Research

• Dynamic model and policy routing for general-purpose AI1 paper raises it · 1 addresses it

  Balancing performance and computational cost across diverse tasks and modalities is critical for scalable AI systems.

  • Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systemsraises · addresses
• Cross-repository consistency in coding agents1 paper raises it · 0 address it

  Real-world software development often requires coordinated changes across interdependent repositories, which current agents struggle to maintain.

  • CrossSWE: Benchmarking Cross-Repository Joint Development for Coding Agentsraises
• Efficient long-video generation with consistent quality1 paper raises it · 1 addresses it

  Real-time streaming video generation demands continuous output without quality degradation or camera drift.

  • Wave Forcing: Towards Speed-of-Light Streaming Video Generationraises · addresses
• Local decision-making for reasoning compression1 paper raises it · 1 addresses it

  Reducing inference costs without sacrificing accuracy requires models to know when to stop reasoning.

  • Think Less, Locally: Local Preference Learning for Reasoning Compressionraises · addresses
• Unified taxonomy and coordination for agentic systems1 paper raises it · 1 addresses it

  Fragmented terminology and rapid growth in agentic systems hinder systematic understanding and collaboration.

  • Advances in Agentic Computer Graphicsraises · addresses

Named by an AI from these papers' abstracts.

• arXiv cs.LGSep 30

  Grand Canonical Generators

  Andreas Burger, Malte Franke, Luka Mucko, Kjell Jorner, Alan Aspuru-Guzik

  We introduce Grand Canonical Generators (GCG), a generative framework that extends Boltzmann generators to the grand canonical ensemble. We present two designs. The first conditions a variable-size generative model on the chemical potential, sampling particle number and configuration jointly. The second factorizes the grand canonical distribution into a particle-number distribution and the corresponding canonical Boltzmann density. This factorized formulation can use any existing Boltzmann generator for the canonical component, encodes the known linear chemical-potential dependence analytically, and yields a tractable likelihood that supports self-normalized importance sampling (SNIS). Empirically, GCG accurately reproduces grand canonical observables on a Lennard--Jones fluid and methane adsorption in a zeolite, demonstrating generalization across chemical potentials and correction via SNIS and grand canonical Monte Carlo.

  PDF

  Summarize this
• arXiv cs.AISep 30

  Ontology-Grounded, Reasoner-Verified Benchmarks for Evaluating LLM Reasoning in Scientific AI

  Nishtha N. Vaidya, Stephan Grimm, Thomas Hubauer, Thomas A. Runkler

  Large language models (LLMs) increasingly underpin scientific AI applications that reason over structured knowledge, from biomedical question answering to materials informatics. However, their logical reasoning often falls short, producing factual inaccuracies unacceptable in these settings. Reliable evaluation remains challenging: manual dataset construction scales poorly, and LLM-based generation risks embedding the very flaws it aims to measure. High-quality benchmarks must ground both correct and incorrect labelled examples in explicit background knowledge, formally verifiable by a standard reasoner. We propose a pipeline that automatically generates ontology-grounded multiple-choice question (MCQ) benchmarks from any sufficiently axiomatised OWL 2 ontology, with correct answers grounded in the ontology by design. Distractors are generated by perturbing the right-hand-side class expressions of class definition axioms, and their incorrectness is formally verified by an OWL reasoner via entailment checks. We evaluate the pipeline on three ontologies: Pizza (small, academic), PMDco (complex, materials science), and DOID (large, biomedical), generating 112, 2,491, and 15,216 MCQs…

  PDF

  Summarize this
• arXiv cs.LGSep 30

  Curvature Under Attack in hZACH-ViT: Gauge Symmetry, Boundary Saturation, and Adversarial Failure

