issues jointly. We develop an efficient BIQA framework that fuses a natural-scene-statistics descriptor with frozen SigLIP and CLIP-H embeddings through a lightweight regression head, and then apply parameter-efficient Low-Rank Adaptation (LoRA) to the SigLIP backbone, training only $0.23\%$ of its parameters. Evaluating both frozen and adapted models across six datasets under image-level and reference-level protocols, we find that image-level splitting inflates frozen-feature SROCC by up to $0.44$ and masks wide variation in true difficulty, which reference-level evaluation reveals. Under this content-independent protocol, LoRA adaptation recovers performance in proportion to the exposed difficulty, with the largest gains where frozen features generalize poorly (up to $+0.357$ SROCC on TID2013) and little benefit where they are already strong.
arXiv:2606.02780v3 Announce Type: replace
Abstract: The success of the transformer architecture as the backbone of modern LLMs is in large part due to its use of attention layers. An attention layer follows the standard neural network paradigm: it takes the residual stream as input and thereby produces context-dependent query, key, and value vectors. However, we find that model performance meaningfully improves when deeper layers learn only a context-free value vector to preserve the original token information, without drawing on any context from the residual stream. When the model has access to this context-free value vector, adding back the context-dependent component provides little additional benefit for aggregate benchmark performance. Such context-free value vectors can be stored as sparse model parameters, eliminating the need to recompute or persistently cache these values. Through systematic ablations on the key design choices for such context-free value vectors, we propose Bank of Values (BoV), a new way of computing value vectors in attention by learning a lookup table of token-specific value vectors for each of the last third of layers. Across 135M and 780M models, BoV improves validation loss over standard attention and, at 780M, the average score across 21 benchmarks, matching the previous best method that adds token information to the value vector with less compute and memory.
arXiv:2606.04257v2 Announce Type: replace
Abstract: Monroe (2026) shows that, if no optimal proof system exists, then every sound arithmetic theory S extending S^1_2 with polynomial-time decidable axioms fails, for all sufficiently large k, to simulate S^1_2+phi_BB(k), where phi_BB(k) asserts the exact k-state Busy Beaver value. This gives the nonexistence hypothesis an information-constraint interpretation through canonical hard instances. If the best-known route to simulation is also necessary--namely, if simulation requires a relative-consistency explanation over a weak base--then the same constraint applies to inaccessible Kolmogorov-randomness facts. We call this conjecture Kolmogorov Hardness (KH).
Finite-scale and hierarchy-level forms of KH yield, conditionally, dense families of small hard tautologies, PH noncollapse with explicit dense separators, and SAT notin P/poly. Under separately stated assumptions, variants yield P-inseparability of a disjoint NP pair, no mutual help between mutually conditionally random axioms, one-way functions via Liu--Pass, derandomization, and Feige-style random-refutation hardness. Allender et al. provide a complementary calibration: full access to conventional random-string oracles supports every PSPACE computation, whereas any fixed sound computably axiomatized theory can certify only finitely many positive randomness instances.
The framework organizes complexity conjectures around canonical information constraints. It seems self-evident that efficient proofs should not leverage true randomness facts unavailable to the proving theory. Yet KH may be independent of standard metatheories: it resembles reflection, can fail internally in nonstandard models even when externally true, and may constrain the metatheories themselves. We propose a research program on extensions, self-evidence, formal independence, and possible new axioms.
arXiv:2606.04460v2 Announce Type: replace
Abstract: AI has the potential to transform cybersecurity by enabling systems that can autonomously detect, analyze, and remediate software vulnerabilities. However, existing cybersecurity evaluations of AI systems are limited in scale or scope, and fail to capture the end-to-end lifecycle of real-world software vulnerability discovery and remediation. To address this gap, we propose CyberGym-E2E, a large-scale and realistic end-to-end cybersecurity benchmark that comprehensively evaluates AI agents' abilities across the full lifecycle of vulnerability discovery, PoC generation, and patch generation. CyberGym-E2E is comprehensive and scalable, as we build an automated, agent-enhanced pipeline for transforming open-source vulnerability data into realistic evaluation environments. Currently, the benchmark consists of 920 real-world vulnerabilities across 139 different open-source projects.
