Artificial Intelligence · Cross-listed from cs.NE
FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution
Hui Chen, Xuan Qi, James Xu Zhao et al. (+5 more)
LLM-guided evolutionary methods, such as AlphaEvolve, have emerged as powerful approaches for challenging computational optimization problems, such as circle packing. However, prior work typically optimizes performance gain over a fixed number of iterations. We argue that practical optimization should maximize gain per unit cost. To this end, we propose FrugalEvo, a cost-aware evolutionary framework where a stronger, higher-cost LLM explores solution strategies, and a cheaper LLM implements them and iteratively refines the resulting code. We also design a cache-efficient
evolution process, where our harness and
prompts maximize the sharing of prefixes across different
evolution steps, to improve cache reuse. To measure solution quality throughout a fixed cost budget, we introduce Budget-Aware Area Under the Curve (BA-AUC), defined as the area under the best-so-far evaluation score curve over cumulative LLM cost, up to the budget. Across 10 mathematical and systems optimization tasks, FrugalEvo matches or surpasses state-of-the-art baselines, including OpenEvolve, ShinkaEvolve, AdaEvolve, and EvoX, in final solution quality and achieves higher BA-AUC on 9 tasks. It also achieves higher average performance than these baselines on 10 algorithmic optimization tasks from ALE-Bench-Lite. Notably, on circle packing, FrugalEvo achieves new state-of-the-art performance with GPT-5.6 Terra and Luna for only 1.68 USD and with GLM-5.3 and its Flash variant for only 0.55 USD, matching or surpassing all baselines, including multi-
agent methods such as CORAL and SwarmResearch, which cost approximately 50 USD on average.
Read the full abstract ▾
All authors Hui Chen, Xuan Qi, James Xu Zhao, Zhaopeng Feng, Shilong Liu, Kuang Xu, Pang Wei Koh, Bryan Hooi
Artificial Intelligence · Cross-listed from cs.SD
Revisiting Input Time-frequency Representations in Multi-pitch Estimation for Vocal Ensembles
Junyoung Koh and Hao-Wen Dong
Multi-pitch estimation in vocal ensembles is challenging because singers occupy overlapping pitch ranges and often sing at closely spaced fundamental frequencies, causing their harmonics to overlap in time-frequency representations. Existing models commonly use harmonic constant-Q transform (HCQT)-based representations to provide frequency-adaptive resolution, at the cost of expensive feature extraction when training mixtures are generated on the fly. We revisit this design and compare HCQT with a linear short-time
Fourier transform (STFT), whose frequency bins are directly provided as model inputs. Despite its fixed frequency resolution and the absence of a pitch-aligned input grid, the linear STFT outperforms HCQT while substantially reducing feature-extraction cost. Further analysis shows that a longer analysis window or broader spectral coverage provides no additional improvement, while restricting the input to the predicted pitch range reduces the advantage of the linear STFT. These results suggest that finer frequency resolution does not necessarily improve vocal-ensemble MPE, and that shorter analysis windows can be more effective for time-varying vocal pitches.
Read the full abstract ▾
Artificial Intelligence
MRVQ: One Resident Index for Dimension- and Rate-Elastic Vector Search
Sean Culatana, Shang-En Huang and Kang Li
Dense-
retrieval services must switch among
embedding-prefix dimensions and index bit rates as latency, quality, and
memory budgets change. Tuning a quantizer separately for each rate gives the best quality, but the
retrieval tier then holds several code streams and quantizer states at once. We introduce Matryoshka Residual Vector Quantization (MRVQ), a post-hoc residual quantizer for frozen
embeddings. Its maximum-rate code can be truncated two ways: dropping residual stages lowers the rate, and dropping
embedding coordinates lowers the dimension. One resident artifact therefore serves every (dimension, rate) pair we evaluate. Across FiQA and NFCorpus, four
embedding families, and {4, 8, 16}-byte codes, MRVQ is the lowest-RAM design we evaluate. It uses 17.8-22.0x less
memory than three separately trained QINCo2 indices, and 1.89-2.02x less than a lean shared-model steelman. The saving is not free: per-rate QINCo2 is 0.026-0.107 nDCG@10 better on FiQA. But MRVQ beats PQ, OPQ, and AdANNS-OPQ at matched code size. We also evaluate a low-build-cost PCA-scalar design that attains quality comparable to RaBitQ and its extension while fitting 420x faster at the median. Finally, we report two negative results: QINCo2 collapses when trained at high rates, and a ranking-bound hypothesis misses its pre-specified acceptance criteria. MRVQ is therefore a low-
memory operating point for elastic
retrieval, not a universal quality winner.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
On-Board Anomaly Detection for Efficient Marine Environmental Monitoring
Thomas Goudemant, Clotilde Szywala, Benjamin Francesconi et al. (+4 more)
Marine ecosystems are impacted by various threats such as oil spills, algal blooms, and sediment floods, which disrupt habitats, wildlife, and human activities. Advances in satellite imagery and Artificial Intelligence (AI) have enhanced our capabilities for early detection and mitigation of such hazards. In this paper, we propose a marine event detection pipeline for Earth observation satellites equipped with multi- or hyperspectral sensors. Our approach includes a self-supervised neural network encoder that compresses satellite images into a reduced latent space, enabling efficient onboard processing. A machine learning anomaly detection model identifies deviations from normal sea patterns to detect environmental anomalies. We compare its performance against traditional
algorithms such as Isolation Forest, One-Class Support Vector Machine and Local Outlier Factors. Our lightweight, resource-efficient pipeline is optimized for deployment on satellites with limited computational resources, ranging from embedded CPUs to AI hardware accelerators. By prioritizing the transmission of critical information, our solution enhances system responsiveness and optimizes satellite communication bandwidth. Demonstrated through current integration across multiple missions, including European Space Agency's (ESA) Phisat-2 mission and Microsoft/Thales Alenia Space IMAGIN-e mission, our pipeline aims to improve marine environmental monitoring by providing timely alerts and efficient data reduction.
