Papers

Domain adaptation is crucial for addressing distributional shifts that degrade model performance across domains. While most existing research has centered on classification, semi-supervised domain adaptation regression (SSDAR) for continuous-output tasks remains largely unexplored, particularly in practical scenarios with limited labeled target data. To address this gap, we propose semi-supervised domain adaptation regression through whitening transform and dual consistency (WhiteCon), which combines domain-specific whitening transform (DWT) and dual consistency regularization to enhance training stability and domain adaptation. DWT reduces the variance of the model parameters by transforming the feature covariance matrix into an identity matrix, thus stabilizing training under ordinary least squares assumptions. In addition, variance consistency regularization, as part of dual consistency regularization, aligns the variances of weak, strong, and mixup-augmented features to improve resilience against augmentation-induced perturbations. Empirical evaluations on various benchmark datasets under SSDAR settings demonstrate that the proposed WhiteCon achieves state-of-the-art performance compared to existing methods, effectively addressing domain shifts in regression tasks. The code for WhiteCon is available at https://github.com/sejin-sim/WhiteCon.

Mixture-of-experts (MoE) language models often exceed the memory of a single GPU. Expert offloading keeps most experts in host memory and loads them on demand, so decoding speed depends on how many experts each token must fetch. Caching and prefetching reduce this cost only as far as the routing allows. Router-only fine-tuning can reshape the routing to reuse experts, but it keeps the experts frozen, so they cannot adapt to the tokens the new routing sends them. We propose MaskCoFT, a masked co-adaptive fine-tuning method that trains routers and experts together with the cross-entropy loss alone. During fine-tuning, a learnable binary mask restricts the Top-K routing of each layer to a subset of experts, and the experts adapt to the tokens redirected to them. At inference, the learned mask becomes a soft prior that re-ranks experts, so every expert remains selectable. We simulate a GPU cache of 4 experts per layer for Mixtral-8x7B and 12 for DeepSeek-V2-Lite. MaskCoFT cuts expert fetches per token by 23.7% and 10.1% relative to the base model. In real offloading system serving, it lowers the time per output token by up to 16.4% and 5.5%, respectively. Its average accuracy over nine benchmarks stays above the base model by 0.92 and 0.53 points.

Multimodal large language models (MLLMs) are increasingly envisioned as core components of scientific and engineering agents, yet their ability to interpret physical fields remains poorly understood. Existing physics benchmarks largely emphasize textbook problem solving or intuitive physical reasoning, leaving open whether MLLMs can infer physically meaningful information from continuous field observations. We introduce PhysFieldBench, a benchmark comprising 24 tasks and 1,160 evaluation examples across controlled equation fields, simulated physical fields, and observed physical fields. The tasks assess three forms of inference: identifying physical mechanisms, comparing latent control variables, and predicting outcome properties. Across representative open-source and proprietary MLLMs, zero-shot performance is low: the best model achieves a chance-normalized score of 29.3, while several open-source models remain near chance. In contrast, a task-specific supervised vision transformer performs substantially better, demonstrating that the inputs contain learnable physical information. To diagnose these failures, a structured self-explanation analysis attributes most errors to missed visual patterns and incorrect visual-to-physical mappings. Further, to explore whether post-training can improve physical inference and generalize to unseen tasks, we compare supervised fine-tuning with final answers or chain-of-thought supervision and reinforcement learning. Final-answer supervision performs best overall but transfers less effectively, whereas reinforcement learning after chain-of-thought supervision achieves the best generalization. Together, these findings highlight the need to improve visual-to-physical grounding and cross-task generalization for MLLMs to reliably interpret physical fields in scientific and engineering workflows.

Long-horizon micromagnetic simulation remains expensive because conventional and learned solvers typically propagate Landau–Lifshitz–Gilbert (LLG) dynamics step by step. Existing learned approaches generally retain stepwise integration or model deterministic evolution, leaving full-field, direct-horizon stochastic prediction largely unexplored. We propose FLARE, a flow-matching framework that recasts stochastic finite-time magnetization prediction as conditional transport over anchor-relative local axis-angle rotations. This rotation-space formulation respects the intrinsic geometry of magnetization dynamics and preserves pointwise unit norm by construction. By explicitly conditioning on the physical prediction horizon, FLARE directly generates full-field stochastic endpoints across multiple target times without stepwise integration. Against the strongest single-checkpoint external baseline on each metric, FLARE achieves 29.9% lower angular energy distance ($15.30^\circ$), and a 37.3% lower fair energy score (0.393). On a representative composed 5-ns two-segment protocol, FLARE achieves a $3{,}062\times$ best-batch speedup over the widely used GPU micromagnetic solver MuMax$^3$ on a single GPU.

