arXiv:2605.29012v1 Announce Type: new
Abstract: Diffusion-based and iterative methods have become effective tools for solving imaging inverse problems. Their reconstruction process naturally forms a trajectory of intermediate estimates. Although these intermediate estimates define a reconstruction trajectory, most methods do not explicitly regularize the transitions between consecutive states. To address this limitation, we introduce TRACE, a training-free TRAjectory-Constrained rEconstruction framework that stabilizes the reconstruction path by coupling adjacent states along the trajectory. This gives a trajectory-level model that can be interpreted as a sequence of proximal updates. Since the exact proximal update is generally intractable, we approximate it with a neural mapping. This yields a diffusion-like reconstruction process with an explicit coupling between neighboring states. We provide a stability analysis showing that temporal coupling bounds trajectory variation and that this control is preserved under untrained network updates. Experiments on linear and nonlinear image reconstruction tasks show that TRACE improves reconstruction quality. Trajectory-level analyses and ablations confirm that temporal coupling directly affects state transitions along the reconstruction path.
Science Journals
arXiv:2605.29009v1 Announce Type: new
Abstract: Post-training large language models with reinforcement learning is bottlenecked by the reward signal. Existing approaches require either ground-truth verifiable rewards, restricting training to domains with automatic correctness checks (e.g., mathematics, code execution), or human preference labels, which are expensive to collect and prone to reward hacking. Recent label-free methods replace ground-truth verifiers with self-referential signals like majority voting or token entropy over a model's own outputs, but risk reinforcing a model's own errors. In this work we propose Cross-Model Entropy (CME), the mean log-likelihood of a generator's response under a separate verifier model, as a label-free reward signal for RL post-training. CME is continuous, training-free, and grounded in the principle that responses a verifier finds unsurprising are likely correct or high quality. Because the verifier is independent of the generator, the signal cannot be gamed through self-consistency. We integrate CME into GRPO with no other changes to the training loop, extending label-free RL to open-ended instruction following -- a regime where self-referential signals are inapplicable or poorly suited. On open-ended instruction following (UltraFeedback prompts, evaluated on AlpacaEval 2.0), CME rewards beat the untrained base in head-to-head LLM-as-Judge comparisons across four model families (Qwen, Llama, Gemma, OLMo) and three training regimes (pretrained, SFT, and instruction-tuned), with tie-adjusted win rates ranging from 52.5% to 71.4%. Code will be released upon publication.
arXiv:2604.13019v3 Announce Type: replace
Abstract: Computer Use Agents (CUAs) fundamentally rely on graphical user interface (GUI) grounding to translate language instructions into executable screen actions, but editing-level grounding in dense coding interfaces (such as VS Code and Cursor), where sub-pixel accuracy is required to interact with dense IDE elements, remains underexplored. Existing approaches typically rely on single-shot coordinate prediction, which lacks a mechanism for error correction and often fails in high-density interfaces. In this technical report, we conduct an empirical study of pixel-precise cursor localization in coding environments. Instead of a single-step execution, our agent engages in an iterative refinement process, utilizing visual feedback from previous attempts to reach the target element. This closed-loop grounding mechanism allows the agent to self-correct displacement errors and adapt to dynamic UI changes. We evaluate our approach across Claude, Qwen, and GPT on a suite of complex coding benchmarks, demonstrating that multi-turn refinement significantly outperforms state-of-the-art single-shot models in both click precision and overall task success rate. Our results suggest that iterative visual reasoning is a critical component for the next generation of reliable software engineering agents. Code: https://github.com/microsoft/precision-cua-bench/tree/main.
arXiv:2605.29389v1 Announce Type: new
Abstract: Rigid-bodied robots often lack compliance needed to adapt to unstructured environments, while fully soft robots, though highly adaptable, struggle with scalability and load capacity. In nature, musculoskeletal systems balance strength and flexibility by integrating hard and soft tissues. Inspired by this principle, we present an automated design method for soft-rigid hybrids that optimizes a freeform soft-body shape, a stiff truss layout, and multi-channel actuation. Our differentiable simulator couples the material point method (MPM) for deformable bodies with extended position-based dynamics (XPBD) for truss elements, enabling gradient-based search. The optimization generates truss skeletons that transmit actuation forces to the soft body. We fabricate the optimized design and evaluate it on a walking task. Experiments reproduce the walking mode predicted by the optimization, which does not emerge without the skeleton. Modal analysis further suggests that the skeleton enables deformation modes near the actuation frequency that promote effective stride generation.