  Athanasios Angelakis, Marta Gomez-Barrero

  Curvature is often treated as an intrinsic property of a representation, although its empirical effect also depends on coordinate scale, learned logit temperature, and numerical safeguards. We study this interaction in hZACH-ViT, a compact Vision Transformer with Euclidean, Poincare, and spherical prototype heads. The backbone architecture, seed-specific initialization, 50-per-class training subset, and optimization protocol are matched across three MedMNIST datasets and five seeds. At the fixed comparison curvature $c=1$, Poincare has the lowest class-macro PGD attack-success rate in all 12 dataset-budget cells and under a stronger CE+DLR multi-restart attack on all three datasets, but it also has the lowest clean MacroF1. An end-to-end curvature intervention changes the interpretation. Reducing Poincare curvature to $c=0.1$ improves clean MacroF1 in every one of the 15 paired seed-dataset comparisons and removes hard boundary clipping, yet on OrganAMNIST it increases strong attack success from $89.7\%$ to $99.3\%$ (paired difference $+9.57$ points; 95\% hierarchical bootstrap CI $[+5.52,+14.03]$). At $c=1$, $40$-$47\%$ of clean Poincare features are hard-clipped, the radial…

  PDF

  Summarize this
• arXiv cs.CLSep 30

  Bayesian Fine-tuning Yields Language Models that are as Bayesian as their Beliefs Allow

  Polina Tsvilodub, Andreas Waldis, Linlu Qiu, Tal Linzen, Michael Franke

  Language models (LMs) are increasingly used for tasks that require reasoning about hidden variables from a few observations, for which Bayesian inference is the normatively correct solution. While supervised fine-tuning of an LM on the outputs of an optimal $\textit{Bayesian}$ model leads to near-Bayesian behavior, standard supervised fine-tuning (SFT) on the true answers for the task falls short of it. But behavior alone does not tell us $\textit{why}$ tuning on a $\textit{Bayesian}$ or an $\textit{oracle}$ (true answers) signal differs: whether the resulting LM represents Bayesian beliefs, acts on them, or turns them into a choice the way Bayes' rule does. To compare them, we formulate increasingly demanding requirements for an LM to count as a Bayesian decision maker, spanning its behavior, representations, and computations, and test them on a flight recommendation task. The Bayes-trained LM acts Bayesian, encodes quantities of Bayes' rule in its middle layers, and uses the encoded belief for the recommendation to a certain extent. The oracle-trained LM differs from it both in the beliefs it holds and whether it reads beliefs out into recommendations. Exchanging beliefs…

  PDF

  Summarize this
• arXiv eess.IVComputer visionSep 30

  Nonparametric Distribution Matching for Self-Supervised Whole-Slide Image Condensation

  Duong M. Nguyen, Trong Nghia Hoang, Hang Thi Nguyen, Thanh Trung Huynh, Phi Le Nguyen +1

  Histological whole-slide images (WSIs) are central to computational pathology but pose severe computational challenges due to their extremely high resolution, often spanning several gigabytes per slide. To enable scalable learning, existing methods apply self-supervised data condensation to reduce computational cost, but typically rely on heuristic prototype learning and do not explicitly preserve learning-relevant feature distributions for downstream tasks. In response, we introduce a principled reformulation of WSI condensation as a distribution-matching problem under a fixed representational lens, and develop NICER, a tractable approximation framework based on a nonparametric prior with slide-adaptive capacity. Experiments on five histopathology datasets, together with clinical evaluation from a board-certified pathologist, show that NICER consistently outperforms prior methods, achieving an average accuracy improvement of 7.44% while offering improved efficiency-accuracy trade-offs, highlighting the benefits of principled, distribution-aware condensation for scalable histological representation learning. Source codes are available in https://github.com/nmduonggg/NICER.