The upgrade and rewriting of large scientific codebases has traditionally been a major challenge. While evolutionary search with large language models (LLMs) can port and accelerate legacy code, repair feedback in prompts alone does not prevent subsequent candidates from repeating the same errors. We introduce Certificate-Driven Evolutionary Search (CDES), which extends evolutionary search with enforceable restrictions derived from failed candidates, recorded as certificates of assumptions, checker evidence, and justified restrictions. Its control logic enforces these restrictions through rejection, backtracking, and targeted repair while preserving compatible edits. We apply CDES to CPU-to-GPU translation of two particle-simulation functions from the Geant4 toolkit, evaluated with a harness that goes beyond unit tests to combine formal checks, numerical comparisons, physics checks, and GPU safety tests. Generated implementations achieve 13.78x and 23.54x function-level speedups over CPU code, including data conversion and transfers; for one function, GPU throughput exceeds an expert implementation by 14.9%, reaching 16.1% when complementary components are combined. In an ablation over execution settings, certificate feedback increases the fraction of candidates passing required correctness checks from 55% to 90%.

Names are personal identifiers, but they also carry social meaning and are widely used to evaluate how language models treat different people. Such evaluations typically assume that matched names are comparable model inputs. We show that this assumption often fails at the lexical interface: matched names are not necessarily matched inputs. Some names receive direct single-token access, while others are assembled from multiple subwords, creating unequal name-surface support. Across nearly half a million first names and 12 LLM-associated tokenizers, direct lexical access is highly selective, model dependent, and uneven across race- and gender-associated name metadata. We introduce NameTrace, a model-native, fine-grained, pre-behavioral framework for measuring whether unequal name-surface support remains a vocabulary property or becomes visible in task-relevant internal representations. NameTrace measures concept accessibility from the model's own probabilities over task-specific adjective axes with continuous task-aligned weights. On matched atomic and short-fragmented names within the same race/ethnicity–gender-associated strata, support predicts systematic differences in concept accessibility across fellowship, hiring, clinical assessment, and lending. These differences persist across all eight matched strata, extend across model families, and transfer to unseen names. Hidden-state interventions further show that the measured task directions have downstream leverage, shifting later constrained choices. Unequal lexical support is therefore demographically structured at the input and remains visible in task-relevant model computation. NameTrace makes lexical comparability measurable, supporting a broader principle: behavioral comparability begins with lexical comparability.

Reinforcement learning (RL) has become an effective post-training paradigm for long-horizon large language model (LLM) agents. However, we find that the resulting policies can be sensitive to various policy perturbations, such as hidden-state noise, pruning, and quantization. In this work, we study how to improve perturbation robustness during policy optimization. We first introduce the notion of a perturbation robust policy and analyze conditions under which perturbed policy updates preserve stable monotonic improvement. Based on this analysis, we introduce Stable Perturbation-Robust Policy Optimization (SPrPO), which applies adaptive and sensitivity-aware perturbations during RL training. We evaluate SPrPO on ALFWorld and WebShop and conduct systematic experiments across multiple perturbation types and scales, showing improved perturbation robustness while maintaining stable policy optimization.

AI systems often feel brittle and fragmented. A large language model (LLM) may correctly explain a concept but fail to apply it, or follow safety instructions in one context but not another. This behavior suggests a general failure to lift local information to a global understanding. To gain fundamental insight, we frame "understanding" as learning constraints and propagating their consequences. We construct learning tasks on monoid worlds, sets of states connected by action transitions, where observed training transitions and an unseen constraint jointly determine held-out transitions. Measuring generalization tests whether models can learn global constraints from local transitions and propagate their consequences. We consider inverse, commutativity, composition, and periodicity constraints relevant to spatial and semantic structure. Across attention, recurrent, and state-space architectures, next-state training fits the data but fails to propagate non-trivial constraints. Compositional training, which uses identical paths but hides intermediate states from the input, achieves 96% accuracy on inverse, commutativity, and composition constraints across architectures, yields corresponding improvements in geometric generalization of world models trained on embodied environments and relational generalization in Wikidata-finetuned LLMs. How far do models propagate constraints when inferring an unseen fact may depend on first inferring others? We define proof depth d of a held-out transition, measuring the minimum number of inference rounds to infer the transition, and find that model generalization decreases sharply with proof depth. Increasing compositional path length T improves generalization. These results provide a formal way to investigate global understanding in language and world models and demonstrate that compositional training promotes information propagation and integration.