arXiv:2605.29330v1 Announce Type: new
Abstract: Current Earth observation benchmarks focus on measuring performance on diverse tasks and applications, typically measuring generalization in-distribution. But when models are deployed, they must generalize to myriad out-of-distribution scenarios, such as new time periods, geographies, scales, and sensors. We introduce EarthShift: the first public testbed for benchmarking robustness across multiple realistic distribution shifts encountered in remote sensing. EarthShift enables users to measure distributional robustness by comparing performance in- and out-of-distribution using datasets from paired datasets from different sources, temporal windows, geographic locations, and sensors. Our experiments on 8 geospatial foundation models (GFMs) and 11 tasks covering 5 shift types show that GFMs consistently perform 15-20% worse out-of-distribution on average regardless of model architecture, size, pre-training or fine-tuning strategy. We show that GFM robustness is similar to that of generic vision foundation models, and even fully-supervised models. This highlights a need for future research to strive for improvements in distributional robustness, not just performance, which can be benchmarked using EarthShift. We release our code and datasets to provide a testbed to guide future work to create foundation models that are robust and reliable in real-world applications. Code and data for EarthShift are available at: https://earthshift.github.io
arXiv:2605.29410v1 Announce Type: new
Abstract: Reliable midair docking between small unmanned aerial vehicles (UAVs) is essential for modular aerial cooperation and manipulation, but it requires precise relative-pose control and repeatable platform under tight thrust and payload constraints. We present a dual-drone docking platform where two quadrotors operate in a leader-follower formation and dock using a lightweight modular frame with passive magnetic latching. A progress-aware mission supervisor manages phase transitions: approach, alignment, capture, and settle. This platform integrates a complete hardware-software stack (ROS 2 with Crazyflie/PX4 interfaces) and synchronized logging for benchmark evaluation. We evaluate the platform in simulation and real-world experiments using quantitative metrics such as formation error, baseline and yaw consistency, docking success rate, time-to-dock, and failure-mode statistics. The platform enables statistically grounded comparison of docking supervision and synchronization strategies and provides a practical testbed for modular aerial cooperation and repeatable midair aerial manipulation.
arXiv:2604.11080v2 Announce Type: replace
Abstract: Rotation-based Post-Training Quantization (PTQ) has emerged as a promising solution for mitigating activation outliers in the quantization of Large Language Models (LLMs). Global rotation methods achieve inference efficiency by fusing activation rotations into attention and FFN blocks, but suffer from limited expressivity as they are constrained to use a single learnable rotation matrix across all layers. To tackle this, layer-wise transformation methods emerged, achieving superior accuracy through localized adaptation. However, layer-wise methods cannot fuse activation rotation matrices into weights, requiring online computations and causing significant overhead. In this paper, we propose ReSpinQuant, a quantization framework that resolves such overhead by leveraging offline activation rotation fusion and matching basis using efficient residual subspace rotation. This design reconciles the high expressivity of layer-wise adaptation with only negligible inference overhead. Extensive experiments on W4A4 and W3A3 quantization demonstrate that ReSpinQuant achieves state-of-the-art performance, outperforming global rotation methods and matching the accuracy of computationally expensive layer-wise methods with minimal overhead.
arXiv:2605.28975v1 Announce Type: new
Abstract: We study the log-alignment ratio (LAR), a measure of parameter-activation alignment, introduced in parameterization theory. We reformulate it as the overlap between a weight spectrum $p$ of the normalized squared singular values of a matrix and an activation spectrum $q$ of the normalized squared projections of inputs onto its singular directions. We show that unembedding LAR tracks the transition between memorization and generalization in two different settings by capturing the spread of $p$ and $q$ during training. In grokking, LAR predicts the effective dimension of the learned function: $k \approx n^{2(1-\text{LAR})}$, where $n$ is the input dimension of the matrix. In 3B-parameter language model pre-training, its deviation from a non-overfitting baseline tracks the generalization gap, and its rate of decline increases as overfitting approaches. LAR is computable from quantities available during the forward pass with negligible computational overhead, and requires no held-out validation data.
