Research

• Compositional coverage and decision grounding in trajectory supervision1 paper raises it · 1 addresses it

  Current tool-use trajectories often lack multi-step dependencies and justified actions, limiting effective agent learning.

  • Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agentsraises · addresses
• Benchmarking agent harness reliability and failure attribution1 paper raises it · 1 addresses it

  Existing benchmarks focus on model capabilities, neglecting the evaluation of agent harnesses and their reliability.

  • Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attributionraises · addresses
• Compositionality of RAG pipeline components1 paper raises it · 1 addresses it

  Isolated gains in RAG components do not necessarily compose, and optimizing one metric can hurt another.

  • Retrieval Augmented Generation Compositionalityraises · addresses
• Token collapse in graph soft prompting1 paper raises it · 0 address it

  Graph-specific tokens in textual graph soft prompting become indistinguishable, failing to convey graph content.

  • On the Token Collapse Phenomenon in Textual Graph Soft Promptingraises
• Label-free monitoring in self-supervised learning1 paper raises it · 0 address it

  Standard signals like loss and feature statistics fail to detect encoder degradation in self-supervised training.

  • Improving Signals, Declining Encoder: A Known-Answer Test of Label-Free Monitoring in Self-Supervised Learningraises

Named by an AI from these papers' abstracts.

• arXiv cs.LGOct 9

  Private and Distributionally Robust Federated Multiclass Classification

  Andrea P. Hernandez, Michael Ibrahim, Nagi Gebraeel

  Fault diagnosis in asset-intensive industries requires multiclass models trained on noisy, sensitive data collected across geographically distributed client sites. Federated learning enables collaborative training without centralizing data, but most approaches do not provide formal privacy guarantees for individual records stored at client sites and can degrade under label noise. To address these limitations, we develop a differentially private, distributionally robust framework for federated multiclass classification that provides sample-level privacy for records stored at each client. We build on a federated Wasserstein distributionally robust multiclass objective with the Crammer-Singer loss, solved using an Alternating Direction Method of Multipliers (ADMM)-based algorithm. To protect the released client updates, our method injects calibrated Gaussian noise into the proximal linearized client updates of both the local model and the local distributionally robust variable before aggregation at the central server, and we quantify the cumulative privacy loss using the moments accountant. We provide per-round sample-level $(ε,δ)$-differential privacy guarantees and an overall…

  PDF

  Summarize this
• arXiv cs.CLOct 9▲ 48

  Multi-Stream Attention Residuals

  Xiaohan Qin, Xiangdong Zhang, Tuo Dai, Sunan Zou, Huaijin Wu +5

  Attention Residuals (AttnRes) enables content-dependent retrieval over network depth, which can be viewed as single-stream softmax attention along the depth axis. Inspired by the success of multi-head attention along the sequence axis, we introduce Multi-Stream Attention Residuals (MSAR), an extension of AttnRes that generalizes this mechanism to multi-head depth attention, yielding substantial performance gains with minimal additional overhead. MSAR draws stream diversity from sequence context through multi-scale causal convolutions, allowing different heads to retrieve historical representations through distinct contextual views while preserving the integrity of the hidden representation. The retrieved streams are combined through lightweight adaptive mixing to generate the single-stream layer input. By retaining single-stream sources and expanding them on demand, MSAR supports multi-stream computation without requiring persistent multi-stream storage or communication. Across all 12 downstream benchmarks at the 18B and 28B MoE scales, MSAR consistently outperforms prior residual variants, including standard residual connections, manifold-constrained Hyper-Connections (mHC), and…

  CodePDF

  Summarize this
• arXiv cs.ROOct 9

  JitterVLA: A Replay Benchmark for Motion Quality in VLA-Driven Human-Robot Manipulation

