arXiv:2609.09233v1 Announce Type: new Abstract: How can language model agents effectively leverage libraries of reusable knowledge to solve long-horizon tasks? Recent work has increasingly focused on agent skills: reusable capabilities represented as skill packages, i.e., multi-file bundles containing instructions, scripts, and other resources that help agents perform specific tasks. Agent skills are typically executed by loading their skill instructions into an agent's context and relying on the agent to follow them. As task horizons grow, however, this approach becomes increasingly brittle, because reasoning quality degrades as more information accumulates in the context window. We investigate an alternative approach in which skill packages are instead invoked as subagents. Rather than loading skill instructions into the main context, subagent execution spawns fresh context windows dedicated to solving individual subtasks. We show that subagent execution outperforms agent-skill execution when skill packages expose clear input-output contracts and their instructions encode the procedural knowledge needed to fulfill those contracts. The tradeoff is additional communication overhead, as extra tokens are required to coordinate between the main agent and its subagents. Our results show that the benefit of reusable knowledge depends not only on its content, but also on how it is organized and invoked.

arXiv:2609.09776v1 Announce Type: new Abstract: Frontier gains in language-model reasoning come from reinforcement learning on reasoning traces and are concentrated in domains with a cheap, sound verifier. We argue the field's binding constraint is the verification gap: no scalable, incorruptible reward for reasoning outside formal domains. We make four contributions. (1) Theory: in a joint-Gaussian model of best-of-N selection, verifier-gold correlation rho is the exact exchange rate between test-time compute and capability, and an unsound verifier pays a polynomial penalty N^(1/rho^2); a margin-free copula form predicts realized soundness of real LLM judges to 4% median error. (2) Demonstration: in program-synthesis testbeds with executable ground truth, including a pre-registered scaled replication, unsound verifiers lose Soundness-under-Pressure as optimization grows (0.94 to 0.32 at N=4096) while a sound verifier improves monotonically; reality-anchored settlement beats a frozen verifier under i.i.d. and adversarial pressure, driving the hacking gap from ~0.27 to ~0; soundness scales log-linearly with settled labels, with on-policy settlement ~10x more label-efficient than random labeling. With real LLM judges and unit-test execution as gold, a weak judge loses soundness under best-of-N (p

arXiv:2609.10036v1 Announce Type: new Abstract: Large language model agents produce fluent action sequences across a wide range of tasks, yet they fail in characteristic ways once the environment becomes partially observable. Ambiguous feedback pushes them into premature commitments. A single informative observation can collapse their uncertainty onto the wrong hypothesis. Policies drift as the history grows. We trace these symptoms to a common structural cause. An LLM agent, as commonly deployed, is a history-conditioned policy with no explicit belief over hidden state. We propose an architectural fix. The Belief-State Engine (BSE) is an inference module placed outside the LLM. It maintains a Bayesian posterior over the latent states of a given POMDP (Partially Observable Markov Decision Process) model, and at each decision step it exposes only that posterior to the LLM. The raw action-observation log is not shown. We set out a minimal four-axiom specification of what a belief-consistent internal state must satisfy, and prove that the LLM paired with the BSE is a sound Markov policy on the belief MDP induced by the underlying POMDP. It therefore inherits the Bellman optimality guarantees of classical POMDP theory, provided the LLM is never exposed to the raw history. We evaluate the architecture on the Tiger POMDP and a red-team attack-graph task, against six baselines: a reactive LLM, Chain-of-Thought, ReAct, a natural-language belief tracker, QMDP, and POMCP. Across both domains, the BSE-augmented agent improves task return, belief calibration, and decision consistency. Ten targeted ablations isolate the contribution of each architectural choice confirms that the effect is not specific to any one model. Code, environment specifications, prompt templates, and seed logs accompany this paper.