Sliding-window KV inference refers to processing a sequence incrementally while retaining only a fixed-size cache of recent key and value states. It can be applied to pretrained causal transformers at inference time without additional training, while its KV-cache memory remains fixed as more tokens are processed. Because cached states are computed in the context of earlier tokens, they may carry information from beyond the current window and transmit it to later states. This study presents a series of experiments using five open-weight models spanning Qwen, Llama, Mistral, and Muse Glimmer. We investigate whether information originating outside the immediate context window can persist through a rolling KV cache and remain useful for retrieval. Initial results show that retaining previously computed states improves retrieval across the models tested compared with recomputing the final fixed window from raw tokens. We then measure how far this effect extends and find that Muse Glimmer and Mistral 7B show the strongest latent information relay: they can recover information even after the relevant source tokens have left the cache. Both models incorporate sliding-window attention in their published architectures, an association that motivates testing whether training with sliding windows promotes more reliable information retention.

Multimodal models increasingly interpret visual environments, but their ability to recognize the same building across photographs, floor plans, elevations, sections, and renderings remains poorly characterized. We introduce ARCH-B, a benchmark of 354 four-choice questions across 11 cross-representational archetypes, constructed from a building-linked corpus of 3.9 million architectural images using visually similar distractors, model-guided difficulty screening, and manual validation. We evaluate 25 multimodal models and collect 5,830 responses from non-expert human participants. Model accuracy ranges from 10.45% to 83.90%, compared with a human baseline of 35.35%. Models perform comparatively well on mixed-representation outlier detection and photograph matching, but remain weaker on floorplan-to-photograph correspondence. Human and model difficulty across archetypes is only weakly correlated (Spearman's (\rho=0.33)). Held-out evaluation confirms that the difficulty identified during screening generalizes beyond the curation models. ARCH-B provides a diagnostic evaluation of visual correspondence and representation transfer across architectural media.

Objective: To develop and characterize CLEAR-Med, a dual-agent framework for natural-language analysis of structured clinical data that separates SQL-based invocation from independent validation. Methods: CLEAR-Med uses one agent to translate a question into executable Structured Query Language (SQL), retain the executed query and database result, and produce a draft. Deterministic checks and a separately invoked cross-provider Validation Agent then accept the draft, request one bounded repair, or abstain. We formalized the system as a bounded selective pipeline and evaluated CLEAR-Med's configuration and scalability, and the Invocation Agent's accuracy and consistency on a 25-query development benchmark, using a harmonized 21-site neonatal hypoxic-ischemic encephalopathy table containing 532 de-identified infant records and approximately 1,300 variables. Results: CLEAR-Med completed all six nominal scalability configurations, including 500x1300. Across 25 development-benchmark queries repeated five times, the Invocation Agent answered 83 of 125 responses correctly (66.4%; query-cluster bootstrap 95% CI, 48.0-83.2%), compared with 15 of 125 (12.0%; 95% CI, 3.2-22.4%) for the ungrounded ChatGPT baseline, a paired improvement of 54.4 percentage points (95% CI, 36.8-72.0%). Conclusion: CLEAR-Med provides a general architecture for traceable analysis of structured clinical data: numerical claims remain linked to executed SQL, and unresolved cases can fail closed. The reported experiments characterize CLEAR-Med's configuration and scalability and the Invocation Agent's accuracy, while the formal analysis establishes the encoded-property guarantee of the complete control flow; a prospective full-pipeline evaluation of the validation and abstention stages is the next stage of this work.