  Faith Ogunwoye, Didar Seyidov, Konstantin Gubernatorov, Dzmitry Tsetserukou

  Vision-language-action (VLA) policies issue sparse targets whose arrival at the robot controller is delayed and irregular, so a reasonable predicted action can still produce abrupt motion near people. Remedies are evaluated on different streams, delays and metrics. JitterVLA replays identical commands and arrival traces through alternative controllers, isolating the controller's effect. We apply it to synthetic reaches, hand trajectories from 20 people, three open VLA pipelines (838 episodes) and a physical UR3. Interpolation lowered modeled p99 jerk for every source, by 83% (615 to 106 m/s^3) on human motion with 200 ms delay, at a 2.0 cm tracking cost, and the effect replicated on 598 new episodes; jerk-limited generation lowered jerk further at a larger cost. Entropy-discontinuity associations had opposite, replicated signs in two pipelines, and entropy gating helped in one but not the other. On the UR3, interpolation lowered accelerometer-derived jerk by 3.0-14.0% in all six exploratory pairs, while a position-derived metric did not resolve the contrast. JitterVLA supports screening before human-centred studies; code and data will be released.

  PDF

  Summarize this
• arXiv cs.CLOct 9▲ 13

  AMLworld-Compact: Importance-Weighted Downsampling for Cost-Effective LLM Evaluation and Error Diagnosis

  Natapong Nitarach, Phume Ngampornsukswadi, Pittawat Taveekitworachai, Surapon Nonesung, Warit Sirichotedumrong +1

  Evaluating large language models (LLMs) on AMLworld's smallest test splits is costly because each of over a million targets requires a separate graph prompt. Sampling reduces this cost, but small balanced subsets change unweighted precision and F1. We introduce AMLworld-Compact, an evaluation set that retains every illicit test transaction and samples benign transactions from supervised-score strata. Its HT-Coreset protocol reduces evaluation targets by 271x and 611x on HI-Small and LI-Small. Horvitz-Thompson weights give unbiased full-test confusion-count estimates for fixed predictions; recall is exact, while precision and F1 are ratio estimates. In a held-out study using Graph Feature Preprocessor (GFP) features, one boosted-tree family defines strata for evaluating the other over 500 draws per configuration. At the released sizes, F1 RMSE is 0.00-2.58 percentage points versus 4.44-7.41 for uniform sampling with HT weights; conservative intervals remain broad. Under the evaluated graph prompts, seven open-weight LLMs have weighted precision near the predict-all-illicit baseline. In an outcome-stratified audit of 1,000 HI-Small few-shot outputs from one run per model, lexical…

  Code
• arXiv cs.SEOct 9

  SWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development Lifecycle

  Xiting Liu, Lin Yang, Yitong Zhang, Jia Li, Shi-Min Hu

  Large Language Models (LLMs) are increasingly used throughout the software development lifecycle. This growing reliance on LLMs raises concerns about their trustworthiness, with deception posing a particularly important risk. Deceptive behavior takes the form of misleading responses or assistance in fabricating, concealing, or distorting information. To study this behavior, we introduce SWE-DeceptionBench, a benchmark for evaluating LLM deception in software engineering. The benchmark covers six lifecycle stages and two deception triggers: Active Deception, where models recognize infeasible or conflicting requirements but still present them as achievable, and Passive Deception, where models help fulfill explicit user requests to mislead others. We further introduce Neutral, Reward, and Pressure conditions to study the effect of external inducements, resulting in 720 test instances in Chinese and English. Evaluating seven mainstream LLMs, we find substantial deception even under the Neutral condition, with aggregate rates of 49.88% for Active Deception and 64.29% for Passive Deception. Deception rates vary across lifecycle stages, and external inducements affect Active and Passive…

  PDF

  Summarize this
• arXiv stat.MEOct 9

  Kernel-based External Validity of Experimental Studies

  Federico Matteucci, Gerhard Neumann

  The external validity of a study is the extent to which its findings generalize to unseen experimental conditions, such as datasets. We formalize the results of a study together with its research question, and define external validity as the probability that two independent and same-sized replications of the study produce results whose maximum mean discrepancy (MMD) is below a given tolerance. This approach, centered on the choice of a space of results and of an appropriate reproducing kernel for the MMD, is flexible enough to be deployed on multiple different types of results and research questions. Additionally, we establish an asymptotic power-law relation between the size of a study and the quantiles of the MMD, which we use to estimate the desired size of an externally valid study from a small-scale preliminary study. We deploy our framework to rankings with ties and discuss kernels suited to different research questions. Experiments on existing case studies and on a simulated newly designed study illustrate the applicability of the framework. We release our code as part of the genexpy Python module.