arXiv:2609.10135v1 Announce Type: new Abstract: To address insufficient contextualization, weak generalization, and poor scenario adaptation in tourism meteorological services, we propose SmartWeatherAgent--a unified three-stage architecture integrating intent recognition, hazard prediction, and reasoning-enhanced generation. The system fuses rule-based methods with large language models to parse queries at multiple granularities and employs a LightGBM model enriched with highland-specific features (e.g., wind speed abruptness rate), achieving an F1-Macro score of 0.605 with 1.60 ms latency on high-wind, precipitation, and low-temperature events. A 12-round micro-step prompt self-optimization loop boosts the composite warning quality score S_final from 4.2 (B01) to 8.9 (B12, +112%). Key improvements include a sharp rise in B08 from data source citation (6.5 -> 8.5), sustained high performance in B10 via physical mechanism explanation, and a peak scientific rigor score of 9.2 in B12 through explicit uncertainty statements. The system autonomously generates structured warnings that integrate causal mechanisms, spatiotemporal evolution, quantitative evidence, regulatory references, and confidence statements--enhancing professional depth, logical rigor, and scientific soundness, and advancing meteorological services toward proactive perception, explainable decision-making, and intelligent agency.

arXiv:2609.10144v1 Announce Type: new Abstract: AI systems become more useful when they can adapt to the people using them, but in multi-agent systems, useful context learned by one agent often remains unavailable to others. We present kernel-managed shared memory, a system-level abstraction in which specialized agents write structured, tagged memories while the agent-system kernel, not individual agents, governs retrieval, privacy enforcement, and prompt injection. We implement and evaluate this design on AIOS and compare it against three alternatives across three assistant models (GPT-4o, Llama-3.1:8B, Qwen-2.5:7B) and 1,800 total trials. Against an unmanaged external memory backend (Mem0) using identical underlying storage, kernel-managed retrieval and injection improve personalization scores by 2.4-4.0 points on a 5-point scale (e.g., 1.05 to 4.69 profile usage on GPT-4o), with every comparison significant at p

arXiv:2609.10315v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has advanced language-model reasoning in domains such as mathematics and code, where objective answers are inexpensive to check. Diagnostic reasoning over complex data lacks this advantage: establishing the true cause of an anomaly often requires costly expert investigation and may remain ambiguous after the fact. We ask whether this asymmetry of verification can instead be engineered. We sample an intervention, inject it into a controlled simulator, and generate the observations it would produce. The hidden intervention provides an oracle label and objective reward, while the agent must still investigate noisy, confounded, and distributed evidence. We instantiate this approach in TRACE, a digital-advertising diagnostic environment with 12 root causes and fine-grained segment attribution. Agents investigate each episode using Python and SQL and must identify both the root cause and, when applicable, the affected segment assignment. On a held-out 235-episode test set, the strongest prompted baseline, Claude Opus 5, reaches 0.686 FullAttr@1. Supervised fine-tuning raises Qwen3.5-35B-A3B from 0.159 to 0.637, and subsequent RL with synthesized rewards reaches 0.757, outperforming all evaluated prompted baselines, including frontier closed-source models and a prompted Qwen3.5-122B-A10B model. The resulting policy also uses substantially fewer tool calls than the prompted 35B base. These results provide evidence that access to a scalable, objective training signal can be a more important constraint than model scale alone. More broadly, simulation-based verification can make otherwise ambiguous diagnostic reasoning tasks amenable to scalable reinforcement learning.

