arXiv:2603.23351v2 Announce Type: replace
Abstract: Laser-enhanced contact optimization (LECO) has emerged as an important method for simultaneously reducing contact resistivity and metallization-induced recombination in advanced crystalline silicon solar cells, thereby enabling concurrent gains in fill factor and open-circuit voltage, particularly in TOPCon devices. However, broader industrial transferability remains constrained by the need to preserve these gains within a narrow process window and by unresolved, architecture-dependent questions regarding the kinetic stability of some LECO-modified interfaces. LECO is therefore examined in this review as a coupled multiphysics process that links localized electrothermal activation and microstructural evolution to device-level electrical signatures through an instantaneous regime map and a reliability classification based on time-dependent drift. A predictive workflow is outlined that couples transient electrothermal modeling with reduced state metrics, including effective diffusion depth and local areal energy density, and propagates calibrated thresholds across the recipe space. The framework separates stable optimization from marginal activation and latent damage, while explaining why fine-line scaling and copper-containing contact stacks can tighten stability margins through current localization and diffusion-barrier constraints. These insights provide a basis for reliability-aware process-window design and future digital-twin-assisted optimization of LECO for scalable, high-efficiency silicon photovoltaics.
Science Journals
arXiv:2602.22870v3 Announce Type: replace
Abstract: The generalized egg dropping problem is a classic challenge in sequential decision-making. Standard dynamic programming evaluates the minimax minimum number of tests in $\mathcal{O}(K \cdot N^2)$ time. A known approach formulates the testable thresholds as a partial sum of binomial coefficients and applies binary search to reduce the time complexity to $\mathcal{O}(K \log N)$. In this paper, we demonstrate that binary search over the complete sequential test domain is suboptimal. By restricting a binary search over multiples of $K$, we isolate a dynamic structural envelope that guarantees convergence. We prove that this boundary balances the search depth against the combinatorial evaluation cost, cancelling the $K$ variable to strictly bound the search phase to $\mathcal{O}(\log N)$. Combined with an incremental traversal, our algorithm eliminates the standard bottlenecks. Furthermore, we formulate an explicit $\mathcal{O}(1)$ space policy to dynamically reconstruct the optimal decision tree.
arXiv:2603.04459v3 Announce Type: replace
Abstract: The rapid expansion of research in LLM safety presents challenges in tracking advancements, making benchmarks important evaluation infrastructures for identifying key trends and facilitating systematic comparisons. Yet no systematic assessment exists of their code quality and runnability, nor of what factors are associated with the community's adoption of certain benchmarks over others. To address this gap, we conduct a systematic measurement study of 31 LLM safety benchmarks (covering prompt injection, jailbreak, and hallucination) with 382 non-benchmark papers as a control group, combining automated static analysis, human runnability testing (220+ person-hours), and bibliometric analysis. We find that only 39\% of benchmark repositories can run without modification, only 16\% provide flawless installation guides, and a mere 6\% include ethical considerations despite containing potentially harmful content. These deficiencies persist across the study period with no significant improvement. Analyzing adoption factors, we find that benchmark adoption correlates with author prominence and code runnability, but not with code quality standards such as Pylint score and maintainability, suggesting that the community's benchmark selection does not reward higher coding standards. Based on these results, we identify potential safety and reliability concerns. Some safety benchmark repositories openly expose harmful content, such as successful jailbreak responses, without any ethical warning or access control, effectively serving as unguarded attack resources. Furthermore, when benchmarks require ad-hoc modifications to run, downstream safety evaluations across different papers may not be comparable. We present case studies illustrating these concrete consequences and propose a targeted checklist to help benchmark contributors improve code quality, documentation, and ethical practices.