  PDF

  Summarize this
• arXiv cs.CROct 9▲ 20

  APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces

  Ziyi Yang, Adel Bibi, Guohao Li, Bernard Ghanem, Carlos Hinojosa

  Professional agents increasingly work through command-line interfaces and multiple tools over shared workspaces containing files, messages, and business applications. These environments create safety risks that are difficult to capture with attacks placed at a single, known read location. We introduce APEX-Harm, a benchmark for evaluating prompt and script injection against long-horizon agents performing finance, consulting, and legal tasks in large workspaces. Each task contains 115 to 328 files, together with email, calendar, chat, document, spreadsheet, PDF, and code-execution tools exposed through MCP servers. The benchmark includes six attack categories covering static and dynamic injections, task-specific script replacement, and attacker-provided generic scripts, and evaluates attack success, exposure, and task performance. We evaluate 12 frontier models on 180 task instances per model. Opus 5 and Sonnet 5 have the lowest overall attack success rates (8% and 20%), while task-specific script replacement and attacker-provided generic script attacks remain substantially more effective, averaging 81-84% and 73% attack success, respectively. Gemini 3.8 Flash achieves the highest…

  Code
• arXiv cs.CLOct 9

  Training User Simulators with Latent Intrinsic Feedback

  Tarek Naous, Craig Boutilier, Wei Xu, Ofer Meshi

  User simulators are gaining attention as environments to train LLM assistants that can better cope with the nuances of multi-turn conversations with real users. Prior work on user simulation has emphasized generating realistic user utterances, leaving unexplored their potential as a source of direct feedback on the assistant's responses. Such evaluation signals may not be explicitly communicated in language, but can instead reside in the latent reasoning of users. In this work, we introduce user simulators with intrinsic feedback, namely, models equipped with latent evaluation states: internal thoughts, reactions, and scalar ratings that evaluate the assistant from a first-person user perspective at each conversation turn. We train LLM-based simulators using interaction logs between real users and assistants and demonstrate that intrinsic feedback improves simulation realism and critiquing behaviors versus prompted simulator baselines, while also providing turn-level evaluations that existing fine-tuned simulators lack. Further, evaluations generated by our trained simulators correlate better with human judgments than those of prompted simulators of the same size. Lastly, our…

  PDF

  Summarize this
• arXiv stat.MLOct 9

  Some remarks on the connection between generative diffusion and optimal transport

  Giulio Biroli, Marc Mézard

  We discuss three simple connections between generative diffusion and optimal transport. First, the joint law of the data and of their Ornstein-Uhlenbeck noising is, at every time, the solution of an entropic optimal-transport problem, at a temperature set by the noise level. Backward diffusion can consequently be read as an annealing which gradually decreases the entropic regularization. Second, we study the speciation transition--how the modes of the data distribution emerge during generation--and compare how it happens in diffusion and flow matching with respect to optimal transport. Using Gaussian mixtures as high-dimensional example, we show that the dynamical instability through which diffusion and flow matching separate the modes becomes, for optimal transport, an exponentially thin boundary layer at the beginning of generation, which is rounded by entropic regularization. Third, considering a generic forward dynamics with a general confining potential, we show that the backward process driven by the score also satisfies a drift-based variational principle whose minimal cost is the entropy difference between initial and final distributions.

  PDF

  Summarize this
• arXiv cs.CVOct 9

  CUBE: Class-conditioned Unknown Boundary Evidence for Open-Set Insect Species Recognition

  Hao Tan, Qimin Zhang, Zhe Xiao, Zekai Zuo, Wanting Liu +1

  Open-set insect species recognition faces significant challenges when deployed in real-world biodiversity scenarios, particularly when encountering unknown species that are visually close to known training classes. Unlike generic out-of-distribution samples, fine-grained unknown insects are often not visually anomalous. They instead tend to appear near the decision boundary of specific known species, leading to unreliable closed-set predictions. To address these challenges, we propose \textbf{Class-conditioned Unknown Boundary Evidence (CUBE)}, a novel evidence-based framework that models unknownness around each known species rather than as a single global unknown class. Our key idea is to evaluate a test sample relative to the known species it most closely resembles, enabling local rejection for visually confusable unknown insects. CUBE learns class-conditioned boundary evidence from auxiliary species, preserves auxiliary species as shadow references during inference, and incorporates taxonomic candidate calibration to verify biological plausibility. When ecological metadata is available, we further introduce CUBE-E, which adds a lightweight location-consistency term without…