Read the full abstract ▾
All authors Thomas Goudemant, Clotilde Szywala, Benjamin Francesconi, Michelle Aubrun, Yves Bobichon, Marjorie Bellizzi, Adrien Girard
Artificial Intelligence
Do Large Language Models Know Colombian Law? A Reliability Benchmark for the Colombian Legal System
Rubén Manrique, Michelle Castellanos, Jorge Morales et al. (+3 more)
Large
language models (LLMs) are increasingly used to support legal practice, education, and research, yet their reliability in national legal systems outside the United States remains largely undocumented. We introduce an expert-validated
benchmark for evaluating LLM reliability on the Colombian legal system. The
benchmark comprises 1,042 items spanning ten areas of law and three question formats (closed multiple-choice, semi-open, and open-ended IRAC), built through a human-in-the-loop pipeline with multi-stage expert review. We evaluate 15 contemporary proprietary and open-weight models with format-appropriate metrics. Accuracy on closed questions ranges widely, from 0.905 (Gemini 3.1 Pro) to 0.577, but on free-text legal answers factual correctness never exceeds 0.45 (on a 0-1 scale) for any model. We find a dissociation between answer relevancy and correctness (Spearman rho = -0.46): models reliably sound responsive while frequently being wrong, a pattern of particular concern for non-expert users. Closed-question accuracy and free-text correctness are strongly rank-correlated (rho = 0.94), so cheap multiple-choice screening predicts model ranking but overstates absolute reliability. An independent rubric-based LLM judge and blind human expert scoring both reproduce the free-text ranking (rho >= 0.88). The judge further reveals that only about half of the norms models cite are correct; the rest are wrong or non-existent. Reliability varies systematically by legal area and follows an inverted-U across question complexity. Our results indicate that current LLMs require expert supervision for Colombian legal tasks, and that grounding answers in authoritative sources is a promising path to higher reliability. We release the
benchmark construction pipeline to support reproducible evaluation.
Read the full abstract ▾
All authors Rubén Manrique, Michelle Castellanos, Jorge Morales, Juan David Gutiérrez, Antonio Barreto Rozo, Joaquín Vélez Navarro
Artificial Intelligence · Cross-listed from cs.CV
LoGo: Local-Global Rewards for Consistent Long-Horizon Video Generation
Ziqi Ma, Shreya Sharma, Mohamed El Banani et al. (+8 more)
Camera-controlled
video models are rapidly advancing toward long generation horizons and complex camera control. A key failure mode is 3D inconsistency: as the camera moves, objects lose permanence and scene structures shift. Existing post-training techniques, which assign a single scalar reward to the entire generation, are poorly suited to correcting these inconsistencies over long horizons. We introduce LoGo, which blends global and spatially localized rewards for camera-controlled
video models. The local reward provides fine-grained credit assignment, which substantially improves 3D consistency, while the global reward preserves camera following and
video quality. Across three base models, LoGo shows a clear advantage on DL3DV and TrajectoryBench, a new
benchmark for long-horizon, complex-camera-control generation that current evaluations lack. LoGo effectively reduces local object shifts, artifacts, and global scene changes, illustrating the importance of credit assignment in post-training
video models. Project website: https://ziqi-ma.github.io/logo-website/
Read the full abstract ▾
All authors Ziqi Ma, Shreya Sharma, Mohamed El Banani, Katja Schwarz, Chongjie Ye, Chao-Yuan Wu, Li Fei-Fei, Ben Mildenhall, Georgia Gkioxari, Justin Johnson, Gowthami Somepalli
Artificial Intelligence
Credit Where It Matters: Dependency-Aware Policy Optimization for Terminal Agents
Yu Li, Guangfeng Cai, Long-Fei Li et al. (+5 more)
Terminal-using
agents benefit from reinforcement learning (RL) in coding, debugging, and other multi-step terminal tasks. In these tasks, later commands often depend on information or intermediate results produced by earlier commands. However, existing trajectory-level and step-level credit assignment methods do not explicitly trace the read-write dependencies through which commands affect the final outcome. Consequently, training signals could still be assigned to irrelevant operations, weakening learning from relevant steps. In this paper, we propose Dependency-Aware Group Policy Optimization (DepGPO), which uses execution dependencies between commands to guide credit assignment for terminal
agents. Specifically, we construct a command dependency graph from execution traces and trace backward from the resources inspected by the task verifier. We then assign credit to relevant writes and their supporting reads along these paths, and use it to redistribute trajectory advantages across steps. Extensive comparative experiments and ablation studies demonstrate that DepGPO improves task performance and training stability on complex terminal tasks.