arXiv:2602.16274v2 Announce Type: replace
Abstract: We present the first regret bound for classical online Q-learning in infinite-horizon discounted Markov decision processes (MDPs), without relying on optimism or bonus terms. We first analyze Boltzmann Q-learning with decaying temperature and show that its regret depends critically on the suboptimality gap of the MDP: for sufficiently large gaps, the regret is sublinear, while for small gaps it deteriorates and can approach linear growth. To address this limitation, we study a Smoothed $\epsilon_n$-Greedy exploration scheme that combines $\epsilon_n$-greedy and Boltzmann exploration, for which we prove a gap-robust regret bound of near-$\tilde{O}(N^{9/10})$. We also obtain sample complexity guarantees, with both regret and sample complexity bounds holding with high probability. To analyze these algorithms, we develop a high-probability concentration bound for contractive Markovian stochastic approximation with iterate- and time-dependent transition dynamics. This bound may be of independent interest as the contraction factor in our framework is allowed to converge to one asymptotically.
arXiv:2505.24573v2 Announce Type: replace
Abstract: In this work, we introduce maximally recoverable codes with locality and availability. We consider locally repairable codes (LRCs) where certain subsets of $ t $ symbols belong each to $ N $ local repair sets, which are pairwise disjoint after removing the $ t $ symbols, and which are of size $ r+\delta-1 $ and can correct $ \delta-1 $ erasures locally. Classical LRCs with $ N $ disjoint repair sets and LRCs with $ N $-availability are recovered when setting $ t = 1 $ and $ t=\delta-1=1 $, respectively. Allowing $ t > 1 $ enables our codes to reduce the storage overhead for the same locality and availability. In this setting, we define maximally recoverable LRCs (MR-LRCs) as those that can correct any globally correctable erasure pattern given the locality and availability constraints. We then identify a large class of global erasure patterns that can be corrected by such MR-LRCs and prove that they are all the correctable patterns when $ t=1 $. We provide three explicit constructions of LRCs that can correct such erasure patterns (thus MR-LRCs for $ t=1 $), based on MSRD codes, each attaining the smallest finite-field sizes for some parameter regime. Finally, we extend the known lower bound on finite-field sizes from classical MR-LRCs to our setting (for any value of $ t $).
arXiv:2605.15412v1 Announce Type: new
Abstract: Modern quantitative trading increasingly relies on systematic models to extract predictive signals from large-scale financial data, where alpha factor discovery plays a central role in transforming market observations into tradable signals. Recent LLM-based methods have shown promise in automating factor generation, but most of them still rely on prompt-level generation--evaluation--feedback loops for iterative optimization. As the loop becomes longer, repeatedly appended historical candidates and feedback can cause context explosion, increase inference cost, dilute useful information, and introduce feedback drift. Moreover, these methods often depend on very large LLMs whose stable generation preferences may lead to structurally similar expressions, redundant candidates, and search stagnation. To address these limitations, we propose \textsc{QuantEvolver}, a self-evolving alpha factor discovery framework based on reinforcement fine-tuning. Instead of accumulating feedback in the prompt, \textsc{QuantEvolver} converts executable quantitative evaluation into policy updates, enabling a Miner LLM to internalize historical optimization experience through parameter learning. Specifically, \textsc{QuantEvolver} constructs high-quality seed factors, builds diverse seed--time-window training tasks, generates executable Factor DSL expressions, evaluates them through Regime Backtest, and optimizes the Miner LLM with Diversity-Complementarity Reward. During training, high-quality factors are continuously accumulated in a Mined Factor Database, which serves as the final discovered factor library. Extensive experiments on three realistic market benchmarks demonstrate the effectiveness of \textsc{QuantEvolver}, which consistently improves the primary evaluation metric of each task over existing LLM-based alpha factor discovery baselines, produces higher-quality and more complementary factor pools.
arXiv:2605.02609v2 Announce Type: replace
Abstract: The effectiveness of active learning hinges on the choice of the acquisition criterion by which a learning algorithm selects potentially informative data points whose label is subsequently queried. This paper proposes a novel gradient-based acquisition criterion, derived from a generalization bound introduced by Luo et al. (2022). This criterion can be applied in lieu of uncertainty measures in uncertainty sampling, or incorporated into diversity-based methods that consider the spread of sampled points in addition to the uncertainty of their labels. We provide a theoretical justification of the proposed acquisition criterion, and demonstrate its effectiveness in an empirical evaluation.