  PDF

  Summarize this
• arXiv eess.ASOct 9

  Vocal Intensity Conversion with Continuous SPL Control via Adversarial Training

  Quentin Le Tellier, Albert Rilliard, Olivier Perrotin, Marc Evrard

  Vocal intensity conversion renders a recorded utterance at a different vocal intensity, rather than simply scaling its amplitude, while preserving its content and speaker identity. Existing systems control intensity through a reference utterance or a few discrete categories. Instead, we control the conversion with any target sound pressure level (SPL) on a continuous dB scale. A lightweight converter, trained as a conditional cycle-consistent GAN without parallel data, transforms the features of a frozen speech encoder, from which a pretrained vocoder resynthesizes the speech. We compare three representations, log-mel spectrograms, WavLM, and SpeechTokenizer, and introduce an objective protocol that measures the achieved intensity change against the target one on a calibrated corpus. With WavLM, the converter achieves a measured 83% of the target change in intensity and also shifts the fundamental frequency. A perceptual evaluation confirms that perceived vocal intensity increases with the target level on amplitude-normalized stimuli.

  PDF

  Summarize this
• arXiv cs.CLOct 9

  BLiMPPI: Benchmark of Linguistic Minimal Pairs for Polarity Items

  Arzu Burcu Güven, Anna Rogers, Leonie Weissweiler, Joakim Nivre, Rob van der Goot

  Negative polarity items (NPIs), such as "anymore" and "ever", are grammatical only in select environments, predominantly in the context of negation. Because their grammaticality depends on both syntax and semantics, they have a rich, multilingual literature in theoretical linguistics, yet work on NPIs in language models is almost entirely confined to English. We introduce BLiMPPI, a multilingual evaluation suite of over 12,000 NPI minimal pairs in 33 languages, built by a pipeline that discovers NPIs in Universal Dependencies (UD) treebanks, labels their licensing environments, and perturbs these into minimal pairs. Evaluating 12 multilingual and 2 monolingual models alongside n-gram baselines, we find that multilingual models struggle most with lower-resource languages and with pairs that are not n-gram solvable. We further examine the effects of NPI typology, language family, licensing variability, and NPI-licenser distance. Data: https://github.com/arzuburcuguven/blimppi-data

  PDF

  Summarize this
• arXiv stat.MLOct 9

  CorrFlow: Exact and Permutation-Equivariant Flow Matching on the Correlation Elliptope

  Gautier Marti

  Correlation matrices combine nonlinear positive-definiteness constraints with a simultaneous row-column permutation symmetry. Their generation therefore involves two distinct problems. First, every output must remain on the correlation elliptope, irrespective of how its variables are ordered. Second, the generator must learn the domain-specific distribution occupied by empirical data inside that valid space. Existing financial image generators mix these problems: they learn ordered matrix entries and repair invalid draws afterward. We introduce CorrFlow, which separates them. A generalized Fisher transform maps full-rank correlation matrices bijectively to unconstrained coordinates, guaranteeing valid outputs without projection. A graph flow-matching network learns the empirical distribution in those coordinates and is permutation equivariant: reordering the variables only reorders the output. We compare a conditional CorrGAN reimplementation, image diffusion, and CorrFlow on $80\times80$ Taiwan equity matrices using five seeds per neural method. CorrFlow produces 100% valid draws without repair and obtains feature sliced-Wasserstein distance $.712\pm.141$, versus $4.339\pm.252$…