arXiv:2606.05558v2 Announce Type: replace
Abstract: Evaluating large language model (LLM) agents in multi-turn interactive environments is expensive and risky, as it requires online environment interaction. We propose ADWM (Autoregressive Diffusion World Model), an evaluation framework that estimates the performance of a new LLM agent policy purely from pre-collected trajectories. The core idea is to learn a latent diffusion world model that simulates how the environment responds to the evaluation policy, without ever executing it in the real environment. Existing diffusion-based OPE methods guide full trajectories in a single pass by jointly diffusing states and actions, an assumption that breaks down for LLM agents whose actions are discrete text that must be sampled from the policy after observing the environment. Unlike autoregressive world models that suffer from compounding errors, ADWM models each transition as an independent denoising process, enabling reliable step-by-step rollouts where the world model and agent alternate in causal order. Crucially, the LLM agent under evaluation directly guides the diffusion generation at each step via a policy-conditioned score function, ensuring that simulated trajectories accurately reflect its decision-making patterns. Empirically, ADWM achieves accurate value estimates and evaluation reliability across diverse multi-turn agent tasks, demonstrating its promise as a practical framework for offline LLM agent evaluation.
arXiv:2606.06197v3 Announce Type: replace
Abstract: Question answering (QA) systems have achieved notable progress with the advent of large language models (LLMs). However, they still face challenges in accurately extracting and generating precise answers from given contexts, particularly when dealing with complex or ambiguous queries. Existing approaches often struggle with contextual understanding, answer consistency, and generalization across diverse domains. In this work, we propose a question answering system based on large language models, where the input consists of a textual context and a corresponding question, and the output is a concise and accurate answer. The motivation behind this research lies in addressing the limitations of current QA systems, particularly their tendency to produce irrelevant or imprecise responses despite having access to the correct context. Our methodology involves fine-tuning a pre-trained LLM on a benchmark QA dataset to improve its contextual comprehension and answer extraction capabilities. Specifically, we utilize the Stanford Question Answering Dataset (SQuAD1.1), which provides high-quality context-question-answer triplets for supervised training and evaluation. Experimental results show that the fine-tuned Roberta-base model achieves the highest performance, attaining a ROUGE-L score of 86.84%, a BLEU score of 28.24%, and a BERTScore of 95.38%. These results indicate strong accuracy and answer relevance, demonstrating the effectiveness of the proposed approach for context-based question answering tasks. Furthermore, the findings confirm that targeted fine-tuning substantially improves the reliability and precision of QA systems.
arXiv:2606.06491v2 Announce Type: replace
Abstract: Robot manipulation alternates between low-risk transit phases that call for fast execution and high-risk contact stages that demand slow, precise motion. Yet existing Vision-Language-Action models (VLAs) only inherit a single fixed speed from training demonstrations. Prior efforts to accelerate VLAs through model compression, KV-cache reuse, or reinforcement learning only shift the policy from one fixed speed to another, and leave deceleration almost unexplored. We observe that the magnitude of each predicted action already governs how fast the robot moves, opening a direct route to controllable execution speed. We turn this observation into TempoVLA, a single VLA whose execution speed is controlled by an explicit condition. TempoVLA combines two coupled components. (1) A data-side Variable-Speed Trajectory Augmentation (VSTA) that re-times demonstration to any target speed by merging or splitting actions while preserving its motion semantics. (2) A model-side conditioning mechanism that feeds the speed to the policy. Statistics show that VSTA reaches the requested speed with negligible motion error. Experiments in simulation and on real-world tasks demonstrate that TempoVLA achieves flexible speed control in both directions, while VSTA additionally boosts the default $1\times$ performance via better data utilization. Furthermore, by cooperating with a large multimodal model, TempoVLA realizes dynamic speed control, accelerating through low-risk phases and decelerating for high-risk ones.
arXiv:2606.06547v2 Announce Type: replace
Abstract: Diffusion Large Language Models (dLLMs) refine tokens iteratively but commit them irreversibly, leading to a "stability lag" where early decisions remain fragile even after being written. We reveal that Post-Training Quantization (PTQ) error easily flips these borderline decisions at the write frontier, which are then permanently locked in and amplified. To address this, we propose Frontier-Aware Instability-Reweighted Calibration (FAIR-Calib), a two-stage PTQ framework for dLLMs. Stage I probes a full-precision teacher to estimate a position prior that combines frontier hits and masked-stage reliability. Stage II performs off-policy, layer-wise calibration by minimizing a reweighted hidden-state MSE, effectively prioritizing the protection of fragile frontier states without requiring expensive end-to-end diffusion rollouts. We further theoretically justify our weighted objective as a surrogate for output KL divergence. Empirically, FAIR-Calib consistently outperforms state-of-the-art baselines on LLaDA and Dream (W4A4), significantly reducing frontier decision flips and suppressing post-commit mismatches across diverse benchmarks.