Read the full abstract ▾
All authors Yu Li, Guangfeng Cai, Long-Fei Li, Shuo Han, Shengtian Yang, Han Luo, Kaibing Yang, Lei Feng
Artificial Intelligence
NeutronGym: Physics-Graded Neutron Instrument Design for LLM Agents
Lijie Ding and Changwoo Do
Designing a scientific instrument tests whether
language-model
agents can do physics rather than recall it, provided the grading cannot be argued with. We introduce NeutronGym, to our knowledge the first executable environment for
neutron instrument design:
agents build instruments through validating tools, McStas ray-traces what they build, and a level-resolved ladder grades syntax, runtime, structure and science with no LLM judge. Procedural families supply unlimited instances of a fixed layout whose design parameters the
agent must set, with held-out parameter regimes; a curated slice, McStasBench, adds 16 tasks from published instruments behind memorization probes and a sandbox. Seven models reproduce at most 7 of the 16, none retrieves a reference, and none meets an improvement target. The environment also trains. Reinforcement learning on its reward takes Qwen3-8B from 11% to 77% of held-out instances of a family whose targets come from a hidden design (69% at a second seed), past an untrained Qwen3-32B, and the recipe holds, at one seed each, on three further gated families. The analysis says what that gain is. Without the ladder's partial credit it collapses by 60 points. From reward alone the trained model reaches what a classical optimizer reaches, at the
agent's simulation budget, only when handed the closed-form physics (77% against 81%, a gap that does not separate at this size), while frontier models still solve 98-99%. Getting a trustworthy result meant failing four task designs that no-model baselines could solve, and we release the probes that found them.
Read the full abstract ▾
Artificial Intelligence
Depth as Time in One-Step Generative Models
Arnold Caleb Asiimwe, William Yang, Sanghyuk Chun et al. (+2 more)
The recent wave of one-step generative models, which compress the multi-step trajectory of
diffusion via either
distillation or learned flow maps, has reached an inflection point where they can generate high-quality images. Here, we ask a natural question that follows from these advances: what happens to the denoising trajectory of multi-step
diffusion when generation is compressed into a single forward pass? We offer an empirical observation we call depth as time: the denoising computation that multi-step
diffusion performs across sampling steps appears to unfold across the depth of a single forward pass, and can be recovered by decoding intermediate layers with the model's own output head. Most interestingly, we show that this depthwise computation depends on the transport task a flow map is trained to solve. The most surprising case is MeanFlow, where probing shorter transport intervals reveals both denoising and renoising within a single network evaluation. In contrast, generators trained without a time-indexed transport task, such as drifting models, do not exhibit the same depthwise denoising. Consequently, we show that models that exhibit the depthwise denoising phenomenon are more compressible across the layerwise computation: a MeanFlow SiT-L/2 model can be compressed by $16.6\times$ in parameters into a single time-conditioned block. We offer an explanation for this denoise-then-renoise behavior and show that, when we treat the layerwise computation explicitly as a flow, a single time-conditioned block can be trained to denoise across layers, compressing a MeanFlow SiT-L/2 model by $16.6\times$ in parameters. Together, these results suggest that the temporal computation of
diffusion is not eliminated by one-step generation, but reorganized across network depth.
Read the full abstract ▾
All authors Arnold Caleb Asiimwe, William Yang, Sanghyuk Chun, Esin Tureci, Olga Russakovsky
Artificial Intelligence
Video-Time Priors for EEG-fNIRS Emotion Regression on Familiar Videos
Minghao Kong, Ying Gao, Jiurun Chen et al. (+4 more)
Do viewer-specific physiological signals improve continuous emotion regression beyond the stimulus-driven response shared across viewers? We examine this question by predicting emotion ratings for new viewers watching
videos that also appear in the training set. As a stimulus-only baseline, we define a
video-time prior:the smoothed median of training labels for each
video at each second. We then combine this prior, using a fixed fusion weight, with a graph-based model of electroencephalography (
EEG) and functional near-infrared spectroscopy (fNIRS) signals. On MER-PS 2026, five-fold cross-validation grouped by participant over 24 participants yields a mean absolute error (MAE) of 29.01 for fusion, compared with 29.06 for the prior alone. On an external cohort of four participants excluded from training, the corresponding MAEs are 27.72 and 28.04. In this cohort, most of the MAE reduction relative to a global-constant baseline comes from the prior, that is, from
video identity and playback time alone.Fusion lowers MAE for three of the four held-out participants and for nine of the fifteen
videos. The added value of physiological signals is therefore small and varies across participants and
videos. Because the model uses physiological signals recorded after each prediction time, it supports only offline prediction. Generalization to unseen
videos remains untested.
Read the full abstract ▾
All authors Minghao Kong, Ying Gao, Jiurun Chen, Muyao Chen, Zheng Ge, Jianxin Wu, Rongjie Wang
Artificial Intelligence · Cross-listed from q-fin.TR
When a Correct Reward Is Not Enough: Diagnosing and Guiding PPO in an Analytically Solved Broker-Trader Game
Siu Tung Wong and Carlo Campajola
Reinforcement learning (RL) is increasingly used for financial optimal-control problems when complex dynamics make analytical strategies difficult to obtain. There are financial mathematics literactures which provides many solved models whose equations and controls could evaluate and guide learning; we ask whether RL can exploit these results. We place a proximal policy optimisation (PPO)
agent in an analytically solved continuous-time broker–trader game. PPO replaces the broker and chooses its trading speed while interacting with an informed trader and
stochastic uninformed order flow. We derive a finite-step reward from the broker's continuous-time payoff and verify its discrete implementation through grid refinement and an exact one-step identity. With zero uninformed flow, a validation-selected PPO–FFNN approaches the reference action. With
stochastic uninformed flow, the tested PPO–FFNN and PPO–LSTM remain inaccurate, although supervised learning confirms that their actors can represent the action. Monte Carlo diagnostics show that their critics do not reliably rank nearby actions; potential-based reward shaping also gives no reliable improvement. Under partial information, a causal certainty-equivalent controller based on the broker's observable history remains close to the reference, while PPO has larger errors and lower payoffs. Finally, we freeze the analytical policy and train PPO to adjust it after the execution cost changes. Halving the cost yields a repeatable improvement that closes \(2.22\%\) of the gap to the changed-cost reference. The analytical solution therefore provides both a
benchmark for diagnosing RL and a useful starting policy for adaptation.