arXiv:2609.10350v1 Announce Type: new Abstract: The banking system now depends on a small set of shared artificial intelligence vendors for fraud screening, credit decisioning, anti-money-laundering triage, customer analytics, and internal decision support. This paper studies how a compromise inside one of those vendors can propagate along a chain of operational, informational, and financial linkages until it triggers losses that look, from the outside, like a classical banking crisis. We build a four-layer heterogeneous network that couples AI vendors, financial institutions, interbank exposures, and customer accounts, and we propose CFC-Prop, a stochastic epidemic-and-clearing model that runs on that network. On a synthetic dataset with 60 vendors, 220 banks, roughly 2,500 vendor-bank service edges, and 1,400 interbank exposures, CFC-Prop reproduces the heavy-tailed loss distributions and the sharp dependence on patch latency that are consistent with prior cyber-financial evidence. We also train an early-warning model, CFC-GNN, that uses vendor-side incident telemetry and graph structure to flag high-cascade-risk vendors before impact. Across four baselines the proposed model reaches AUROC 0.82 and AUPRC 0.60 while keeping calibration errors bounded. We release the full code, synthetic data, and reproducible scripts. The results argue that cyber concentration among AI vendors is a first-order financial-stability problem and give supervisors a concrete quantitative tool for reasoning about it.

arXiv:2502.17017v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated impressive performance in various natural language processing tasks, yet their ability to perform multi-step logical reasoning remains an open challenge. Although Chain-of-Thought prompting has improved logical reasoning by enabling models to generate intermediate steps, it lacks mechanisms to assess the coherence of these logical transitions. In this paper, we propose a novel, lightweight evaluation strategy for logical reasoning that uses query-key alignments inside transformer attention heads. By computing a single forward pass and extracting a "QK-score" from carefully chosen heads, our method reveals latent representations that reliably separate valid from invalid inferences, offering a scalable alternative to traditional ablation-based techniques. We also provide an empirical validation on multiple logical reasoning benchmarks, demonstrating improved robustness of our evaluation method against distractors and increased reasoning depth. The experiments were conducted on a diverse set of models, ranging from 1.5B to 70B parameters.

arXiv:2609.09240v1 Announce Type: cross Abstract: Ultra-low-bit language models promise reductions in storage and memory traffic, but a nominal "1.58-bit" label does not specify the deployed representation or its execution cost. We study a scale-up of an aggressive post-training conversion pipeline from Qwen3-4B to Qwen3-8B. The conversion uses KOTMS rotation, E2M-ATQ adaptive ternarisation, and GPTQ-style error compensation in a weight-only A16 configuration. We do not claim these algorithms as new. Our contribution is the end-to-end scale-up characterisation: an external reproduction gate, matched 4B/8B capability analysis, cross-corpus perplexity, effective-bit accounting, lossless lattice-aware packing, and direct packed execution. The 8B model reaches a three-corpus perplexity ratio of 1.361x, with WikiText-2, C4, and PTB ratios of 1.318x, 1.393x, and 1.371x. On eight zero-shot tasks at n = 500, mean accuracy is 64.6% versus 72.4% for FP16, corresponding to 78.5% chance-corrected retention and a 7.8-point absolute cost. The matched 4B run retains 69.6%, yielding an 8.9-point 8B advantage. The packed checkpoint is 8.24 GiB and preserves the recorded perplexity to measurement precision. Direct packed execution reaches 15.52 tokens/s in 7.35 GiB, while a preliminary packed GEMV remains slower than FP16 cuBLAS. The result is a validated scale-up baseline: model size improves robustness to aggressive post-training discretisation, actual serialisation is solved for the measured artefact, and direct execution is feasible, while broader seeds, calibration distributions, and kernel optimisation remain open.

arXiv:2609.09241v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling model capacity while preserving efficient inference in large foundation models. However, most MoE models use a fixed top-$k$ expert selection policy, assigning the same expert budget to every token even when fewer experts may be sufficient. Inference-time dynamic top-$k$ routing can reduce computation without retraining, but existing methods often overlook the distributional shift caused by deviating from the training-time routing configuration. We show that reducing the number of activated experts consistently increases the RMS scale and variance of SMoE outputs, inducing a representation mismatch that contributes to downstream performance degradation in addition to the loss of expert capacity. To address this correctable component, we propose Layer-wise Distribution Alignment (LDA), a lightweight inference-time correction that uses layer-wise calibration statistics to align reduced-routing representations with the default configuration. Across multiple SMoE LLMs, benchmarks, and routing strategies, LDA recovers much of the performance lost induced by the distributional shift under reduced routing while preserving sparse-inference efficiency with negligible overhead.