  PDF

  Summarize this
• arXiv cs.CLOct 9

  zip2zip++: Towards Inference-Time Token Compression with Minimal Quality Loss

  Saibo Geng, Andrea Gentilini, Xinxian Ma, Nathan Ranchin, Yunzhen Yao +1

  Dynamic vocabularies built on-the-fly via Lempel-Ziv-Welch (LZW) compression let a language model represent the same text in fewer tokens, but prior work shows that this efficiency comes at a cost to reasoning and perplexity. We show that this quality gap is not a fundamental price of compression but can be substantially closed through targeted improvements to the compression layer and LZW codec, without modifying the underlying pretrained language model. Our analysis reveals four key issues: (1) LZW's compression algorithm creates an implicit conflict between the input embedding and the output embedding, a tension that a single shared embedding cannot resolve; (2) naively applying RoPE to LZW-compressed sequences ignores that merged tokens can span multiple tokens; (3) merging certain tokens (notably digits) disproportionately hurts downstream accuracy; and (4) dynamic vocabularies introduce an inherent segmentation ambiguity that confounds standard evaluation. We address these through decoupled input/output dynamic embedding layer, size-aware RoPE positioning, and a modified LZW codec supporting selective merges and multi-view segmentations. Across four models, our recipe…

  PDF

  Summarize this
• arXiv cs.CVOct 9

  Thyroid Nodule Segmentation in Ultrasound Images with Conformal Uncertainty Estimation

  Francesco Teodori, Pierpaolo Brutti, Umberto Ferraro Petrillo

  Thyroid nodules affect a large proportion of the general population. Although most are benign, a non-negligible fraction is malignant. Ultrasound imaging is the primary diagnostic modality, and accurate nodule segmentation is a prerequisite for CAD systems to classify malignancy and assess metastatic risk.\\ In this work, we propose a thyroid nodule segmentation framework that integrates a DeepLabV3+, channel-attention modules and post-hoc conformal prediction, providing both accurate mask and pixel-level uncertainty estimates. We address thyroid ultrasound nodule segmentation as the first stage of a pipeline that also includes malignancy classification and metastatic risk prediction. We adopt DeepLabV3+, whose Atrous Spatial Pyramid Pooling (ASPP) captures multi-scale context, with an EfficientNet-B5 backbone for its accuracy-efficiency trade-off. Additionally, we test three channel-attention modules: Squeeze-and-Excitation, CBAM and Grouped Channel Attention (GCA), paired with two loss formulations (Dice-BCE and Boundary).\\ Since binary masks do not indicate prediction confidence, we wrap the trained model with a split conformal prediction layer that produces pixel-level…

  PDF

  Summarize this
• arXiv cs.LGOct 9

  A small cognitive core explains human behavior at scale

  Marcel Binz, Eric Schulz

  Psychology has proposed many principles of cognition. Each, however, was developed in isolation, leaving their combined explanatory power unknown. We assembled a small set of established principles into one model, which we call COntextual Retrieval and Encoding (CORE). CORE consists of a hierarchy of episodic memories into which prediction errors are written and whose encoding, retrieval, and forgetting depend on context. Fitted jointly to 7,036,442 choices from 137 experiments, the model predicts human choices better than black-box models and reproduces 75% of reported behavioral effects when simulated. Moreover, its latent variables show classic signatures of Bayesian learning and event segmentation. Taken together, these findings suggest that a small cognitive core accounts for much of human behavior. They also open a path toward making psychology more than the sum of its parts, by building computational models on the entire experimental record.

  PDF

  Summarize this
• arXiv eess.IVOct 9

  Exploring the Latent Structure of AMD Severity Using Retinal Foundation Models

  Niccolò Fineschi, Jovana Panic, Atsushi Watanabe, Hideaki Hayashi, Kazuya Nishimura +5

  Retinal foundation models have demonstrated strong performance across a wide range of ophthalmic tasks, yet relatively little is known about how disease-related information is represented within their learned embeddings and whether this distribution influences downstream prediction performance. In this work, we use Age-related Macular Degeneration (AMD) as a case study to investigate how disease severity is represented within the embedding space of RET-CLIP, a retinal vision-language foundation model, using bilateral fundus images from the AREDS dataset, benchmarked against non-retinal encoders. We first characterize the distribution of AMD severity within the learned representation space and then evaluate how this structure influences classification performance across three clinically relevant task formulations of increasing granularity. Finally, we analyze the most influential latent dimensions combining feature attribution, statistical phenotype association, and qualitative image analyses. Our results show that RET-CLIP represents AMD severity as a continuous spectrum rather than a set of discrete categories, with healthy and advanced disease stages exhibiting clearer…