Read the full abstract ▾
Artificial Intelligence
HazardWeaver: Scientific Route Selection for Hazard Analysis Agents
Wangshu Zhu, Xueqi Cheng, Liang Wu et al. (+1 more)
Understanding and assessing natural hazards is essential for disaster preparedness and risk reduction. Recent advances in large
language models have spurred growing interest in AI
agents for hazard analysis, particularly their ability to integrate scientific data, models, and tools into automated workflows. However, effective automation requires
agents to determine which scientific methods are appropriate for a given event and executable with the available data and tools. As new evidence and execution results become available, these conditions can change, requiring
agents to reconsider their choices. We formulate this problem as state-dependent scientific route selection and introduce HazardWeaver. Specifically, HazardWeaver first leverages the Hazard Knowledge Compiler to extract evidence-linked conditions governing scientific applicability, then its Hazard Capability Graph represents executable scientific capabilities and checks compatibility between their inputs and outputs. Using these complementary representations, the Hazard Weaver
Agent component selects applicable and executable routes, carries out their workflows, and revises its decisions as the analysis state changes. To evaluate both the scientific outputs and the decisions that produce them, we introduce the Hazard Weaver
Benchmark, comprising 141 instances across seven single-hazard domains and four multi-hazard interaction classes. The
benchmark accommodates multiple valid scientific routes and evaluates output correctness, route validity, and justified abstention. Extensive experiments on this
benchmark show that HazardWeaver outperforms existing
agent systems, with the largest gains on tasks with multiple eligible scientific routes. Our code is publicly available at https://github.com/LabRAI/HazardWeaver.
Read the full abstract ▾
All authors Wangshu Zhu, Xueqi Cheng, Liang Wu, Yushun Dong
Artificial Intelligence · Cross-listed from cs.CR
Threat-Preserving Representation Sensitivity in Agent-Security Benchmarks
Neeraj Karamchandani, Piyush Nagasubramaniam, Xinhong Xie et al. (+2 more)
Security
benchmarks for LLM-based
agents often report the attack success rate (ASR) as a measure of model robustness and use these scores to compare different models and defense mechanisms, assuming that they describe the security of the
agent. In this paper, we explore whether it also influences the
benchmark's measurement. To measure the effect of the
benchmark representation, we introduce threat-preserving representation sensitivity (TPRS), which measures how much the ASR changes when we change the
agent-visible representation while holding the underlying task, harmful action, security policy, ground truth, environment, and the evaluation criteria fixed. On
Agent Security Bench (ASB), replacing threat-related tool names with threat-neutral names raises the committed attack success rate by 11.67 percentage points on GPT-5-mini and by 13.21 points on Claude Haiku 4.5. On MCPTox, replacing the original neutral tool name with an explicit threat-related name lowers the ASR by 11.00 percentage points on GPT-5-mini and 4.11 points on Claude Haiku 4.5. On AgentDojo, adding threat-related wording to the attack-relevant tool changes ASR by only 0.50 percentage points on GPT-4o-mini, yet the benign utility falls by 5.36 points on tasks requiring that tool. We ran an experiment on MCPTox where we observed that a threat-neutral name matched on
token count, length, and casing reproduces most of the shift produced by the threat-explicit name (8.54 of 11.00 points on GPT-5-mini). The results show that a security score measured under one representation may fail to generalize across threat-preserving representations of the same security problem. Robustness claims should therefore be supported by performance across a controlled set of threat-preserving representations rather than relying on a single representation-dependent score.
Read the full abstract ▾
All authors Neeraj Karamchandani, Piyush Nagasubramaniam, Xinhong Xie, Sencun Zhu, Dinghao Wu
Artificial Intelligence · Cross-listed from cs.CV
Rethinking What to Cache in Few-Step Diffusion Transformers: Solver-Aware Target Selection
Shuo Yang, Lihao Fang, Yi Zhang et al. (+5 more)
Diffusion Transformers (DiTs) can generate high-quality images and
videos, but generating each sample requires multiple costly DiT forward passes. Two common ways to accelerate DiT sampling are step
distillation, which reduces the number of sampling steps, and caching, which skips some DiT evaluations by reusing a tensor computed at an earlier step. Most caching methods decide in advance which tensor to reuse. After
distillation, adjacent sampling steps are farther apart. Reusing a tensor across this larger gap introduces more error, so choosing what to cache becomes especially important. We therefore introduce AutoTarget, a method that chooses the cached tensor for a given model, solver, and reuse schedule. AutoTarget uses a small set of runs without cache reuse to measure the error caused by reusing each candidate tensor, then selects the candidate with the lowest error. We also analyze how an error at one reuse step affects the final sample. For Euler sampling, we identify cache targets that produce the same trajectory and show why a stored solver update may not. Experiments on distilled image and
video DiTs show that the best cache target changes with the model, image resolution, and solver. AutoTarget reduces DiT evaluations and retained cache storage. Generation quality remains close to the corresponding uncached run. On the tested PixArt-LCM and FLUX.1-schnell settings, its calibration ranking matches the ranking from held-out cached runs. To help others reproduce the method, we provide its core implementation on GitHub at https://github.com/wali1024-offical/AutoTarget.