arXiv:2609.09244v1 Announce Type: cross Abstract: The edge-of-chaos condition preserves first-order input perturbations in wide randomly initialized networks, but physics-informed losses, score matching and derivative regularization depend on higher input derivatives. For smooth scalar-input fully connected networks, using a joint Gaussianity of the finite derivative jet that holds in the infinite-width limit at each fixed depth, we derive mean-field recursions through third order that are exact at the variance fixed point, with finite-depth corrections that decay geometrically. At criticality, the first-derivative variance is depth-invariant, whereas the second-derivative variance grows linearly whenever the activation has nonzero curvature. The resulting third-order system closes on mean-field susceptibilities. For residual networks with branch scale L^{-1/2}, we prove that every fixed finite derivative order has uniformly bounded variance under explicit regularity assumptions. Simulations verify the critical growth laws, the residual bound, and the closed recursion. The results concern initialization, not trained-network performance.

arXiv:2609.09245v1 Announce Type: cross Abstract: Repeated-sampling evaluations increasingly extrapolate pass@k far beyond the number n of samples collected per problem. We show that, in the pooled/random-task conditional-Binomial model, fixed-n success counts identify only the n free moments of the latent per-task success distribution. Consequently, direct pass@k is identified for k n, even with arbitrarily many exchangeable tasks at the same rollout budget. This is stronger than the observation that the usual estimator is undefined beyond n: it characterizes the information missing from the fixed-depth count-law experiment. We give exact count-law-preserving constructions with incompatible extrapolations, state the exceptional unique-extension case, and compute sharp population identified intervals through Hausdorff principal representations. On the public 10,000-rollout-per-problem release of Brown et al., counterfactual n = 16 evaluations leave failure at k = 1000 ambiguous by factors from 1.5 to over 2,600 across four MATH/GSM8K/CodeContests configurations. The calibration shows that intermediate-scale failure share alone does not determine width. Our result does not reject parametric inference-time scaling laws; it supplies the nonparametric baseline against which their assumptions can be evaluated. We give an exact, conservative one-coordinate finite-task confidence certificate and a reporting standard separating direct estimates, identified sets, and model-conditioned forecasts.

arXiv:2609.09250v1 Announce Type: cross Abstract: A verifier for robot policies reads a candidate behavior and returns a score for how well it did, used both to evaluate vision-language-action policies and to train them. Verifiers range from success detectors and reward models to runtime monitors, safety filters, and temporal-logic specifications. We survey roughly 150 verifiers and compare them along two properties. Availability is how much a verdict costs, how early in a rollout the verdict arrives, and how often a verdict can be asked for. Availability rises as verdicts get cheaper, earlier, and denser. Credibility is how much a high score tells us about the task. Credibility falls as the judgment becomes gameable and self-serving. We group the verifiers by who supplies the judgment: human verifiers, rule-based and formal verifiers, learned and pretrained verifiers, and model-intrinsic verifiers. Across the four families, we find that credibility falls as availability rises. Regardless of who supplies the judgment, there is no free checker. We then examine what validates a verifier itself, and how much a high score tells us. Three measures appear in the literature: agreement with human labels, the performance of the policy it trains, and behavior under reward hacking. We close with nine metrics that make a verifier claim checkable, and coordinates for the verifiers still to be built.

arXiv:2609.09254v1 Announce Type: cross Abstract: Field-programmable gate arrays (FPGAs) enable efficient neural-network inference, but most deployment flows either accelerate multiply-accumulate operations or convert pretrained quantized models into lookup tables (LUTs). We present DiffLUT-Net, an FPGA-native network connected by six-input LUTs that are trained from scratch. We jointly learn the 64 truth-table entries of a LUT and the source to each of its six input ports using a differentiable LUT function relaxation and hardware source selection. After training, the truth tables and connections are discretized, unused logic can be pruned, and the network is exported directly as synthesizable Verilog. Across five benchmarks, DiffLUT-Net achieves favorable accuracy-resource trade-offs. These results demonstrate the effectiveness of jointly learning LUT functions and sparse connectivity for compact FPGA-native inference. The code is available at https://github.com/TUDa-HWAI/DiffLUT-Network.