arXiv:2606.06752v2 Announce Type: replace
Abstract: In this industrial experience paper, we present Pomona, a lightweight agentic tool that utilises agent skills for continuous code quality improvement. Inspired by the Kaizen (TM) philosophy, Pomona automates a cycle of discovery and incremental repair: a Scanning skill identifies tasks and prioritises them in a backlog, while a Repair skill generates small, easily reviewable pull requests (PRs). This design enables frequent, low-risk improvements while maintaining engineer trust and reducing technical debt. We evaluated Pomona at Bloomberg through a three-month team deployment and a questionnaire distributed to senior engineers. The results are promising: 32/39 PRs (82.1%) were merged with a median time-to-close of just over two hours. Moreover, 10/12 surveyed engineers expressed a desire to adopt Pomona, praising its small diff sizes and focus on code quality. Since our evaluation, another team has adopted Pomona. We conclude with actionable insights for deploying agents in industry.
arXiv:2607.16676v1 Announce Type: cross
Abstract: How deep does a graph neural network need to be on a sparse graph? We study its purest statistical form: node classification on the sparse contextual stochastic block model (CSBM) with average degree $\Delta=O(1)$, whose local weak limit is a broadcast-labelled Poisson Galton-Watson tree. Prior work derived a message-passing classifier $h_\ell$ that aggregates from each vertex at distance $k\le\ell$ the attenuated evidence $2\operatorname{artanh}(\gamma^k t(X_v))$, with $\gamma$ the edge signal and $t$ a bounded likelihood-ratio transform of the feature. We prove that the value of depth is governed by a single number, the Kesten-Stigum ratio $\kappa=\gamma^2\Delta$. Below the threshold ($\kappa<1$), the error sequence is Cauchy at a geometric rate, $|\mathcal{E}(\ell)-\mathcal{E}(\ell')|\le C\kappa^{(\ell+1)/3}$ for all $\ell'>\ell$, so all layers beyond depth $O(\log(1/\epsilon))$ change the error by less than $\epsilon$; conversely, under mild regularity each sufficiently deep layer still flips the decision with probability at least $c\kappa^{\ell/2}$, the empirically sharp exponent. Above the threshold ($\kappa>1$), depth is geometrically productive: $\mathcal{E}(\ell)$ is driven to a branching-process floor of order at most $1/(\kappa-1)$ at any geometric rate $\kappa^{-s\ell}$, $s<1$ (this bound has content only for $\kappa>17$). No local classifier of any depth beats the universal floor $e^{-\Delta}\Phi(-\zeta)$ set by isolated roots ($\zeta$ the feature signal-to-noise ratio), while the first layer provably helps by an explicit total-variation amount. Simulations with an exact belief-propagation baseline on the same trees show that the pairwise rule's error curve is mildly non-monotone in $\ell$, so an optimal finite depth exists (an exact instance is certified in the appendix), while BP saturates strictly faster, at an effective per-layer ratio below $\kappa$ that we identify.