  AI40PDF

  Summarize this
• arXiv cs.CVSep 30

  Harnessing Vision-Language Models for Perceptual Quality Assessment and Autonomous Content Adjustment in Augmented Reality

  Elias Rotondo, Lin Duan, Yanming Xiu, Sangjun Eom, Conrad Li +1

  Advancements in augmented reality (AR) continue to foster innovative solutions, facilitating novel methodologies within educational systems, healthcare delivery, and risk-mitigation protocols. However, optimizing for end-user immersion and comfort remains challenging, as AR head-mounted displays contend with constrained scene geometry, spatial jitter, and temporal instability. User studies are the standard AR evaluation method for visual quality, but their cost, diminishing scalability, and inflexibility pose bottlenecks during iterative application design. To address this problem, we present an automated framework for AR content evaluation and refinement, built on vision-language models (VLMs), to evaluate and predict the visual fidelity of AR scenes as perceived by users. First, we introduce RateAR, a benchmark of AR images and videos collected across diverse scenes and environmental conditions, with good-to-excellent reliability (ICC(2,5) >= .90) across perceptual factors, including object placement, scale, and shadow consistency. Subsequently, we evaluate eleven commercial VLMs on the crafted benchmark. Results support that VLM-based quality predictions strongly correlate…

  PDF

  Summarize this
• arXiv cs.LGSep 30

  Learning Transferable Skills using Goal-Conditioned Bisimulation

  Mohammad Amin Abbasfar, Farbod Azimmohseni, Mohammad Hossein Rohban

  Unsupervised skill discovery has emerged as a promising approach for leveraging reward-free datasets to pretrain general-purpose policies. However, current skill discovery methods either require access to expert data or exhibit limited generalization, failing to transfer effectively to previously unseen layouts. A key challenge is to learn representations that capture the temporal structure of the environment while remaining robust to variations across layouts. To address this issue, we present an objective for learning action-aware temporal representations that satisfy the functional equivariance property while preserving the local temporal structure of the environment. Building upon this embedding, we further propose unsupervised skill discovery using bisimulation, which learns transferable skills by conditioning the behavior of skills exclusively on the subset of state features that directly affect their execution. This enforces invariant behavior across different layouts, enabling skills to transfer effectively to other configurations. Finally, through comprehensive empirical evaluations, we show that skills learned in a given environment can be effectively applied to solve…

  PDF

  Summarize this
• arXiv cs.LGSep 30

  LabBook: Harnessing Experimental History for Efficient LLM-Driven Discovery

  Bo Yuan, Wenqian Ye, Zelin Zhao, Lama Moukheiber, Henry Kautz +2

  Evolutionary approaches to LLM-driven discovery often generate new programs from a small set of selected ancestors. This keeps contexts manageable but can omit useful evidence from other experiments, whereas including the full experimental history produces long, redundant contexts. We introduce a simple, single-agent discovery harness built around LabBook, an agent-maintained memory that serves two complementary roles: guiding retrieval of relevant evidence from a complete experimental log and informing the generation of new solutions. At each iteration, the same agent combines its memory with retrieved evidence and jointly produces the next program and an updated LabBook. This separates complete history retention from selective context construction, without requiring an explicit population or branching search structure. On 49 Frontier-CS problems, LabBook improves the observed quality-cost trade-off over the evaluated evolutionary baselines with two backbones, while remaining competitive across nine additional mathematical, systems, and heuristic-design tasks. Code will be released at https://github.com/BoYuanVisionary/LabBook.

  PDF

  Summarize this
• arXiv cs.CLSep 30

  Closing the Loop: Practical Training Recipes for Looped Language Models

  Andrei Marchenko, Viacheslav Bezrukov, Oleg Kashurin, Inessa Fedorova, Dmitry Bocharov +3

  Looped language models increase effective depth by repeatedly applying a shared block of layers, but existing large-scale recipes require multi-stage training over trillions of tokens, while the benefits of recurrence remain difficult to separate from differences in data and training. In this work, we establish practical training recipes for looped language models, with three main results. (1) We develop a compute-efficient from-scratch pipeline that reduces the training budget from 7.7T tokens in Ouro to 310B tokens while retaining strong reasoning performance. Pretraining followed by high-quality mid-training, together with learning-rate warmup and stronger exit-gate regularization, enables stable recurrent training without prior multi-stage schedules. (2) Under controlled comparisons, our 1.4B LoopLM outperforms a parameter-matched dense model trained on the same data and token budget on all 12 evaluated benchmarks, including +14 points on GSM8K, +10 on MATH, and +22 on DROP. At matched inference compute, it approaches a 3.9B dense model on mathematical reasoning and reading comprehension while using only 36\% as many parameters. (3) We introduce a minimal recipe for…