arXiv:2609.09295v1 Announce Type: cross Abstract: The fixed-charge network flow problem (FCNFP) couples continuous flow allocation with discrete arc-activation decisions, making it a canonical but computationally challenging model for a variety of network design and resource allocation problems. Exact mixed-integer linear programming formulations capture the fixed-charge structure faithfully, but often become difficult to solve on large networks. We propose a scalable continuous-optimization algorithm for large-scale single-commodity FCNFP based on an iteratively reweighted least-squares (IRLS) framework. The method replaces the discontinuous fixed-charge and linear arc cost objective with a smooth nonconvex Lasry--Lions surrogate and solves a sequence of weighted quadratic flow subproblems. Each subproblem is solved by a warm-started dual semismooth Newton method whose Newton systems have weighted graph-Laplacian structure, enabling the use of modern Laplacian solvers. To further improve the discovered arc supports of the challenging underlying combinatorial problem, we also develop an algorithmic variant that incorporates objective-driven perturbation restarts and an anchor-union restricted search that jointly leverages supports discovered by IRLS and by complementary FCNFP heuristics. Computational experiments on 410 benchmark, synthetic, and large-scale instances show that our method obtains the best objective quality among the evaluated scalable FCNFP algorithms, with a mean gap of $1.316\%$ to a time-limited MILP reference and a win-or-tie rate of $90.0\%$ among the non-MILP methods. The results indicate that combining smooth continuous optimization with support-level search is an effective strategy for producing high-quality feasible solutions to large-scale FCNFP.

arXiv:2609.09388v1 Announce Type: cross Abstract: Brain-age prediction models are commonly evaluated by predictive accuracy, yet accurate predictions alone do not establish that a model relies on reproducible or neurobiologically supported mechanisms. Post-hoc explanation methods can expose these mechanisms, but existing workflows typically stop at diagnosis or require correction targets to be specified before model analysis. We propose XAI-Refine, an automated explanation-knowledge loop for brain-age prediction from resting-state functional connectivity. At each iteration, XAI-Refine consolidates complementary post-hoc analyses across repeated training runs into reliable, structured model explanations. It converts each reliable explanation into a neutral neurobiological question, retrieves and verifies relevant literature, and compiles the verified evidence into an admissible set in the same typed explanation space. The target for refinement is defined as the minimal projection of the current model explanation onto the admissible set induced by applicable verified knowledge. This revised explanation is then translated into a differentiable constraint while preserving the originating model variable, measurement operator, and applicable scope. Candidate updates are promoted only when multi-seed validation confirms target-directed explanatory movement, predictive performance remains within a prespecified guardrail, and non-target explanatory drift remains bounded. Experiments on functional-connectivity-based brain-age prediction evaluate predictive performance, explanation reliability, literature alignment, and target-specific model revision, illustrating a structured route from post-hoc analysis to evidence-guided model refinement.

arXiv:2609.09432v1 Announce Type: cross Abstract: Real-world datasets often exhibit evolving distributions, known as concept drift. Ignoring drift degrades predictive performance, while reliance on fixed hyperparameters further limits model adaptability under changing conditions. Adaptive learning addresses this challenge by continuously updating models online, allowing them to incrementally adjust and remain effective as data distributions evolve. This paper presents the Stream Cruise Control Method (SCCM), a comprehensive framework for drift detection and adaptation in online regression. SCCM enables automated adaptation through early-response, pre-update drift detection, drift magnitude quantification, KPI-window-based thresholding for local false-alarm mitigation, dynamic hyperparameter tuning, and model recalibration. SCCM also adopts an in-memory design for real-time adaptability, unlike purely reactive methods that typically activate adaptation only after performance degradation is observed. By using dynamic thresholding and remaining agnostic to data distributions, SCCM supports KPI-based monitoring across varying data streams, including high-dimensional and large-scale settings. SCCM is integrated with four online regression models and evaluated on 18 synthetic datasets covering abrupt, incremental, and alternating gradual drift, together with eight real-world datasets. The evaluation uses both R2 and MSE and compares against eight detector--adaptation baselines. Results show improved predictive performance and effective drift handling across the evaluated online regression settings.