Read the full abstract ▾
All authors Shuo Yang, Lihao Fang, Yi Zhang, Haixiang Wang, Xincheng Ye, Shufan Chen, Jipeng Guo, Youqing Wang
Artificial Intelligence
HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents
Alham Fikri Aji, Faiz Rizki Ramadhan, Zayd M. K. Zuhri et al. (+14 more)
We introduce HyperBrowseComp, a multilingual and
multimodal browsing
benchmark comprising 423 manually authored and human-validated questions across 13
languages, written by native or highly proficient speakers. Questions are designed to be extremely challenging. Each question targets a concise, publicly verifiable answer whose discovery requires locating obscure evidence, following multi-step clue chains, or inspecting heterogeneous sources such as
videos, scanned documents, images, or maps. Easier questions are filtered out by evaluating them with models without internet access to reduce the likelihood that they can be answered with parametric knowledge alone. We evaluate several models using provider-native search and a shared external
retrieval harness under a common
agent protocol. To contextualize model performance and effort, we also conduct a human evaluation on a sample of the questions. HyperBrowseComp provides a challenging testbed for persistent information seeking across
languages and evidence modalities, with difficulty arising from discovering and connecting evidence on the open web.
Read the full abstract ▾
All authors Alham Fikri Aji, Faiz Rizki Ramadhan, Zayd M. K. Zuhri, Seung Hun Eddie Han, Ryandito Diandaru, Qinrong Cui, Jan Christian Blaise Cruz, Badrinath Chandana, Peerawat Chomphooyod, Ahmed Attia, Jonibek Mansurov, Emilio Villa-Cueva, Canh Duong Nguyen, Imran Turganov, Minghao Wu, Peerat Limkonchotiwat, Irina Nikishina
Artificial Intelligence
Learning to Assess Heartbeat Observability for mmWave Heart-Rate Sensing
Yuxuan Hu, Shilin Shan, Jianfei Yang et al. (+1 more)
Contactless heart-rate sensing with millimeter-wave (mmWave) radar requires assessing whether individual measurements support reliable estimation. We study learning to assess heartbeat observability, defined as the readability of the heartbeat component in an acquired phase spectrum, for selective heart-rate estimation. Coherent superposition of scatterer returns can suppress this component even under similar macroscopic observation geometry, motivating assessment directly from acquired measurements. To obtain training supervision across different observability conditions, we develop a controllable multi-scatterer frequency-modulated continuous-wave (FMCW) simulator. Agreement between the dominant heartbeat-band peak and the known heart rate provides an automatic observability label for each simulated measurement. We propose HEAR (Heartbeat Estimation with Assessed Reliability), a compact dual-task
Transformer that jointly predicts an observability score and heart rate. Its input combines spectral magnitudes with frequencies relative to the respiration fundamental, providing context for respiratory harmonics. Trained solely on simulated observations, HEAR transfers zero-shot to two public real-world
datasets collected at 60 and 120 GHz from 134 subjects. The same learned score supports selective prediction with both HEAR's own heart-rate head and multiple existing
estimators. On the 120 GHz
dataset, score-based selection reduces the HR head's mean absolute error from 17.9 BPM at full coverage to 1.6 BPM at 50% coverage. The complete pipeline achieves an end-to-end processing latency of 50.8 ms on an edge device. Project page: https://yuxuanhu9.github.io/HEAR/.
Read the full abstract ▾
All authors Yuxuan Hu, Shilin Shan, Jianfei Yang, Feng Xu
Artificial Intelligence
Knowledge or Calculator? Decomposing the Skill Premium in Verifiable Financial Agent Workflows
Jermyn Zhen Yong Bek, Zhuang Qiang Bok and Zhongtian Sun
Financial AI
agents must do more than retrieve facts: investment workflows require correct quantitative execution, reliable use of procedural resources, and auditable structured outputs. We introduce FinSkillBench, an evaluation suite of 2,603 point in time episodes across 12 subtasks in portfolio construction, risk management, and fundamental analysis, with hidden regenerable ground truth and task specific deterministic verifiers. Executing 17,820 episodes across 9 models and 3 resource conditions, the paired analysis across 8 models shows that curated skill packages raise mean scores by +16.2 points (0.366 to 0.528), whereas skills generated within a single episode add only +0.5 points while consuming more
tokens and turns. We then decompose the curated premium by granting human authored procedural documents and executable domain tools separately: documents alone add +5.6 points, tools alone add +19.5 points, and their combination is subadditive. The premium is strongly workflow dependent: executable tools dominate numerically intensive workflows, documentation matters more when procedural or output schema guidance is the bottleneck, and interpretive tasks benefit from both. The effects are sign stable across 10 scoring variants and cluster bootstrap analyses, and an independently implemented second harness reproduces the directional pattern while showing that effect magnitudes depend on how tools and data are exposed. Overall, a measured "skill premium" is a property of the full model, resource, and harness system rather than of the underlying model alone.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Cephalonauts One: A deep fMRI dataset for decoding naturalistic speech in the human brain
Antoine Collas, Louis Jalouzot, Géraud Ilinca et al. (+11 more)
Cephalonauts One is a whole-
brain 3 Tesla (3T) functional
magnetic resonance imaging (fMRI)
dataset recorded while subjects listened to audio podcasts. Three healthy subjects underwent multiple scanning sessions, each consisting of five 15-minute runs, while listening to podcasts in their native
language. With 30 hours of fMRI data per subject, the current release is the deepest available fMRI
dataset using naturalistic
speech stimuli. The
dataset pairs
brain activity with the corresponding podcast audio, transcript annotations, and derived stimulus
embeddings. Furthermore, we introduce a
brain decoding
benchmark formulated as audio segment
retrieval: given fMRI activity from a held-out session, the decoder must identify the corresponding time-aligned podcast audio segment among candidate segments. We provide standardized splits, evaluation metrics, and baseline decoders for this task. Finally, a scaling analysis shows that decoding performance improves continuously with the amount of training data per subject.