arXiv:2605.15409v1 Announce Type: new
Abstract: In this paper, we introduce a model for a buoyancy-driven, air-to-air heat exchanger. This model, derived from first principles, features a conservative boundary condition at inflow based on the compressible Bernoulli equation, and a dissipative boundary condition at outflow based on pressure continuity. We solve for the steady-state behavior numerically and asymptotically, with excellent agreement between the two, and we study the tradeoff between the efficiency and air flow predicted by the model.
arXiv:2605.15408v1 Announce Type: new
Abstract: We show that the covariance matrix of any cylindrically symmetric coherent orbital angular momentum (OAM) eigenmode with quantum number $\ell$ takes a universal form depending only on $\langle r^2\rangle$, $\langle k_r^2\rangle$, and $\ell$, independently of the radial profile, and that this form is identical to the covariance matrix of a twisted Gaussian Schell-model (TGSM) beam.} More specifically, both matrices share the same pattern of zero and nonzero entries, with the off-diagonal blocks proportional to $\ell$ and the TGSM twist parameter $u$, respectively. This result holds for an arbitrary radial profile and provides direct term-by-term identification of parameters between the two sets of beams. We work out the correspondence in detail for three important families: Laguerre--Gaussian (LG), Bessel--Gaussian, and perfect vortex beams (PVBs), and derive the conditions under which each coherent OAM mode maps onto a physically realizable TGSM beam. {Because the covariance matrix governs second-moment evolution under arbitrary ABCD (symplectic) transformations, any two beams sharing the same covariance matrix are second-order indistinguishable at every propagation plane. In particular, the matched TGSM and coherent OAM beams share identical beam-width evolution, far-field divergence, and $M^2$ beam-quality factor.} In particular, the well-developed TGSM propagation toolbox applies directly to the second-order moment evolution of the three coherent families. We further show that within each beam family the covariance matrix uniquely determines the beam parameters, with exact uniqueness established for LG modes. Additional results include cross-family second-moment equivalence conditions and a proof that PVB modes form a complete orthonormal basis in the limit $w\to 0$.
arXiv:2601.07820v2 Announce Type: replace
Abstract: In human conversation, both interlocutors play an active role in maintaining mutual understanding. When listeners are uncertain about what speakers mean, for example, they can request clarification. It is an open question for language models whether they can assume a similar listener role, recognizing and expressing their own uncertainty through clarification. We argue that reference games are a suitable testbed to approach this question as they are controlled, self-contained, and make clarification needs explicit and measurable. To test this, we evaluate three vision-language models comparing a baseline reference resolution task to an experiment where the models are instructed to request clarification when uncertain. The results suggest that even in such simple tasks, models often struggle to recognize internal uncertainty and translate it into adequate clarification behavior. This demonstrates the value of reference games as testbeds for interaction qualities of (vision and) language models.
arXiv:2605.15754v1 Announce Type: new
Abstract: Driven by rapid advances in artificial intelligence and modern GPU computing capabilities, deep learning methods based on the optimization paradigm have provided new pathways to solve spatiotemporal physical problems, whose mathematical core lies in solving partial differential equations (PDEs). As an emerging class of function-space learning methods, neural operators (NOs) have exhibited great potential in efficient PDE solving. However, existing mainstream neural operator frameworks suffer from critical bottlenecks when modeling time-dependent PDEs over long time horizons, including accuracy degradation, insufficient stability, high training costs, and excessive memory consumption, which severely limit their practical deployment. To address these challenges in long-time prediction with neural operators, we propose a novel spatiotemporally decoupled physics-informed neural operator architecture, termed the physics-informed Stone-Weierstrass neural operator (PI-SWNO). The design is theoretically grounded in the decoupling paradigm combining time-invariant spatial basis functions with time-varying evolution coefficients, as well as the Stone-Weierstrass approximation theorem. By encoding spatial and temporal information via two separate subnetworks, the framework structurally mitigates the accumulation of errors over extended time intervals. Furthermore, we introduce a time-marching batch-wise sampling strategy to resolve the memory bottleneck of full-range modeling over extended time spans, ensuring continuity and convergence of full-time-domain solutions.