arXiv:2607.18181v1 Announce Type: new
Abstract: Battery-free Internet of Things (IoT) requires iterative design of vibration energy harvesters (VEHs) under coupled physical constraints, while LLMs are emerging as interface layers for engineering workflows. However, existing engineering benchmarks primarily assess final artifact validity, offering limited insights into how LLMs behave across different stages of coupled physical design. We introduce VEHBench, an engineering-native diagnostic benchmark for LLM-assisted VEH design, featuring 763 literature-grounded tasks scored by an analytical physical oracle. VEHBench evaluates four design roles: specification triage, verifier-guided search, corrupted-state recovery, and policy-conditioned selection. Experimental results reveal that LLM capability is strongly stage-dependent: no single model consistently dominates the entire workflow, and response-control profiles expose distinct behavioral patterns across design roles. VEHBench thus provides a stage-aware foundation for evaluating, selecting, routing, and improving verifier-grounded engineering LLMs. The benchmark artifact is available at https://huggingface.co/datasets/AnonymousVehbench/vehbench
arXiv:2607.18184v1 Announce Type: new
Abstract: We present anyakrakusuma, an open-source Python library that solves the discrete static Schr\"{o}dinger bridge problem, the entropically regularized counterpart of optimal transport, through a log-domain Sinkhorn--Knopp iteration and reconstructs the entropic interpolation between two empirical point clouds. The solver is paired with a diagnostic pipeline that characterizes the optimal coupling and the intermediate distributions through information-theoretic and geometric measures. We exercise the library on four idealized planar cases spanning a circle-to-circle dilation, a spiral-to-mixture fragmentation, a rigid reorientation of two moons, and a Lissajous-to-trefoil deformation. The log-domain formulation is necessary rather than merely convenient at the parameters studied, where the cost-to-regularization ratio reaches four hundred and the Gibbs kernel underflows double precision across most of its range; the iteration nonetheless attains a marginal residual of $10^{-9}$ and unit marginal fidelity in every case. Residual histories decay geometrically over approximately eight decades at per-iteration contraction factors between $0.966$ and $0.976$, which are local rates near the fixed point that lie many orders of magnitude below the worst-case Hilbert-metric bound. The covariance analysis recovers an imposed ninety-degree reorientation to within $0.07^\circ$, roughly forty times smaller than its uncertainty, across a masked interval of near-isotropy on which the principal axis is unobservable. The diagnostics are reported with explicit attention to the regimes in which each is well defined, including the differential entropy, which is meaningful only on the open interpolation interval. The presented cases are constructed rather than measured; quantitative application to empirical point clouds requires further study.
arXiv:2505.02722v2 Announce Type: replace
Abstract: Although large language models (LLMs) have demonstrated impressive reasoning capabilities across general domains, their effectiveness in real-world clinical practice remains limited. This is likely due to their insufficient exposure to real-world clinical data during training, as such data is typically not included due to privacy concerns. To address this, we propose enhancing the clinical reasoning capabilities of LLMs by leveraging real-world clinical data. We constructed reasoning-intensive questions from a nationwide sepsis registry and fine-tuned Phi-4 on these questions using reinforcement learning, resulting in C-Reason. C-Reason exhibited strong clinical reasoning capabilities on the in-domain test set, as evidenced by both quantitative metrics and expert evaluations. Furthermore, its enhanced reasoning capabilities generalized to a sepsis dataset involving different tasks and patient cohorts, an open-ended consultations on antibiotics use task, and other diseases. Future research should focus on training LLMs with large-scale, multi-disease clinical datasets to develop more powerful, general-purpose clinical reasoning models.
arXiv:2602.14247v2 Announce Type: replace
Abstract: A networked aerial robot team (NART) comprises a group of agents (e.g., unmanned aerial vehicles (UAVs), ground control stations, etc.) interconnected by wireless links. Inter-agent connectivity, even if intermittent (i.e. sparse), enables data exchanges between agents and supports cooperative behaviours in several NART missions. It can benefit online decentralised decision-making and group resilience, particularly when prior knowledge is inaccurate or incomplete. These requirements can be accounted for in the offline mission planning stages to incentivise cooperative behaviours and improve mission efficiency during the NART deployment. This paper proposes a novel path planning tool for a Sparse, Aware, and Cooperative Networked Aerial Robot Team (SpArC-NART) in exploration missions. It simultaneously considers different levels of prior information regarding the environment, limited agent energy, sensing, and communication, as well as distinct NART constitutions. The communication model takes into account the limitations of user-defined radio technology and physical phenomena. The proposed tool aims to maximise the mission goals (e.g., finding one or multiple targets, covering the full area of the environment, etc.), while cooperating with other agents to reduce agent reporting times, increase their global situational awareness (e.g., their knowledge of the environment), and facilitate mission replanning, if required. The developed cooperation mechanism leverages soft-motion constraints and dynamic rewards based on the Value of Movement and the expected communication availability between the agents at each time step. A ground sensing coverage use case was chosen to illustrate the current capabilities of this tool.