Read the full abstract ▾
All authors Antoine Collas, Louis Jalouzot, Géraud Ilinca, Corentin Caris, Romain Valabrègue, Ahmed Hassayoune, David Goncalves, Madeleine Hueber, Thaddée Delebarre, Julien Savatovsky, Clara Fonteneau, Charles Maussion, Bertrand Thirion, Alexis Thual
Artificial Intelligence
Recursive Harness Self-Improvement for Frontier Reasoning Data Synthesis
Wenlong Zhang, Zhengbo Jiao, Chenxu Zhang et al. (+5 more)
Generating progressively harder
reasoning problems requires synthesis procedures that adapt as the task distribution evolves. Existing task-level recursion reuses generated problems as seeds but leaves the construction harness unchanged. We present task-harness co-
evolution, a framework for recursive harness self-improvement (RSI) in
reasoning-data synthesis. Online self-improvement converts intermediate solver failures into reusable skills during generation. Post-task self-improvement revises skills,
prompts, and workflows after each batch, adopting candidates only when they generate harder valid tasks within a bounded cost increase. Model weights and verification criteria remain fixed. Across mathematics, coding, and science, mean solver accuracy decreases from 100.0% to 54.8% over fourteen
evolution rounds. Ablations show that combining both update schedules produces harder tasks than fixed-harness recursion or either schedule alone. The resulting data improves downstream SFT and GRPO performance. In particular, a 27B student fine-tuned on 10K synthesized mathematics examples achieves 62.5% mean-16 accuracy on APEX, competitive with selected frontier-model references. These results support adapting the synthesis harness alongside the tasks to generate increasingly challenging data with downstream training value.
Read the full abstract ▾
All authors Wenlong Zhang, Zhengbo Jiao, Chenxu Zhang, Lekang Jiang, SiYuan Ma, Qituan Zhang, Guo Chen, Linfeng Zhang
Artificial Intelligence · Cross-listed from cs.LG
Beyond Trained Models: Compiling GNNs for a Sound Explainer Benchmark
Steve Azzolin, Francesco Paolo Nerini, Stefano Teso et al. (+4 more)
Explainers for Graph Neural Networks (GNNs) are commonly evaluated by their plausibility, i.e., how well their explanations recover a predefined ground truth, such as a motif planted in the data. This protocol implicitly assumes that a GNN trained on such data relies on the intended motif. Although prior work has questioned this assumption, plausibility remains widespread. First, we show that the assumption is violated on several widely used
benchmarks, where, e.g., degree statistics alone suffice to solve the task. Then, we remove this confounder by replacing training with compilation. We achieve this by introducing $\mathsf{Gracr}$, the first compiler translating graded modal logic formulas into GNN weights, yielding models that replicate the behaviour of the corresponding formulas. Since the behaviour of the model is now known by construction, we can define its ground truth explanation formally and compute it exactly. Building on this, we introduce $\mathsf{Gracr}\mathsf{Bench}$, a
benchmark of compiled GNNs for the evaluation of explainers against this exact ground truth. Experiments on eleven explainers across six tasks show its effectiveness for fine-grained diagnostic evaluation: notably, we discover that most explainers are not robust to indirect influences or alternative implementations of the same formula. These results position $\mathsf{Gracr}\mathsf{Bench}$ as a novel, rigorous evaluation setting for graph post-hoc explainability.
Read the full abstract ▾
All authors Steve Azzolin, Francesco Paolo Nerini, Stefano Teso, Francesco Bonchi, Bruno Lepri, André Panisson, Andrea Passerini
Artificial Intelligence
From Benchmarks to Production: A Text-to-SQL System for Complex Financial Data
Arijit Sehanobish, Bruno Gomes Coelho, Guillaume Michel et al. (+3 more)
General-purpose Text-to-SQL systems achieve strong performance on academic
benchmarks like Spider and BIRD, where schemas are relatively shallow and column values are often human readable. In production financial databases, where concepts are stored as opaque integer keys rather than human-readable strings, these methods fall below 50%, as even simple queries require multiple joins and filter predicates reference opaque IDs. We present Financial LINking Text-to-SQL (FLINT), a domain-specialized Text-to-SQL system that closes this gap through three key components: (1) a lookup
agent that dynamically resolves natural-
language concepts to question-specific reference table constraints, (2)
embedding-based
retrieval of structurally similar query templates from a compact, expert-authored bank, and (3) schema linking that prunes a large table schema to the relevant subset by traversing foreign-key chains, rather than relying on name similarity alone. We evaluate on two
datasets totaling 359 questions over production financial schemas. FLINT outperforms various state-of-the-art baselines using the same LLM. The system is deployed in production as part of a financial data
retrieval service.