arXiv:2605.15755v1 Announce Type: new
Abstract: Multimodal large language models (MLLMs) can produce fluent artwork emotion explanations, but they often suffer from attribute flooding: they enumerate many visible formal attributes without identifying which cues actually support the affective judgment. We therefore formulate artwork emotion understanding as Attribute-Grounded Selective Reasoning (AGSR), where predefined formal attributes serve as evidence units and only emotionally operative attributes should enter the final interpretation. To make this problem measurable, we extend EmoArt, originally introduced at ACM MM 2025 as a 132,664-artwork resource with content, formal-attribute, valence-arousal, and emotion annotations, by adding a 1,400-artwork human salience extension annotated by 15 art-trained annotators. This extension provides instance-level supervision for distinguishing attributes that are merely present from those that are emotionally salient. We further propose FAB-G (Formal-Attribute Bottleneck-Guided reasoning), a supervised multi-agent framework that first predicts attribute-level salience and then constrains downstream emotional analysis to the retained cues. Experiments show that FAB-G yields consistent gains in emotion, arousal, and valence prediction, achieves stronger agreement with human-marked salient attributes under Dice and Tversky metrics, and produces substantially more compact final explanations than prompting-based baselines. Cross-dataset evaluation further suggests that attribute-grounded salience selection transfers beyond the source distribution of EmoArt, while also revealing attribute-specific boundary cases. The dataset and project page are available at https://zhiliangzhang.github.io/EmoArt-130k/
arXiv:2603.04261v2 Announce Type: replace
Abstract: Evidence on the effectiveness of Man-At-The-End (MATE) software protections, such as code obfuscation, has mainly come from limited empirical research. Recently, however, an automatable method was proposed to obtain statistical models of the required effort to attack (protected) software. The proposed method was sketched for a number of attack strategies but not instantiated, evaluated, or validated for those that require human interaction with the attacked software.
In this paper, we present a full instantiation of the method to obtain statistical effort models for game resource localisation attacks, which represent a major step towards creating game cheats, a prime example of MATE attacks. We discuss in detail all relevant aspects of our instantiation and the results obtained for two game use cases. Our results confirm the feasibility of the proposed method and its utility for decision support for users of software protection tools. These results open up a new avenue for obtaining models of the impact of software protections on reverse engineering attacks, which will scale much better than empirical research involving human participants.
arXiv:2603.03243v2 Announce Type: replace
Abstract: We present Whole-Body Mobile Manipulation Interface (HoMMI), a data collection and policy learning framework that learns whole-body mobile manipulation directly from robot-free human demonstrations. We augment UMI interfaces with egocentric sensing to capture the global context required for mobile manipulation, enabling portable, robot-free, and scalable data collection. However, naively incorporating egocentric sensing introduces a larger human-to-robot embodiment gap in both observation and action spaces, making policy transfer difficult. We explicitly bridge this gap with a cross-embodiment hand-eye policy design, including an embodiment agnostic visual representation; a relaxed head action representation; and a whole-body controller that realizes hand-eye trajectories through coordinated whole-body motion under robot-specific physical constraints. Together, these enable long-horizon mobile manipulation tasks requiring bimanual and whole-body coordination, navigation, and active perception. Results are best viewed on: https://hommi-robot.github.io
arXiv:2605.16245v1 Announce Type: new
Abstract: Generative artificial intelligence (AI) is increasingly integrated into the online platforms where humans exchange opinions; large language models (LLMs) now polish users' posts on LinkedIn and provide context for content shared on X. While prior work has shown that AI can express biased opinions and shape individuals' opinions during human-AI interactions, less attention has been paid to its influence on collective opinion formation when mediating human-to-human communication. We address this gap via a combination of empirical and theoretical analyses. We show empirically that LLMs from multiple popular families introduce directional biases when instructed to edit human-written texts on contested topics, for example, nudging texts in favor of gun control and against atheism. Building on this observation, we introduce a mathematical model of opinion dynamics in which an AI system sits between users on a social network, transforming the opinions they express and perceive. By analytically characterizing the equilibrium of this model and performing simulations on real social network data, we show that biases introduced by AI in human-to-human communication can be amplified through the network and shift collective opinion in their direction. In light of these findings, we investigate whether such biases are controllable by online platforms. We audit the "Explain this post" feature on X and find evidence of pro-life bias in Grok's outputs on abortion-related content, which we trace back to specific design choices. We conclude with a discussion of the broader implications of our findings in relation to ongoing legislative efforts in the European Union.