arXiv:2606.07557v2 Announce Type: replace
Abstract: Decentralized multi-agent swarm coordination remains fundamentally challenged by the combinatorial scaling of joint action spaces and high-overhead training or optimization loops when managing localized group behaviors. To address this problem from a different perspective, this paper introduces the Swarm Policy Interference Network (SPIN) framework, which models multi-agent communication topologies as compressed tensor networks. By factorizing the joint policy tensors of local multi-agent cliques into Open Boundary Condition Matrix Product State (MPS) chains, SPIN replaces explicit exponential joint-action enumeration with clique-level contractions that scale linearly in clique length for fixed local behavior and bond dimensions. To connect raw spatial geometry with this discrete algebraic backend without relying on online training loops, we introduce a decoupled framework combining a lightweight frozen neural mapper evaluated offline with a deterministic zero-shot importance-reweighting filter based on the Radon-Nikod\'ym derivative. We evaluate an executable prototype of this framework within a simulation experiment across distinct task regimes: single-target tracking, decentralized area coverage, and structured multi-goal coordination. The results demonstrate that SPIN functions as a reusable decentralized coordination layer across tracking, dispersion / area coverage, and structured multi-goal coordination, with its strongest gains appearing in multi-goal coordination and dense local interaction regimes, without requiring scenario-specific online optimization or retraining.
arXiv:2606.07559v2 Announce Type: replace
Abstract: Fine-tuning a language model often fails silently when its correct completion must outrank a near-synonym competitor. Cross-entropy loss falls monotonically while the correct token never overtakes the competitor. We study five transformer architectures of two families over a fivefold parameter range, on ten contexts where the correct completion and nearest competitor overlap substantially. We construct an order parameter combining the predicted distribution with the geometric overlap between token embeddings. The density-matrix formulation is natural because the prediction distribution lives over a non-orthogonal embedding basis. It decomposes additively into a signal, tracking commitment to the correct token over its nearest competitor, and a background drag, set by how the embedding bulk leaks probability into the score. This isolates two failure modes. In kinematic failure the signal stays small and the model never commits. In structural failure the drag actively worsens as fine-tuning proceeds and the model degrades geometrically even as its loss decreases. Sharp jumps resemble phase transitions but are not. Tracking it after every gradient step rules out spontaneous symmetry breaking. Under LoRA fine-tuning the embedding matrix is frozen, so no geometric phase transition is possible and the discontinuity lies in the softmax readout. One dimensionless quantity is consistent across all five models under full fine-tuning, while a second sorts them into two classes by bulk embedding distribution and predicts whether LoRA alone can drive a sentence to commit. As a blind test, the framework predicts the critical learning rate of a held-out architecture, used to fit no parameter, to within 2.1% of a subsequent sweep. All findings concern the near-synonym geometric mechanism studied here and should not be extrapolated without re-calibration to instruction tuning or broader tasks.
arXiv:2606.07939v2 Announce Type: replace
Abstract: Research on artificial intelligence and work assigns each occupation a single exposure score. We build an instrument to see what those scores average over: a decomposition of 1,961 O*NET work activities into 15,817 atomic micro-actions by a consensus multi-agent LLM pipeline, clustered from text alone into seven semantic classes. Projecting exposure indicators onto these classes reveals two extreme poles, tool-mediated physical execution and planning-and-design, separated by a gap far larger than random partitions of the same data produce (permutation $P < 10^{-4}$; Cliff's $\delta = 0.80$ under our tech-risk index and $0.90$ under GPT-4 task ratings). The poles flank a broad central band that carries most work and is only weakly more compressed than chance. The poles are stable across clustering resolution, sentence encoder (under a common partition), and indicator, yet which pole is most exposed has inverted since 2013: the two extremes swap identity between the Frey-Osborne computerisation era and the LLM era, and at the occupation level an occupation's 2013 automatability declines as its linguistic content rises ($\rho = -0.40$, $n = 618$). We release the instrument and its outputs. The durable object for forecasting is the structure of work itself, not any era's exposure ranking.