Under the accelerated pace of AI development, any benchmark whose difficulty is calibrated with humans or current AI systems becomes circular, or saturates soon. How can we then evaluate machines that may become more capable than the current machines and the people who write the tests? One answer to the question hinges on inverse problems, inductive inference questions for which difficulty depends on the complexity of the underlying mechanism, given the observations and the previous knowledge. Levin's Kt, a computable variant of Kolmogorov complexity, puts a theoretical upper bound to that difficulty, balancing the simplest representation encoding for the mechanism and the logarithm of the time steps to run that mechanism. Previous tests derived from Levin's Kt, such as the original C-test, are based on minimalistic Universal Turing Machines (UTM), capable of very limited representations and no previous knowledge. Reasoning large language models (LLM) are UTMs that capture a compendium of human culture as knowledge, using prompts as natural language programs. This paper presents the first test based on Levin's Kt with LLMs as representational machines. Fresh test items can be produced at high difficulties, estimated in a ratio scale measured in bits, before any human or frontier model can solve them. We formalise the measure, devise a lightweight generation and certification pipeline, explore the effect of the power of the reference machine and the gap between examiner and examinee. We produce a first battery of certified items administered to twelve LLMs. The resulting agent characteristic curves decrease with difficulty, down to the uncharted high-difficulty region, the supra-intelligence window of items we can certify, yet beyond generations of frontier intelligence.

People often learn from others' demonstrations, and inverse reinforcement learning (IRL) techniques have realized this capacity in machines. In contrast, teaching by demonstration has been less well studied computationally. Here, we develop a Bayesian model for teaching by demonstration. Stark differences arise when demonstrators are intentionally teaching (i.e. showing) a task versus simply performing (i.e. doing) a task. In two experiments, we show that human participants modify their teaching behavior consistent with the predictions of our model. Further, we show that even standard IRL algorithms benefit when learning from showing versus doing.

On-policy self-distillation (OPSD) uses a self-teacher conditioned on privileged information to turn the sparse outcome signal of reinforcement learning with verifiable rewards (RLVR) into dense token-level supervision. Yet the teacher's advantage may depend on information unavailable to the student at inference, raising a central question: which privileged changes are worth distilling? We use cross-problem recurrence as an empirical cue for potentially reusable guidance. Comparing the representation shifts induced by full solutions and compact hints, we find that hint-induced shifts are more concentrated and directionally consistent across problems, and yield more sustained downstream gains despite revealing less information. Motivated by this association, we propose Privileged Representation Isolation for On-Policy Self-Distillation (PreSO). At the source, PreSO uses compact hints to limit the solution-specific detail entering the privileged shift. At the target, it estimates a leading low-rank subspace from shifts pooled across related problems, projects the privilege-induced correction onto this subspace, and adds it to the student's unprivileged representation to form the representation-level distillation target. The selected subspace serves as an operational proxy for recurring structure, rather than a guaranteed separation of transferable and instance-specific information. On five competition-level mathematics benchmarks, PreSO consistently outperforms strong baselines across Qwen3-1.7B, 4B, and 8B, improving average accuracy over the base model by 6.8, 9.0, and 10.0 points. Beyond peak accuracy, PreSO attains the highest final-checkpoint average at every model scale, with improvements that persist through the end of training.

Group-relative reinforcement learning methods such as GRPO train large language model (LLM) agents by comparing rollouts for the same task. When every trajectory in a group fails with the same reward, relative advantages collapse toward zero, leaving no useful learning signal. A frozen teacher can recover from a student-visited state, but letting it complete the task makes the recovered suffix entirely teacher-generated. We ask: after repairing a student failure, when should control return to the student? We propose outcome-verified teacher-student handoff, instantiated in Verified Handoff for Group Policy Optimization (VH-GPO). The teacher provides enough support to reach a state from which the student can succeed, then returns control so that successful experience is again student-generated. Given an environment-verified teacher recovery, VH-GPO selects the earliest independently confirmed handoff point found within a bounded search budget. With Qwen2.5-1.5B, VH-GPO increases success rates over GRPO from 59.38% to 94.79% on ALFWorld and from 71.62% to 77.34% on WebShop. Improvements also hold with the 7B student, for which additional teacher and student output tokens amount to 1.77% and 2.61% of regular student rollout output tokens on ALFWorld and WebShop, respectively. Ablation studies demonstrate the effectiveness of the key components. These results support using verified teacher assistance to repair failures while reinforcing the student's ability to complete tasks independently.