arXiv:2605.25090v2 Announce Type: replace
Abstract: We improve upon the Johnson-type bound of Hayashi and Yasunaga for insertion-deletion codes by encoding each local list into a binary constant-weight code. The resulting local list-size bound is tight for sufficiently large alphabets. Applying the McEliece--Rodemich--Rumsey--Welch bound to this constant-weight formulation yields an asymptotic rate bound that strictly improves on Yasunaga's Elias-type bound in the nontrivial range.
arXiv:2605.29464v1 Announce Type: cross
Abstract: In randomized trials involving multiple treatments, bivariate survival outcomes present significant analytical challenges for making decisions. This paper addresses the problem of deriving optimal individualized treatment rules to maximize the joint survival probability beyond fixed time points $(t_1, t_2)$ through deep neural networks, while accounting for right censoring. We propose a novel approach that models treatment rules via stochastic policies, coupling marginal accelerated failure time models via link function to capture bivariate dependence. To enhance robustness and effectiveness of decision making, we introduce an adaptive prediction-powered method that leverages auxiliary predictions from machine learning models.
arXiv:2605.29169v1 Announce Type: new
Abstract: Traditional cryptography, rooted in problems, e.g., integer factorisation or discrete log, is inevitably vulnerable to a fully operational quantum computer. Although it remains an engineering frontier, the looming threat extends to encrypted data stored today, which could be decrypted in the future with quantum capabilities. To safeguard against this eventuality, the backbone of the modern quantum-safe cryptography is the Shortest Vector Problem (SVP). We enhance Laarhoven's treatment of Ajtai et al.'s sieving as a genetic algorithm (GA) for the SVP by incorporating domain-informed SVP representation and crossover while naturally extending application to the module lattices.
arXiv:2605.28960v1 Announce Type: new
Abstract: Fundamental understanding of interatomic forces in molecules must emerge from quantum mechanics, yet widely used empirical force fields rely on simplified mechanistic approximations that often fail to capture the complexity of many-body systems. Here we employ recent developments in quantum field theory (QFT) for long-range electron correlation and machine learning force fields (MLFFs) to directly compute the depth and scatter of interatomic forces for molecular systems containing hundreds of atoms. We find that while the average interaction strength decays polynomially with interatomic separation, the interaction scatter remains robust and exhibits substantial anisotropy. Both QFT and MLFFs demonstrate that increasing the molecular size further amplifies this scatter and anisotropy -- a phenomenon not considered in traditional textbook empirical models. These results provide new benchmarks for force models, shift the focus from interacting atoms to interacting ``hotspots'' that might determine the folding pathways of (bio)polymers, and rationalize why MLFFs are uniquely successful in capturing the nuances of complex molecular systems. Our findings offer a roadmap for the development of more accurate and quantum-aware molecular force fields.
arXiv:2604.05157v3 Announce Type: replace
Abstract: Computer-Use Agents (CUAs) leverage large language models to execute GUI operations on desktop environments, yet they generate actions without evaluating action quality, leading to irreversible errors that cascade through subsequent steps. We propose IntentScore, a plan-aware reward model that learns to score candidate actions from 398K offline GUI interaction steps spanning three operating systems. IntentScore trains with two complementary objectives: contrastive alignment for state-action relevance and margin ranking for action correctness. Architecturally, it embeds each candidate's planning intent in the action encoder, enabling discrimination between candidates with similar actions but different rationales. IntentScore achieves 97.5% pairwise discrimination accuracy on held-out evaluation. Deployed as a re-ranker for Agent S3 on OSWorld, an environment entirely unseen during training, IntentScore improves task success rate by 6.9 points, demonstrating that reward estimation learned from heterogeneous offline trajectories generalizes to unseen agents and task distributions.