arXiv:2609.09433v1 Announce Type: cross Abstract: Leave-One-Subject-Out (LOSO) evaluation estimates generalisation performance for subject-based classification but makes Neural Architecture Search (NAS) computationally expensive because a fully nested implementation requires N independent architecture searches and, assuming approximately linear training cost, scales as O(N^2). We propose a leakage-free, block-based approach that shares NAS runs across subjects. On the BioVid Heat Pain dataset, our approach increased the mean accuracy from 82.79% to 83.39% while reducing the number of parameters by up to 99.2%.

arXiv:2609.09476v1 Announce Type: cross Abstract: In-vehicle assistants must translate natural-language requests into accurate vehicle function calls under strict memory and latency constraints, making small language models (SLMs) attractive for on-device deployment. For such models, a key design choice is how the available function surface is presented. Two approaches are to represent each function with a dedicated Functional Token (FT) or provide function schemas directly in the prompt. FTs enable compact inference but are restricted to functions learned during training, whereas Schema-in-Prompt (SIP) can generalize to unseen functions at the cost of longer prompts and higher inference overhead. We introduce a benchmark of 9,822 single-turn examples spanning 79 vehicle functions derived from Android Automotive, including held-out functions and requests requiring refusal. We compare both approaches under matched fine-tuning across four SLMs from 270M to 1.7B parameters. On functions seen during training, scaling provides limited benefit: the 270M model can match the 1.7B model, while the strongest overall performance occurs at 0.6B. On held-out functions, FT achieves zero accuracy by construction, whereas SIP generalizes and improves substantially with scale. On out-of-scope requests, FT can invoke an unavailable function it was trained to emit, while SIP more reliably refuses based on the functions offered. This flexibility comes with higher memory use and latency. Our theoretical analysis explains how SIP enables generalization and why longer schema contexts increase inference cost. Overall, function-surface representation, rather than model scale alone, determines the capabilities and failure modes of SLM-based vehicle function calling.

arXiv:2609.09511v1 Announce Type: cross Abstract: Physical-layer authentication (PLA) in non-terrestrial networks (NTNs) is challenged by severe Doppler shifts, long delays, and fast channel variations, which cause distribution shifts and degrade conventional learning methods. Existing PLA schemes often rely on single features or generalize poorly to unseen environments. This paper proposes a secure adaptive framework for authentication in multi-zone networks (SAFA-MZ), a causal meta-learning framework for distributed PLA (DPLA) in NTNs. First, we design a multi-feature fingerprint that combines spatial, angular, combiner, subspace, and Doppler-delay features. The fingerprint is adaptive and distributed, as it fuses heterogeneous physical-layer features and measurements from multiple aerial nodes. Second, we formulate a structural causal model (SCM) to capture the relations among design choices, environmental factors, extracted features, and authentication outcomes. Third, we develop a model-agnostic meta-learning (MAML) strategy with invariant risk minimization (IRM) and causal consistency regularization for fast adaptation to unseen NTN environments with few labeled samples. Fourth, we propose a two-stage authentication scheme that performs local recognition and activates time-difference-of-arrival (TDOA) localization with a graph attention (GAT) network only when needed, which reduces backhaul overhead. Simulations show that SAFA-MZ achieves 92% accuracy and 96% AUC, outperforming centralized deep learning and single-feature baselines across diverse environments.