  PDF

  Summarize this
• arXiv cs.SDOct 9

  AudioTETRIS: Token Elimination via Transitional Importance Signals for Efficient Audio LLMs

  Shreya Sajid, Anna Vettoruzzo, Joaquin Vanschoren

  Large Audio Language Models (LALMs) achieve strong performance on speech-text tasks, but standard audio encoders produce hundreds of tokens for even short audio clips. Because self-attention scales quadratically in sequence length, this inflates inference-time compute substantially. Current training-free token compression methods prune or merge tokens based solely on coarse attention or feature similarity. However, treating audio tokens as generic, isotropic features smooths over spectral transitions, destroying fine-grained phonetic transitions essential for decoding speech. In contrast, speech signals exhibit highly structured temporal patterns where information density peaks at acoustic transitions. We propose AudioTETRIS, a training-free, two-stage framework that uses the audio encoder's representation geometry as an acoustic prior for token importance before applying attention-based compression. Instead of discarding encoder structure after the encoding stage, AudioTETRIS propagates this prior directly into the LLM decoder to compute a per-token fused score. This score drives progressive top-$k$ token selection across decoder layers without requiring additional training or…

  PDF

  Summarize this
• arXiv cs.LGOct 9

  EchoTab: Learning Measurement-Grounded Representations for Echocardiographic Diagnosis through Tabular Reconstruction

  Michelle Espranita Liman, Ioana Ionac, Alexander Müller, Eimo Martens, Daniel Rueckert +1

  Diagnostic information in multi-view medical imaging studies, like echocardiography, is distributed across views, each capturing different aspects of cardiac structure and function. In clinical practice, these views are first interpreted through quantitative measurements, which then support specific diagnoses. However, existing echo representation learning methods do not explicitly model measurements as an intermediate representation between views and diagnosis. As a result, individual measurements are not explicitly represented in a form that downstream diagnostic tasks can selectively use, hindering accurate diagnosis. Inspired by this hierarchical clinical workflow, we introduce EchoTab, a measurement-grounded representation learning framework that represents multi-view echocardiography studies using measurement-specific tokens as an intermediate representation between echo views and diagnosis. Each measurement token selectively attends to the views relevant to its estimation and is trained through tabular reconstruction to predict the corresponding measurement value. The resulting tokens form a factorized echo representation, which encode clinically meaningful structural and…

  PDF

  Summarize this
• arXiv hep-thOct 9

  TheoPhysEval: Assessing AI agents at autonomous theoretical physics problem solving

  A. Ramesh Chandra, Aaghaz Mahajan, Ainesh Sanyal, Mianqi Wang, Shubhadeep Chakraborty +30

  We present a suite of 50 unpublished research-level theoretical physics problems with verifiable answers. Without AI assistance, a typical problem in our collection could be solved by a world expert in about a day or less but would take considerably longer for experts in adjacent specialties. We test the ability of off-the-shelf AI agents to tackle these problems autonomously, without human hints. When given access to tools available in a realistic setting, including the ability to search the literature and write scripts for numerical and symbolic work, the best-performing agent, GPT-6-Astra harnessed in Codex, obtains the final answers with a near-perfect accuracy of 98% at an average cost under USD 3 per problem. On average, agents show only small changes in accuracy when denied web search and access to background research papers, suggesting significant memorization of the literature. These results suggest that state-of-the-art agents can accurately perform concrete calculations required across theoretical physics research. We comment on the broader implications of these findings and discuss possible explanations for the current lack of agent-led breakthroughs in theoretical…

  PDF

  Summarize this

• Anomaly detectors24+71.4%
• Channel state information15+36.4%
• AI tutors15+36.4%
• Character recognition OCR12+20.0%
• Multimodal emotion8+14.3%
• Physics informed neural132−10.2%
• Machine learned interatomic37−15.9%
• Supervised & diffusion models91−24.8%