arXiv:2603.18859v2 Announce Type: replace
Abstract: Reinforcement learning (RL) shows promise for enhancing LLM agentic reasoning, yet sparse terminal rewards hinder fine-grained optimization. Process reward modeling offers an alternative but incurs high computational costs, reward hacking risks, and annotation bottlenecks. We introduce RewardFlow, a lightweight method for estimating state-level rewards in agentic reasoning. By constructing state graphs that capture the intrinsic topological structure of trajectories, RewardFlow performs topology-aware propagation to estimate each state's contribution to success, yielding principled, annotation-free dense rewards. Used for RL optimization, RewardFlow substantially outperforms prior baselines across four agentic benchmarks: +6.2% average success rate on text-based tasks, +29.7% on visual reasoning over the strongest baseline across three model scales, and +10% accuracy on DeepResearch, with superior robustness and training efficiency. The implementation of RewardFlow is publicly available at https://github.com/tmlr-group/RewardFlow.
arXiv:2603.16673v4 Announce Type: replace
Abstract: Embodied robotic systems increasingly rely on large language model (LLM)-based agents to support high-level reasoning, planning, and decision-making during interactions with the environment. However, invoking LLM reasoning introduces substantial computational latency and resource overhead, which can interrupt action execution and reduce system reliability. Excessive reasoning may delay actions, while insufficient reasoning often leads to incorrect decisions and task failures. This raises a fundamental question for embodied agents: when should the agent reason, and when should it act? In this work, we propose RARRL (Resource-Aware Reasoning via Reinforcement Learning), a hierarchical framework for resource-aware orchestration of embodied agents. Rather than learning low-level control policies, RARRL learns a high-level orchestration policy that operates at the agent's decision-making layer. This policy enables the agent to adaptively determine whether to invoke reasoning, which reasoning role to employ, and how much computational budget to allocate based on current observations, execution history, and remaining resources. Extensive experiments, including evaluations with empirical latency profiles derived from the ALFRED benchmark, show that RARRL consistently improves task success rates while reducing execution latency and enhancing robustness compared with fixed or heuristic reasoning strategies. These results demonstrate that adaptive reasoning control is essential for building reliable and efficient embodied robotic agents.
arXiv:2604.17176v2 Announce Type: replace
Abstract: Future spacecraft operations require autonomy that can interpret high-level mission intent while preserving safety. However, existing trajectory optimization still relies heavily on expert-crafted formulations and does not support intent-conditioned decision-making. This paper proposes an intent-aligned spacecraft guidance framework that links high-level reasoning and safe trajectory optimization through explicit intermediate abstractions, based on behavior sequences and waypoint constraints. A foundation model first predicts an intent-aligned behavior plan, a waypoint generation model then converts it into waypoint constraints, and the safe trajectory is computed via optimization. This decomposition enables scalable supervision without sacrificing safety. Numerical experiments in close-proximity operation scenarios demonstrate that the proposed pipeline achieves over 90\% SCP convergence and yields a $1.5\times$ higher rate of generating trajectories that satisfy the top intent-prioritized performance criteria than heuristic decision-making. These results support the use of intermediate behavior abstraction as a practical interface between foundation-model reasoning and safety-critical onboard spacecraft autonomy.
arXiv:2604.11088v2 Announce Type: replace
Abstract: Random rules improve a coding agent's task performance as much as expert-curated ones (both $+13.8$pp on a discriminative subset of SWE-bench Verified), and in our data every individually beneficial rule is a negative constraint ("do not refactor unrelated code"), while every individually harmful one is a positive directive ("follow code style"). We arrive at these findings through the first large-scale controlled study of agent rule files (\texttt{CLAUDE.md}, \texttt{.cursorrules}, and the broader family of agent skills, plugin manifests, and persona definitions): we scrape 679 rule files (25{,}532 rules) from GitHub and conduct over 5{,}000 agent runs of Claude Code with Claude Opus 4.6 on SWE-bench Verified. Three patterns emerge. (i) Rule polarity cleanly separates beneficial from harmful rules; we read this through the lens of potential-based reward shaping (PBRS). (ii) Performance gains are largely content-independent: random, shuffled, mismatched-domain, and unconverted-format rule files all match curated rules, pointing to a context priming mechanism. (iii) Individual rules often appear harmful in isolation yet do not visibly accumulate damage in ensemble: pass rates remain stable across rule counts from 0 to 50. These findings expose a hidden reliability risk in the rapidly growing ecosystem of community-authored rules and skills, and they yield a clear principle for safer agent configuration: constrain what agents must not do, rather than prescribing what they should.