Rule decisions such as content moderation, advertising compliance, and eligibility checks combine several conditions, exemptions, and missing-information cases, and an error can be fixed only once the failing condition is known. We introduce SemTree, a framework that represents a rule decision as a semantic decision tree: each node is a natural-language question with explicit Yes/No/Unknown criteria, a pluggable semantic judge answers it, and the branching structure is compiled on the answers that this judge actually gives. The executed path is the reasoning behind every decision, so errors are repaired where they occur: a reviewer corrects a single node and replays the rule, corrected nodes become training labels for the judge, and a tool-using LLM editor revises questions and subtrees while observing execution results. On all 8,276 ShARC test cases, a tree executed by a hosted judge reaches 67.70% accuracy with 2.99 questions per case, on par with asking the same judge for the final label (68.23%); an earlier tree compiled for a different judge scores 47.87% when executed by this judge, while a new tree compiled on this judge's answers to a 12-question initial pool already scores 64.39%. Node-level repair raises BANKING77 accuracy from 82.04% to 86.16%, an explicit exemption node cuts the false positives of a Chinese e-commerce moderation clause from 24 to 5, and a trained editor raises the development accuracy of edited trees from 64.47% to 73.35%.

This paper proposes a hybrid reinforcement learning trading framework integrating intraday market data with transformer-based financial sentiment signals. The system extracts sentiment dynamics and semantic event clusters from financial news and incorporates them into a PPO-based trading agent. Experiments on intraday NSE data demonstrate improved risk-adjusted returns compared to price-only baselines.

Concept representations in diffusion models drift across network depth and denoising time, yet existing sparse autoencoders offer only per-block or per-timestep dictionaries, leaving no single feature dictionary for localization and intervention in the network. We present Shared Sparse Autoencoder (SharedSAE), which learns one sparse dictionary shared across four U-Net attention blocks and all 50 denoising steps of SDXL 1.0. A block-specific low-rank input adapter aligns the residual distribution of each block before the shared encoder, and a temporal conditioning module with a shared timestep branch and a block-timestep correction branch absorbs temporal non-stationarity. Despite spanning both axes, Shared SAE preserves a coherent dictionary structure. Built on the shared dictionary, localized feature suppression reduces the number of NudeNet-positive generations in the I2P detector-positive subset from 139 to 1. Tracing sparse features across the trajectory further reveals that concept representations are redistributed across U-Net blocks during generation, shifting from the earliest downsampling block toward intermediate and later blocks as denoising proceeds. SharedSAE thus provides a unified, interpretable, and intervention-ready representation space for diffusion models, enabling concept analysis and erasure at any covered block and denoising step.

Ocean wave forecasting is essential for maritime safety, offshore operations, and coastal resilience, yet remains challenging due to systematic biases in physics-based models. Physical models, while widely used, rely on approximations and parameterizations that limit their accuracy under complex ocean-atmosphere conditions. To enhance ocean wave forecasting, we propose BridgeCast, within a physics-AI hybrid framework for bias correction. BridgeCast is a probabilistic model based on conditional flow matching (CFM) that learns to transform physical model forecasts into reanalysis-like fields. It treats physical forecasts as corrupted observations and employs a continuous-time generative process to bridge their distribution toward that of reanalysis data. BridgeCast is parameterized by a Transformer-based architecture that enables spatiotemporal modeling, incorporation of exogenous atmospheric variables, and flexible inference via both ordinary and stochastic differential equation formulations. Extensive experiments on real-world datasets demonstrate that BridgeCast consistently outperforms state-of-the-art baselines across regions and forecast lead times.

Serving an answer from a large language model requires deciding when to abstain, yet a verifier's ranking accuracy alone does not determine the error rate among served answers. We introduce PriceCheck, which builds a compact family of decision rules from label-free checks such as re-solving a problem. Each check has a price: its agreement rates on correct and incorrect answers and its cost per run. Prices fitted on a small, class-enriched labelled set compose into predictions of a schedule's coverage and cost, guiding which checks to run and when to stop. A calibration test then selects a schedule at a stated selective-risk target. In mathematics, the selected schedules serve 76.1% of answers on average and keep held-out selective risk below 1.5% on all 15 splits. Under the shared testing protocol, PriceCheck serves more answers at that target than reward models, a prompted judge, the generator's confidence and a trained correctness classifier. At matched coverage, it keeps the fewest wrong answers among these scorers. Across 118 diagnostic schedules, price-based coverage predictions have a rank correlation of 0.97 with observed coverage. These results show that choosing how checks are combined and stopped matters alongside how well a verifier ranks answers. Code is available at https://github.com/js-lee-AI/PriceCheck.