Read the full abstract ▾
All authors Arijit Sehanobish, Bruno Gomes Coelho, Guillaume Michel, Sophia Zhi, Valerie Faucon-Morin, Kristen Howell
Artificial Intelligence
Reasoning Models Are Accurate but Unsound on Identification
Arman Behnam and Binghui Wang
A
reasoning model asked whether a causal effect is recoverable from observational data can fail in two ways: it refuses an identifiable query or answers a nonidentifiable one. The latter is more consequential, as no observational data can validate the claimed formula. Measuring this failure requires queries that are provably non-identifiable, which prior evaluations lack, and grading that accepts correct formulas in any equivalent form, which string matching cannot provide. We build CERTID, a formal identification pipeline that addresses both limitations. CERTID uses the sound and complete causal identification
algorithm ID to certify whether an effect is identifiable from a given graph and query, and verifies returned formulas against structural causal models whose interventional distributions are known exactly. CERTID further develops theoretical results to mitigate structural leakage, repair non-identifiable queries, and establish grading guarantees. We evaluate three frontier
reasoning models (Gemini Flash, Gemini Pro, and GPT5.5) on 1,200 certified instances spanning 4 to 50 vertices. Accuracy proves a poor proxy for soundness: on identical instances, the false-claim rate on non-identifiable queries varies by seventeen-fold across models. We also find that models decide identifiability with 97-100% accuracy on graphs generated after the strongest model's training snapshot. Instances, the certification procedure, the verifier, and per-instance records are available at https://anonymous.4open.science/r/certid-D718.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Weave Forcing: Compositional Memory Routing for Interactive Long Video Generation
Ziyi Wang, Junchi Yao, Heqian Qiu et al. (+5 more)
Recent advances in autoregressive
video generation have improved temporal consistency over extended durations, yet interactive storytelling requires more than continuous scene extension: a new shot may combine characters and backgrounds from different historical shots. Whole
prompt retrieval can overlook the distinct reference needs of individual components, while directly combining all historical
memories may introduce unrelated visual content. To address these problems, we present Weave Forcing, a training-free framework for compositional
memory reuse in interactive long
video generation. First, we use an LLM for semantic slot routing to decompose user
prompts into character and background descriptions and explicitly select suitable historical references for each component. To isolate the required content, masked
memory weaving uses contrasting
attention maps conditioned on semantic slots to construct refined semantic masks, selectively exposing relevant
tokens from compressed historical KV
memories to guide the generation of the current shot. We further introduce coverage adaptive RoPE to adjust temporal offsets and
memory retention according to no, partial, or full reference coverage, addressing visual artifacts observed when incomplete historical references are positioned close to the current generation. Extensive experiments demonstrate that Weave Forcing improves cross-shot subject and background consistency while maintaining competitive visual quality and text
alignment.
Read the full abstract ▾
All authors Ziyi Wang, Junchi Yao, Heqian Qiu, Wenbo Shi, Chengjiu Wang, Jinyang He, Binkai Hong, Hongliang Li
Artificial Intelligence
Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and Monitorability
Samuel Lewis-Lim, Xingwei Tan, Mario Sanger et al. (+2 more)
Chain-of-thought (CoT)
reasoning allows humans to inspect how large
language models reach their answers, and oversee model behaviour. This
reasoning comes at an increased inference cost, motivating efficient methods that train models to solve tasks using fewer
tokens. However, a common concern is that such training may cause models to skip important
reasoning steps, so the CoT no longer faithfully reflects the model's decision. It is unclear whether or when this occurs in practice, since different efficiency methods apply length pressure to models' CoT in distinct ways, and faithfully explaining a model's decision takes more
tokens on some tasks than others. To understand these dynamics, we fine-tune a variety of models with three methods that apply length pressure differently, namely a fixed generation budget, a per-example length target, and a group-relative length reward. We evaluate how efficient
reasoning affects CoT faithfulness (i.e., how well the CoT reflects model decisions on related inputs) and monitorability (i.e., whether the CoT reveals when input interventions alter the output). We find that it affects faithfulness and monitorability differently. Faithfulness falls in most settings, primarily because the trained models are less consistent. Monitorability is more robust, as models keep acknowledging the influence on their answer even when the CoT is much shorter.
Read the full abstract ▾
All authors Samuel Lewis-Lim, Xingwei Tan, Mario Sanger, Zhixue Zhao, Nikolaos Aletras
Artificial Intelligence · Cross-listed from cs.LG
Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation
Md Sazid Uddin, Md. Khairul Alam Mazumder and M. F. Mridha
Mechanistic edits (ablations, weight edits, activation steering) are the standard tools for unlearning a harmful capability from a neural network while preserving useful ones. Current approaches validate their effects only by testing, which can never cover an entire continuous region of inputs. Prior work at the interpretability-verification boundary certifies descriptions of a model: what a
circuit computes, or whether it faithfully explains the whole. We instead certify the behavioral effect of an edit: that disabling a
circuit removes one skill and provably preserves another, for every input in a region; a feature non-interference guarantee in the information-flow-security sense. We demonstrate such certified edits from toy ReLU networks up to a standard softmax + LayerNorm
transformer, proving removal and preservation over continuous
embedding-space regions and reaching roughly 9x the input-perturbation dimension an exact solver can handle by switching to sound bound propagation. Furthermore, we prove that no finite deterministic black-box test can certify removal, exhibiting an edit that passes exhaustive testing yet provably fails on a survivor pocket that can be made arbitrarily small. Guarantees hold on small, standard-architecture networks and, like any removal claim, presuppose that the target skill admits a decidable specification, a property which real-world harms may not have.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Detect and Suppress: A Mechanistic Defense against Adversarial Patches in VLA Models
Yukiya Horiba, Koshiro Aoki, Shunsuke Yasuki et al. (+2 more)
Adversarial patches can disrupt
Vision-
Language-Action (VLA) models by manipulating visual observations, leading to failures in
robot control. However, it remains poorly understood which internal mechanisms underlie these failures and how targeted interventions can mitigate them. In this work, we mechanistically analyze VLA representations using a sparse autoencoder (SAE) and identify a feature whose activation strongly correlates with the presence of an
adversarial patch. Based on this analysis, we suppress the identified feature at inference time only when a linear probe detects an attack. This intervention improves robustness without the cost of fine-tuning the VLA. We evaluate our method against VLA
adversarial patch attacks on LIBERO-10. Conditional intervention improves success rate under intermittent attacks, whereas continuously applying the same intervention substantially degrades policy performance. These results show that attack-related internal representations can provide useful targets for VLA
adversarial defense and that controlling when to intervene is important for limiting disruption to nominal policy behavior.