arXiv:2604.07789v2 Announce Type: replace
Abstract: Recent advances in language model (LM) agents have significantly improved automated software engineering (SWE). Prior work has proposed various agentic workflows and training strategies as well as analyzed failure modes of agentic systems on SWE tasks, focusing on several contextual information signals: Reproduction Test, Regression Test, Edit Location, Execution Context, and API Usage. However, the individual contribution of each signal to overall success remains underexplored, particularly their ideal contribution when intermediate information is perfectly obtained. To address this gap, we introduce Oracle-SWE, a unified method to isolate and extract oracle information signals from SWE benchmarks and quantify the impact of each signal on agent performance. To further validate the pattern, we evaluate the performance gain of signals extracted by strong LMs when provided to a base agent, approximating real-world task-resolution settings. These evaluations aim to guide research prioritization for autonomous coding systems.
arXiv:2604.06811v2 Announce Type: replace
Abstract: Skill-based agent systems tackle complex tasks by composing reusable skills, improving modularity and scalability while introducing a largely unexamined security attack surface. We propose SkillTrojan, a backdoor attack that targets skill implementations rather than model parameters or training data. SkillTrojan embeds malicious logic inside otherwise plausible skills and leverages standard skill composition to reconstruct and execute an attacker-specified payload. The attack partitions an encrypted payload across multiple benign-looking skill invocations and activates only under a predefined trigger. SkillTrojan also supports automated synthesis of backdoored skills from arbitrary skill templates, enabling scalable propagation across skill-based agent ecosystems. To enable systematic evaluation, we release a dataset of 3,000+ curated backdoored skills spanning diverse skill patterns and trigger-payload configurations. We instantiate SkillTrojan in a representative code-based agent setting and evaluate both clean-task utility and attack success rate. Our results show that skill-level backdoors can be highly effective with minimal degradation of benign behavior, exposing a critical blind spot in current skill-based agent architectures and motivating defenses that explicitly reason about skill composition and execution. Concretely, on EHR SQL, SkillTrojan attains up to 97.2% ASR while maintaining 89.3% clean ACC on GPT-5.2-1211-Global.
arXiv:2605.29359v1 Announce Type: new
Abstract: Compute governance proposals often rely on the assumption that frontier AI training requires large, detectable computing clusters. However, recent advances in distributed training algorithms could allow developers to conduct frontier-scale training on distributed agglomerations of hardware, rather than needing large datacenter facilities. Developers who prefer not to be constrained by regulations may structure their hardware in a manner that evades the registration and monitoring requirements associated with compute governance. Therefore, regulations must be designed to detect and prevent illicit distributed training operations. This paper evaluates the feasibility of such evasion and outlines recommended countermeasures, including whistleblowing, chip tracking, forensic accounting, and memory and compute thresholds for clusters.
arXiv:2603.27518v3 Announce Type: replace
Abstract: Aligned language models that are trained to refuse harmful requests also exhibit over-refusal: they decline safe instructions that seemingly resemble harmful instructions. A natural approach is to ablate the global refusal direction, steering the hidden-state vectors away or towards the harmful-refusal examples, but this corrects over-refusal only incidentally while disrupting the broader refusal mechanism. In this work, we analyse the representational geometry of both refusal types to understand why this happens. We show that harmful-refusal directions are task-agnostic and can be captured by a single global vector, whereas over-refusal directions are task-dependent: they reside within the benign task-representation clusters, vary across tasks, and span a higher-dimensional subspace. Linear probing suggests that the two refusal types are representationally distinct from the early transformer layers. These findings provide a mechanistic explanation of why global direction ablation alone cannot address over-refusal, and establish that task-specific geometric interventions are necessary.