arXiv:2606.08012v2 Announce Type: replace
Abstract: The oracle problem, broadly understood as the difficulty of reliably incorporating external information into blockchain-based systems, has been widely examined by scholars and practitioners. Recent comparative research has shown that several challenges of modern blockchain oracles, including attributability, accountability, integrity, and query design, mirror procedural and epistemic constraints already present in ancient oracular institutions such as the Delphic Oracle. Yet the translation of these insights into applied oracle design remains largely unexplored. This paper introduces the Dodona Protocol, a modular, chain-agnostic oracle service inspired by procedural patterns identified in ancient and modern oracle systems. Named after the Oracle of Zeus at Dodona, one of the oldest oracular sanctuaries in ancient Greece, the protocol operationalizes principles such as structured consultation, access control, attributable resolution, constrained query formats, reputational accountability, and tiered service availability. Its first module implements a query and dispute resolution mechanism in which a named expert resolver provides binding answers to structured questions submitted by petitioners. The oracle does not claim to reveal objective truth; rather, it produces outcomes that parties have agreed in advance to accept. The paper presents the design rationale, architecture, and comparative positioning of the Dodona Protocol. It frames the protocol as a living research experiment within the Design Science Research tradition, where the deployed system functions as the research artifact and operational data support structured analysis, iterative refinement, and peer-reviewed dissemination. In doing so, the paper seeks to bridge the gap between oracle theory and oracle practice.
arXiv:2606.08015v2 Announce Type: replace
Abstract: We propose Q-Guided Value-Gradient Matching (Q-VGM), an off-policy reinforcement learning method for a central difficulty in fine-tuning flow-matching vision-language-action (VLA) policies: improving an expressive flow-matching action expert with a learned $Q$-function. Effective improvement must exploit the critic's first-order signal $\nabla_A Q$, yet flow policies make this hard: backpropagating values through the multi-step denoising chain is unstable at VLA scale, and the tractable action likelihoods required by policy gradients are unavailable under iterative denoising. Existing value-based methods therefore backpropagate through the full chain, use the critic only for test-time selection or guidance, or distill critic-improved actions as terminal labels that never supervise the velocity field. Q-VGM instead casts policy improvement as optimal control over the denoising dynamics, where the optimal residual velocity is the gradient of a denoising-time value function: clean-action estimates improved by iterative $Q$-gradient ascent with keep-best selection are converted into residual velocity targets that directly supervise the velocity field -- no action likelihoods, no backpropagation through the denoising chain, fully offline on a fixed replay buffer, and no critic at inference time. The critic is an action-sensitive stepwise IQL critic on compact latent states from the frozen VLA backbone. This enables a few-shot-initialization, learn-from-experience paradigm: starting from a few-shot-SFT $\pi_{0.5}$ policy, Q-VGM improves the policy from its own rollouts without additional expert supervision, raising the average LIBERO success rate from 79.0% to 92.5%, outperforming all same-backbone, same-critic baselines, and attaining high success rates on four real-robot manipulation tasks, including fine-grained plug insertion.
arXiv:2604.27967v2 Announce Type: replace
Abstract: Background: We introduce StructGP, a continuous-time multi-task Gaussian process that couples process convolutions with differentiable structure learning to uncover a sparse, ordered directed acyclic graph (DAG) of inter-variable dependencies while preserving principled uncertainty. We further propose LP-StructGP, which augments StructGP with latent pathways-shared, temporally shifted trajectories inferred via subject-specific coupling filters and a softmax gating mechanism-to capture cross-patient progression patterns. Both models are trained under sparsity and acyclicity constraints using scalable low-rank updates using likelihood-based objectives. Results: In simulations, graph recovery improved with cohort size, with the median Structural Hamming Distance reaching zero at the largest cohort size, while pathway assignments showed high Adjusted Rand Index. Our analysis establishes that the ordered StructGP graph is identifiable from the population marginal likelihood. On a MIMIC-IV septic shock cohort (n=1,008; norepinephrine, creatinine, mean blood pressure), StructGP improves short-horizon (6 h) forecasting over independent-task baselines (average RMSE 0.68 [95% CI: 0.63-0.74] vs. 0.88 [0.83-0.94]) and, with 15 additional inputs, markedly outperforms unstructured kernels (0.63 [0.58-0.69] vs. 3.02 [2.85-3.18]) with superior calibration (coverage 0.96 vs. 0.84). For long horizons (up to 6 days), LP-StructGP further reduces error for creatinine (RMSE 0.95 [0.88-1.03] vs. 1.17 [1.08-1.25]) and improves overall coverage (0.93 [0.93-0.94] vs. 0.91 [0.91-0.92]). On the PhysioNet Challenge, StructGP attains competitive accuracy (MAE 3.72e-2) relative to a strong published graph neural model. Conclusion: These results show that structured process convolutions with latent pathways deliver interpretable, scalable, and well-calibrated forecasting for irregular clinical time series.