Read the full abstract ▾
All authors Yukiya Horiba, Koshiro Aoki, Shunsuke Yasuki, Bum Jun Kim, Taiki Miyanishi
Artificial Intelligence · Cross-listed from stat.ML
AREX: Affine-Residual Exponential Integrator for Few-Step Sampling in Flow Matching
Shizheng Lin, Soon Hoe Lim and N. Benjamin Erichson
We introduce AREX, a training-free sampler for pretrained flow matching models that uses the target mean and covariance to capture an analytically tractable part of the sampling dynamics. We show that the velocity field of the moment-matched Gaussian target is the $L^2$-optimal affine approximation to the marginal velocity field. This motivates decomposition of the learned dynamics into an affine component over the whole sampling path, determined by the first two target moments, and a neural residual term. AREX keeps the affine component and integrates it using an explicit
matrix-valued propagator. In turn, we only require to integrate over the residual term. This differs from scalar exponential integrators, which analytically handle only isotropic linear dynamics. Across image and text-to-image generation tasks, AREX consistently improves sample fidelity in the few-step sampling regime without retraining the underlying model.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
MobiAgent: Dual-Loop Recursive Policy Self-Improvement for Long-Horizon Mobile Manipulation
Chenzhi Liu, Yue Zhang, Jiehong Lin et al. (+4 more)
Long-horizon mobile manipulation presents significant challenges due to compounding execution errors and capacity interference between locomotion and arm control. While recent
Vision-
Language-Action models excel at short-horizon tasks, they lack the hierarchical
reasoning required for multi-stage objectives. Furthermore, existing hierarchical
agents suffer from rigid sub-task mapping, inflexible replanning, and a lack of continuous learning. To address these limitations, we introduce MobiAgent, a dual-loop agentic framework that bridges robust deployment execution and recursive policy self-improvement. During deployment, the Inner Loop decouples high-level
reasoning from low-level control through highly composable atomic skills. It employs
Vision-
Language models for receding-horizon planning and visual reflection, dynamically composing skills to ensure robust error recovery. These skills are executed by specialized flow-matching experts that share a unified VLM backbone, maximizing reusability while mitigating capacity interference. Concurrently, the Outer Loop drives automated lifelong learning by autonomously segmenting and verifying deployment rollouts, clustering them to discover atomic skills, and continuously fine-tuning the skill library without human annotations. Evaluations on RoboCasa, BEHAVIOR-1K, and real-world tasks demonstrate the effectiveness of MobiAgent. It outperforms $\pi_{0.5}$-TA by 22.5 percentage points on BEHAVIOR-1K and enables robust recovery from execution failures. Through autonomous data recycling, success improves from 7.50% to 27.50% on RoboCasa and from 32.5% to 57.5% on Astribot S1.
Read the full abstract ▾
All authors Chenzhi Liu, Yue Zhang, Jiehong Lin, Jianan Wang, Bo Wang, Zhongrui Wang, Xiaojuan Qi
Artificial Intelligence · Cross-listed from cs.LG
Single or Multiple Policies for Phase-Structured Reinforcement Learning?
Guilhem Loussouarn, Nancy Nayak and Kin K. Leung
Many reinforcement-learning (RL) problems are non-stationary yet structured and can be decomposed into phases, each with its own transition probabilities and reward functions. When the phase sequence is known, the common solution augments the state with information to satisfy the Markovian property and applies standard RL techniques. However, prior work finds that the multi-policy approach for different phases can outperform a single state-augmented policy shared among the phases, for reasons that remain unclear. In this work, we first show that the shared policy can theoretically achieve performance of any multi-policy solution. However, whether a multi-policy solution can perform better than the corresponding single shared policy in practice depends on function approximation, learning and optimization processes, as well as, for multi-policy solutions, the sample efficiency and loss of continuity from one policy to another. We propose a regime-based phase decomposition method to identify which policy can provide better performance. The method is based on consideration of the duration of transient system dynamics relative to the duration of the quasi-stationary period. Numerical experiments are conducted with different non-stationary RL problems to validate our four major hypotheses: (a) longer phase durations favor multi-policies, (b) the heterogeneity between phases increases the burden on single policy, (c) multi-policies need sufficient data for each phase, and (d) environment-specific transition dynamics between phases can affect which policy is preferable.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CV
Preserving Anatomical Continuity: Three-Stage Pipeline for Colon Segmentation in 3D Abdominal CT Scans
Deshan Kalupahana, Sonit Singh, Praveen Ravindran et al. (+1 more)
Accurate colon segmentation from CT images is essential for colorectal disease analysis, yet deep learning based methods often produce disconnected predictions due to complex anatomy. This study introduces a three-stage,
topology-preserving segmentation pipeline to address this issue. The first stage performs initial deep learning-based segmentation, followed by centreline bridging to reconnect disjoint regions and a reconstruction stage to refine continuity. Evaluations on TotalSegmentator and RAOS
datasets using overlap, distance and
topology-based metrics demonstrate improved structural consistency while maintaining segmentation accuracy. The proposed method enhances topological integrity, enabling more reliable colon segmentation for clinical and research applications.
Read the full abstract ▾
All authors Deshan Kalupahana, Sonit Singh, Praveen Ravindran, Arcot Sowmya