arXiv:2603.14026v3 Announce Type: replace
Abstract: This work establishes the well-posedness and a priori error analysis for the mixed FEEC-type finite element approximation of the three-dimensional vector Laplace boundary value problem subject to the Dirichlet boundary condition. The Dirichlet condition disrupts the structure of the standard de Rham complex, requiring the vorticity to be sought in a non-standard function space to achieve well-posedness. We derive error estimates that confirm the numerically observed suboptimal convergence rates. In particular, by developing a discrete Caccioppoli-type inequality for discrete curl-harmonic functions, we prove $(k-1/2)$-th order convergence in the energy norm on general domains and $k$-th order convergence in $L^2$ on convex domains, where $k \ge 1$ denotes polynomial degree of the finite element spaces. These results extend the previous two-dimensional analysis developed in [Arnold, D.N., Falk, R.S. and Gopalakrishnan, J., 2012. Mixed finite element approximation of the vector Laplacian with Dirichlet boundary conditions. Mathematical Models and Methods in Applied Sciences, 22(9), p.1250024.]~to three-dimensional domains with general topology. As a direct application, a discretization of the Stokes problem in vorticity-velocity-pressure form is studied.
arXiv:2603.23069v3 Announce Type: replace
Abstract: The task of authorship style transfer involves rewriting text in the style of a target author while preserving the meaning of the original text. Existing style transfer methods train a single model on large corpora to model all target styles at once: this high-cost approach offers limited flexibility for target-specific adaptation, and often sacrifices meaning preservation for style transfer. In this paper, we propose AuthorMix: a lightweight, modular, and interpretable style transfer framework. We train individual, style-specific LoRA adapters on a small set of high-resource authors, allowing the rapid training of specialized adaptation models for each new target via learned, layer-wise adapter mixing, using only a handful of target-style training examples. AuthorMix outperforms existing, SoTA style-transfer baselines-as well as GPT-5.1-for low-resource targets, achieving the highest overall score and substantially improving meaning preservation in both automatic and human evaluations.
arXiv:2605.29564v1 Announce Type: new
Abstract: When using reinforcement learning (RL) for contact-rich robotic manipulation, vision can provide task-relevant information that accelerates learning beyond what proprioception alone can achieve. However, vision-enabled policies tend to overfit to the visual conditions seen during training, limiting their robustness and transferability. We present a human-in-the-loop RL framework that employs teacher-student distillation to achieve robust performance across multiple task variants, trained entirely in the real world without requiring domain randomization or data augmentation. A vision-enabled teacher distills its knowledge into a vision-free student that relies solely on pose, twist, and wrench sensing, combining fast training with strong task generalization. On the real-world NIST assembly benchmark board, our approach achieves 95\% overall success after approximately 50 minutes of training on 3 representative tasks, including robust generalization to 8 unseen task variants. Fine-tuning with distillation achieves full success on the most challenging task. We demonstrate that the resulting policies outperform baselines in both robustness and adaptability.
arXiv:2603.13687v3 Announce Type: replace
Abstract: Murray's cubic branching law ($\alpha=3$) predicts a universal diameter scaling exponent for all hierarchical transport networks, yet arterial trees yield $\alpha \sim 2.7-2.9$. We show that this discrepancy has a structural origin: Murray's universality is an artifact of cost homogeneity, not a biological property. Incorporating the empirical vessel-wall thickness law $h(r)=c_0 r^p$ ($p \approx 0.77$) introduces a third metabolic cost term $\propto r^{1+p}$ that renders the cost function inhomogeneous with incommensurate scaling exponents. By Cauchy's functional equation, homogeneity is necessary and sufficient for a universal branching exponent to exist; its absence implies non-universality, and Murray's law is identified as a singular degeneracy of the cost-function family rather than a general principle. We prove that the resulting scale-dependent exponent satisfies the strict bounds $(5+p)/2 < \alpha^*(Q) < 3$ independently of flow asymmetry (Theorem 4, Corollary 5). The static wall-tissue mechanism bounds the symmetric bifurcation exponent to $\alpha_t \in [2.90, 2.94]$ from measured parameters, marking a first-order symmetry breaking from Murray's law that narrows the empirical gap by one-third. The remaining discrepancy with the cardiovascular mean ($\alpha_{exp} \approx 2.70$) is not a model failure but a mathematical necessity that signals the independent contribution of pulsatile wave dynamics. Additionally, the wall cost breaks Murray's topological degeneracy, bounding the optimal branching number to small finite integers; binary bifurcation emerges as the physiologically selected minimum under steric constraints.