How strong can an AlphaZero-style chess system become under limited training compute when its entire learning loop is engineered for efficiency? We train from random initialization through searched self-play on a single eight-GPU node for 2.5 days. The resulting 6.32-million-parameter model reaches 3,251 benchmark Elo [3,206, 3,297] at 100,000 searches per move (estimated at under five seconds of thinking time) against a fixed-node Stockfish 13 ladder. The run ingests 3.25 million completed games, involves an estimated 100 billion search simulations, and makes 836.6 million training presentations. We investigate search allocation, replay and restart-state selection, policy representation, progressive model sizing, quantized inference, and throughput engineering. Alongside the retained design, we document plausible alternatives that failed to improve the complete learning loop or did not justify their cost. The reported strength is a result of the integrated system, not an isolated Elo gain attributable to any single choice.

The pursuit of recursive self-improvement (RSI) toward general intelligence is divided between macro-level language model scaling and the interaction-driven principles of "Era of Experience". Yet, any self-improving architecture ultimately rests upon its underlying optimization engine: if general intelligence requires learning from grounded interaction, the reinforcement learning (RL) update rule itself must be capable of cumulative adaptation. While algorithm self-discovery has produced Disco103 that surpassed PPO to achieve SOTA benchmark performance – its internal update machinery remains an uninspected black box. We present the first causal mechanistic audit of a self-discovered RL rule, structured directly around the five pillars of the Era of Experience: extended horizon, grounded reward scales, continuing streams, within-lifetime change, and exploration depth. By surgically pinning, freezing, and transplanting recurrent states while holding meta-parameters fixed, we test when learning history acts as an asset or a burden. Three findings organize the audit: (1) Recurrent history actively expands usable reward scales, sustaining a six-decade window versus three under zero-pinning. (2) Decoupling historical content from its maintenance reveals that the penalty of mismatched history stems from perpetual clamping; allowing imported state to evolve naturally attenuates this burden. (3) Under environmental change, controlling replay retention reverses the apparent adaptation advantage over DQN, demonstrating that external data turnover can confound internal plasticity. Validated through capability thresholds and ported to a second rule (OPEN), this work grounds macro-RSI ambitions in micro-level learning dynamics, establishing a foundational audit standard for next-generation, self-evolving RL algorithms.

Sparse-autoencoder decomposability and concentrated feature attribution are increasingly treated as evidence that a model's computation is easier to reverse-engineer. Whether this representational and attributional cleanliness actually predicts a smaller or more tractable causal circuit remains an open question. We test this directly using adversarial training as a controlled instrument: it reliably reshapes internal representations, but this alone does not constitute a test of circuit size. We investigate this question through reverse-engineering complexity: the causal structure required to recover a model's behavior at a fixed level of faithfulness. To our knowledge, this is the first controlled empirical test of whether representational or attributional simplicity translates into causal simplicity at the circuit level. Starting from the same pretrained GPT-2 Small checkpoint, we apply matched standard and adversarial continual training, requiring both conditions to retain competence on indirect object identification and pass independent robustness verification before comparing mechanisms. We then compare the models along three complementary axes: sparse-autoencoder decomposability, SAE feature engagement in task attribution, and the size of faithful circuits recovered from the raw computational graph. The robust model is more SAE-decomposable and engages fewer SAE features in task attribution. Circuit size is regime-dependent: on competence-matched IOI, standard leads or ties below 85% faithfulness, but robust needs substantially fewer edges at high faithfulness (90%, 95%), a pattern established on the primary pair while representational trends generalize across a seven-point sweep and a second corpus.