arXiv:2605.14884v2 Announce Type: replace
Abstract: Graph Neural Networks (GNNs) have advanced significantly in handling graph-structured data, but a comprehensive framework for evaluating explainability remains lacking. Existing evaluation frameworks primarily involve post-hoc explanations, and operate in the setting where multiple methods generate a suite of explanations for a single model. This makes comparison of explanations across models difficult. Evaluation of inherently interpretable models often targets a specific aspect of interpretability relevant to the model, but remains underdeveloped in terms of generating insight across a suite of measures. We introduce AIM, a comprehensive framework that addresses these limitations by measuring Accuracy, Instance-level explanations, and Model-level explanations. AIM is formulated with minimal constraints to enhance flexibility and facilitate broad applicability. Here, we use AIM in a pipeline, extracting explanations from inherently interpretable GNNs such as graph kernel networks (GKNs) and prototype networks (PNs), evaluating these explanations with AIM, identifying their limitations and obtaining insights to their characteristics. Taking GKNs as a case study, we show how the insights obtained from AIM can be used to develop an updated model, xGKN, that maintains high accuracy while demonstrating improved explainability. Our approach aims to advance the field of Explainable AI (XAI) for GNNs, providing more robust and practical solutions for understanding and improving complex models.
arXiv:2605.15406v1 Announce Type: new
Abstract: This work presents a new approach for implementing polymorphism for bottom-up relational languages, without monomorphization. We begin by introducing semiringKanren, a bottom-up weighted relational programming language. We extend this base language to support polymorphism. We describe a new method to compile polymorphic semiringKanren programs into non-polymorphic ones, based on equality patterns and large-enough instances of polymorphic relations. We prove the correctness of this method. Finally, we consider existing work and suggest directions for future research.
arXiv:2605.15404v1 Announce Type: new
Abstract: Large language model personalization typically adapts outputs to user preferences and style but does not account for differences in user evaluation capacity across domains of expertise. This limitation can encourage Professional Domain Drift, where users rely on AI generated reasoning in domains they cannot reliably evaluate. We introduce Capability Conditioned Scaffolding, a typed framework that partitions expertise into strong, mixed, and weak domains and conditions intervention behavior on structured capability profiles. A pilot evaluation across multiple MMLU subsets and four LLM substrates shows consistent profile conditioned intervention behavior, including categorical inversion under profile swapping and selective activation in mixed domain risk zones. These findings suggest that capability aware scaffolding can support more reliable professional human AI collaboration beyond stylistic personalization.
arXiv:2605.16198v1 Announce Type: new
Abstract: We examine one particular dimension of AI governance: how to monitor and audit AI-enabled products and services throughout the AI development lifecycle, from pre-deployment testing to post-deployment auditing. Combining principles from formal methods with SoTA machine learning, we propose techniques that enable AI-enabled product and service developers, as well as third party AI developers and evaluators, to perform offline auditing and online (runtime) monitoring of product-specific (temporally extended) behavioral constraints such as safety constraints, norms, rules and regulations with respect to black-box advanced AI systems, notably LLMs. We further provide practical techniques for predictive monitoring, such as sampling-based methods, and we introduce intervening monitors that act at runtime to preempt and potentially mitigate predicted violations. Experimental results show that by exploiting the formal syntax and semantics of Linear Temporal Logic (LTL), our proposed auditing and monitoring techniques are superior to LLM baseline methods in detecting violations of temporally extended behavioral constraints; with our approach, even small-model labelers match or exceed frontier LLM judges. Our predictive and intervening monitors significantly reduce the violation rates of LLM-based agents while largely preserving task performance. We further show through controlled experiments that LLMs' temporal reasoning shows a pronounced degradation in accuracy with increasing event distance, number of constraints, and number of propositions.