Tool-using language-model agents select and execute third-party artifacts. Different implementations can return the requested output while producing hidden execution effects that task-, attack-, or choice-based evaluations may miss. We study functional counterfeits: implementations that match benign alternatives on the requested output but add an effect forbidden by the task contract. We introduce SINGED (Source Integrity and the Nonidentifiability Gap in Execution Decisions for LLM Agents), a controlled benchmark covering five primary and two held-out task families. It varies displayed rank, evidence depth, decision policy, model release, and agent configuration, while task and process oracles verify the artifact and execution path. Across 7,549 audited trials, the randomized-rank study finds counterfeit execution in 45% (27/60) of rank-one trials and none at later ranks. Cross-candidate comparison eliminates shallow failures and reduces layered failures from 15.7% to 4.2%, but leaves dependency failures; its benefit is uncertain on unseen effects and public-package structures. Moreover, seven releases with no counterfeit executions when benign alternatives are available execute the counterfeit in 55/175 single-source cells after alternatives are removed. SINGED thus exposes a rank-, evidence-, and choice-sensitive outcome-to-execution gap: evaluation must connect correct outputs to execution paths.

AI agents now hold spend authority and settle payments without per-action human confirmation. The resulting loss is often not a security failure: a counterparty with the correct domain, the correct settlement address and a genuinely delivered service can charge more than it should, and no check keyed on identity will see it. We present three artefacts for measuring and reducing that loss. First, a taxonomy of agentic commerce fraud that separates five observation levels (agent reasoning, wire, settlement rail, counterparty, principal) from the request-level and history-level evidence available at each, and records which levels can observe which attacks. Second, Agentic Commerce Bench (ACB), a benchmark of twenty fraud classes generated from production aggregates, 1,647 catalogued service operations and 1,068 settlements, of which six involve a counterparty that is exactly who it claims to be. Third, gordonguard, an open-source detector stack and offline harness with which an operator can audit an agent configuration, replay hostile counterparties without an account, and run the same detectors inline. Calibrating to a stated false-positive budget on clean training traffic gives a 6.5% clean flag rate, replicated across three independent generations, and leaves eight of twenty classes no better than chance. On the four classes a reasoning layer can observe, a widely used agent security scanner run over its jailbreak-detection panel scores zero on all four, while correctly scoring 1.0 on a jailbreak supplied as a control. A measured median payment of $0.007 places a hard constraint on deployment: one human review costs 143 times the value of the payment it examines.

On-policy distillation (OPD) trains a student on its own rollouts using dense supervision from a teacher. In multi-turn environments, a mistake at a critical decision step can redirect the subsequent rollout toward poor outcomes. We use low teacher confidence on student actions to select high-uncertainty steps for correction. In a controlled ALFWorld study, a single teacher correction at a low-confidence step improves subsequent student behavior and task success, motivating selective intervention during distillation. We propose UOPD, an uncertainty-aware intervention method for on-policy distillation. At low-uncertainty turns, UOPD executes student actions and applies the standard OPD loss. At high-uncertainty turns, it samples and executes teacher actions and trains the student to imitate them through supervised fine-tuning, which minimizes forward Kullback-Leibler divergence in expectation. UOPD utilizes adaptive uncertainty thresholds to target a scheduled intervention rate. Empirically, we evaluate UOPD across a broad range of agentic tasks, including ALFWorld, WebShop, and Search, demonstrating its superior performance over OPD methods and their variants. UOPD improves WebShop score by up to $15.8\%$ relative to standard OPD.

A central aim of neuromorphic computing is to provide a viable alternative to highly energy-intensive Transformer-based AI. However, efficient alternatives struggle to capture the set of qualities that have secured the Transformer's status as the de facto standard in sequence modelling. Any realistic contender must be data-adaptive, able to capture long-range dependencies, and GPU-parallelisable, but also non-linearly recurrent to enable complex reasoning. Based on evidence suggesting the auditory cortex operates on fixed timescales, this work proposes the ADaptive with Prescriptive Timescales Network (ADPTNet) as a potential solution to achieving all four properties simultaneously. ADPTNet is built around local topological conjugates, obtained by a novel combination of linear attention and Riemannian optimisation, applied to static global dynamics. This enables non-linear yet predictable long-term behaviour. Dynamical systems theory proofs provide theoretical guarantees for the parametric control of ADPTNet's timescales (its Lyapunov spectrum). ADPTNet improves performance on Selective Copying over Hawk, the existing method balancing long-range memory and adaptability, while also improving state tracking over linear SSMs like Mamba. On sequential CIFAR-10, ADPTNet matches linear SSM accuracy and outperforms existing selective models (incl. the Transformer), using fewer parameters. We also introduce a neuromorphic SpikingADPTNet, which achieves a new state-of-the-art accuracy on the Spiking Speech Commands dataset ($83.56\%\pm0.15$). Finally, ADPTNet's constant timescales enable two efficient, Jacobian-free extensions to the DEER parallel simulation algorithm (Conv and Forward DEER) that retain the same average convergence. Conv DEER adds no computational overhead beyond the network's forward pass and enables non-linear RNN parallelisation via iterated convolutions for the first time.