arXiv:2605.15682v1 Announce Type: new
Abstract: Large-scale pre-trained diffusion models have been extensively adopted for real-world image Super-Resolution because of their powerful generative priors through textual guidance. However, when super-resolving high-resolution images with patch-wise inference strategy, most existing diffusion-based SR methods tend to suffer from over-generation, due to the misalignment between the global prompt from LR image and the incomplete semantic information of local patches during each inference step. On the other hand, most existing methods also failed to generate detailed texture in local patches due to the overemphasis on global generation capabilities in network designs and training strategies. To address this issue, we present DreamSR, a novel SR model that suppresses local over-generation and improves fine-detail synthesis, thereby achieving visually faithful results with ultra-high-quality details. Specifically, we propose a dual-branch MM-ControlNet, where the ControlNet generates local textual feature with patch-level prompts while the pre-trained DiT provides global textual feature with global prompts, thereby mitigating over-generation and ensuring semantic consistency across patches. We also design a comprehensive training strategy with stage-specific data processing pipelines and a Receptive-Field Enhancement strategy, enhancing the model's capability to capture patch information and effectively restore local textures. Extensive experiments demonstrate that DreamSR outperforms state-of-the-art methods, providing high-quality SR results. Code and model are available at https://github.com/jerrydong0219/DreamSR.
arXiv:2605.15775v1 Announce Type: new
Abstract: Continual learning (CL) aims to train models sequentially over multiple domains without forgetting previously learned knowledge. However, existing CL methods optimize for in-domain performance and are therefore prone to learning spurious, domain-specific cues (``shortcut learning''), which limits generalization to unseen domains after deployment. In this paper, we address this limitation through continual learning of domain-invariant representation. We introduce a broad class of CL methods that sequentially learn representations capturing invariant structures across domains. Our methods are motivated by the observation that such invariant structures often preserve the underlying causal mechanisms, which can reduce the risk of overfitting to domain-specific cues and thus offer better out-of-domain generalization. Our proposed CL methods combine replay-based training with a tailored sequential invariance alignment to learn -- and preserve -- invariant structures over time. We evaluate our methods under a deployment-oriented protocol that measures performance on unseen target domains. Across six benchmark and real-world datasets spanning vision, medicine, manufacturing, and ecology, our methods consistently outperform existing CL baselines in terms of generalization to unseen target domains. As an ablation, we further show that na\"ive extensions of sequential training with existing domain-invariant representation learning (DIRL) methods provide only limited benefits. To the best of our knowledge, this is the first work to develop domain-invariant representation methods for CL.
arXiv:2509.20349v3 Announce Type: replace
Abstract: Accurate time-series forecasting for complex physical systems is the backbone of modern industrial monitoring and control, yet deep learning models often lack the physical consistency required in regulated environments.To bridge this gap, we introduce Process-Informed Forecasting (PIF) models for temperature in pharmaceutical lyophilization, embedding deterministic production recipes as macro-structural priors. We investigate classical methods (e.g., Autoregressive Integrated Moving Average (ARIMA) model) and modern deep learning architectures, including Kolmogorov-Arnold Networks (KANs). We compare three different loss function formulations that integrate a process-informed trajectory prior: a fixed-weight loss, a dynamic uncertainty-based loss, and a Residual-Based Attention (RBA) mechanism. We evaluate all models not only for accuracy and physical consistency but also for robustness to sensor noise. Furthermore, we test the practical generalizability of the best model in a transfer-learning scenario to a new process. Our results show that PIF models outperform their data-driven counterparts in terms of accuracy, physical plausibility and noise resilience, offering a scalable framework for reliable and generalizable forecasting solutions in critical manufacturing.