Correlations between events in machine learning datasets may result in shortcut learning, where models learn to predict the target event based on the presence of a correlated event. When these correlations are spurious – arising from data collection artifacts – models are likely to perform poorly in practice. We propose a pipeline to uncover shortcut learning in audio classifiers by discovering recurring concepts in their temporal explanations. Specifically, we isolate audio segments that explain classifier decisions, caption them with an ensemble of Large Audio-Language Models, and use a Large Language Model to extract recurring concepts. The resulting concepts can be audited by humans to uncover potential shortcut learning. We evaluate our framework using datasets curated from AudioSet Strong, controlling for the presence or absence of spurious correlations. Results show that this approach reliably uncovers learned shortcuts, such as the model relying on the presence of "laughter" to predict "applause".

Jev is a non-generative System One model that assigns probabilities to predefined answer options and cannot answer outside them. Its accuracy and calibration on medical question-answering and case-based diagnostic-reasoning tasks are unknown. We evaluated Jev 1.13 on four medical benchmarks: MetaMedQA, PubMedQA, DiagnosisArena-MCQ and the NEJM Case Challenges. GPT-6 Sol, with (medium) and without reasoning, was the reference. The primary outcome was top-1 accuracy; key secondary outcomes were calibration, selective prediction and recognition of unanswerable questions. All 8,469 requests returned a valid answer. Jev's accuracy was similar to that of GPT-6 Sol with medium reasoning on PubMedQA (78.4% vs 78.2%;), lower on MetaMedQA (74.8% vs 82.7%) and much lower on DiagnosisArena-MCQ (59.8% vs 82.4%;) and the NEJM cases (61.8% vs 82.4%). On MetaMedQA, Jev's probabilities were the best calibrated (expected calibration error 0.063 vs 0.146), and its answers with a probability of at least 0.9 (52.9% of questions) were 93.4% accurate, but GPT-6 Sol was as accurate when it accepted a similar proportion of questions. On DiagnosisArena-MCQ, Jev's probabilities discriminated poorly (AUROC 0.645 vs 0.768). Of the 162 questions whose correct answer was "I don't know or cannot answer", Jev chose that option for 10.5% (GPT-6 Sol, 8.6%). Median latency was 0.27-0.31 s; all 2,823 items cost USD 0.08. Jev was fast and inexpensive, and its accuracy was similar to that of a frontier LLM on research abstracts but lower on examination questions and much lower on complex diagnostic cases. Task-specific validation is required before clinical use.

In many high-stakes applications, machine learning is dominated by black-box models that require post hoc explanations to justify their predictions. These explanations are often unreliable because they do not reflect the model's actual computations, limiting accountability and trust. A natural alternative is to use models that are interpretable by design. However, existing rule-based approaches, such as RuleFit and decision trees, while transparent, often lack stability and predictive strength, reinforcing a perceived trade-off between traditional performance measures and model understandability. To address this, we propose Sparse Relaxed Regularized Regression Rule-Fit (SR4-Fit), an intrinsically interpretable algorithm for both classification and regression that produces compact and stable rule sets without sacrificing performance. Using demographic data from the U.S. Census Bureau's American Community Survey, SR4-Fit predicts U.S. House election outcomes with high accuracy and interpretability while uncovering demographic interactions missed by black-box models. We further validate SR4-Fit across fourteen benchmark datasets (six classification and eight regression), where it outperforms existing rule-based methods, including RuleFit and decision trees in terms of accuracy, stability, and compactness while remaining competitive with black-box models in predictivity. These results demonstrate that interpretability and predictive reliability need not be mutually exclusive, offering a practical and transparent alternative for high-stakes decision-making.