arXiv:2505.23678v3 Announce Type: replace
Abstract: While reinforcement learning (RL) over chains of thought has significantly advanced language models in tasks such as mathematics and coding, visual reasoning introduces added complexity by requiring models to direct visual attention, interpret perceptual inputs, and ground abstract reasoning in spatial evidence. We introduce ViGoRL (Visually Grounded Reinforcement Learning), a vision-language model trained with RL to explicitly anchor each reasoning step to specific visual coordinates. Inspired by human visual decision-making, ViGoRL learns to produce spatially grounded reasoning traces, guiding visual attention to task-relevant regions at each step. When fine-grained exploration is required, our novel multi-turn RL framework enables the model to dynamically zoom into predicted coordinates as reasoning unfolds. Across a diverse set of visual reasoning benchmarks--including SAT-2 and BLINK for spatial reasoning, V*bench for visual search, and ScreenSpot and VisualWebArena for web-based grounding--ViGoRL consistently outperforms both supervised fine-tuning and conventional RL baselines that lack explicit grounding mechanisms. Incorporating multi-turn RL with zoomed-in visual feedback significantly improves ViGoRL's performance on localizing small GUI elements and visual search, achieving 86.4% on V*Bench. Additionally, we find that grounding amplifies other visual behaviors such as region exploration, grounded subgoal setting, and visual verification. Finally, human evaluations show that the model's visual references are not only spatially accurate but also helpful for understanding model reasoning steps. Our results show that visually grounded RL is a strong paradigm for imbuing models with general-purpose visual reasoning.
arXiv:2605.16205v1 Announce Type: new
Abstract: Deploying compound LLM agents in adversarial, partially observable sequential environments requires navigating several design dimensions: (1) what the agent sees, (2) how it reasons, and (3) how tasks are decomposed across components. Yet practitioners lack guidance on which design choices improve performance versus merely increase inference costs. We present a controlled study of compound LLM agent design in CybORG CAGE-2, a cyber defense environment modeled as a Partially Observable Markov Decision Process (POMDP). Reward is non-positive, so all configurations operate in a failure-mitigation mode. Our evaluation spans five model families, six models, and twelve configurations (3,475 episodes) with token-level cost accounting. We vary context representation (raw observations vs. a deterministic state-tracking layer with compressed history), deliberation (self-questioning, self-critique, and self-improvement tools, with optional chain-of-thought prompting), and hierarchical decomposition (monolithic ReAct vs. delegation to specialized sub-agents). We find that: (1) Programmatic state abstraction delivers the largest returns per token spent (RPTS), improving mean return by up to 76% over raw observations. (2) Distributing deliberation tools across a hierarchy degrades performance relative to hierarchy alone for all five model families, reaching up to 3.4$\times$ worse mean return while using 1.8-2.7$\times$ more tokens. We call this destructive pattern a deliberation cascade. (3) Hierarchical decomposition without deliberation achieves the best absolute performance for most models, and context engineering is generally more cost-effective than deliberation. These findings suggest a design principle for structured adversarial POMDPs: invest in programmatic infrastructure and clean task decomposition rather than deeper per-agent reasoning, as these strategies can interfere when combined.
arXiv:2605.16206v1 Announce Type: new
Abstract: We present fully kinetic two-dimensional, three-velocity-component (2D3V) PIConGPU simulations of a three-beam direct-drive interaction with a 15 $\mu$m solid-density cryogenic hydrogen cylinder, establishing a predictive numerical baseline for the operational DRACO ($\tau=30$ fs) and upcoming PENELOPE ($\tau=150$ fs) laser facilities at HZDR. The simulations resolve charge-separation fields on the order of 3 TV/m and reveal a robust kinematic bifurcation of the accelerated population into a fast (1-5 MeV) ion beam and a slower bulk (1-100 keV) flow. We demonstrate analytically and numerically that the charge-separation front ($v_{hb}$) is an intrinsically non-quasi-neutral electrostatic double layer that lies outside the closure assumptions of radiation-hydrodynamic models. A simple $2v_{hb}$ reflection scaling derived directly from the front trajectory tracks the centroid of the constant-energy fast-ion band under the impulsive 30 fs driver and the time-varying upper edge of the swept fast-ion band under the sustained 150 fs driver, across both intensities ($a_{0}=12.7$ and 22.0), establishing this non-thermal mechanism as the dominant acceleration pathway. We then scan an external axial magnetic field from 0 T to 10 kT. Laboratory-achievable 20 T fields leave all macroscopic observables unchanged; fields at the kT scale progressively magnetise the MeV hot-electron population, quench the laser-driven charge-separation mechanism, suppress the fast-ion band, and more than double the net-inward compression time of the short-pulse driver-while extending the outer target envelope. A geometric equivalence argument maps these kT-scale results onto larger-diameter cryogenic hydrogen jets.