  PDF

  Summarize this
• arXiv cs.LGSep 30

  ORBIT-FMIB: Tracking Order-Resolved Epistatic Information Through ESM-2

  Maryam Rahimimovassagh, Ivan Garibay, Niloofar Yousefi

  Protein foundation models support mutation-effect and structural prediction, but predictive performance alone does not reveal which forms of biological interaction information remain accessible through model depth. We ask whether ESM-2 retains higher-order epistatic information as strongly as first- and second-order information across its representation hierarchy, introducing ORBIT-FMIB, a diagnostic framework combining Walsh-based interaction decomposition with subset-conditioned neural dependence estimation. The method is validated on synthetic landscapes with known interaction structure before being applied to the dense four-site GB1 fitness landscape using frozen ESM-2 representations. An initial production run suggested ESM-2 retains higher-order epistatic information less well than lower-order information ($Δ_{\mathrm{HO-LO}}=-0.107$). An independent replication of the complete measurement grid, under matched GPU hardware and identical critic seeds, substantially reduced this contrast ($Δ_{\mathrm{HO-LO}}=-0.017$), and its sign was unstable across otherwise-defensible evaluation-pairing choices applied to the same trained critics ($-0.011$ to $+0.015$). We therefore do not…

  PDF

  Summarize this
• arXiv cs.AISep 30

  A Simple Doxastic Deontic Logic for Norm-Guided Decision Making

  Thorsten Engesser, Agata Ciabattoni

  Making decisions despite conflicting norms and incomplete or unreliable information is a fundamental challenge for autonomous systems. We introduce a simple doxastic deontic logic for this setting: a classically reducible fragment of Chellas' Minimal Deontic Logic, extended with explicit conditional norms and combined with multi-agent KD45, so that norms can depend on agents' beliefs about both facts and norms. On this logic we define the Doxastic Norm Compliance Optimization Problem, where an agent chooses a decision minimizing weighted norm violations. We distinguish subjective optimization (relative to the agent's beliefs) from objective optimization (relative to the actual facts). We give conditions under which (i) the two coincide and (ii) optimal decision-making can be reduced to weighted partial MaxSAT in polynomial time.

  PDF

  Summarize this
• arXiv cs.CVSep 30

  VisionQ: VLM-as-a-Judge Taxonomy, Dataset and Benchmark for Qualitative Analysis in Computer Vision

  Vu Dinh Xuan, Duc-Hai Nguyen, Minh-Dung Dao, Vu Quynh Giao, Quang Hong Nguyen +4

  Qualitative comparison figures are central evidence in computer vision papers, and vision-language models (VLMs) are increasingly used to judge them. Yet existing benchmarks score only scalar quality or overall preference, so a judge can be rewarded for picking the preferred image for the wrong visual reason. We introduce VisionQ, the first benchmark built from peer-reviewed CV comparison figures that grounds every judgment in a named visual criterion: each question states the criterion, and a judge is credited only when it selects the output the authors identify as best on that criterion. We call this task criterion-conditioned visual discrimination. VisionQ comprises (1) a corpus of 1,409 CVPR and ICCV papers with 1,800+ validated comparison figures and 3,911 hand-annotated data points linking method crops to author-stated visual claims; (2) a six-axis, 51-leaf taxonomy of the visual criteria behind qualitative judgment; (3) a criterion-conditioned evaluation protocol that hides method names, captions, and paper identity and reports accuracy per criterion; and (4) VisionQ-Judge, a DPO-tuned Gemma-4-E4B judge trained on symmetric evidence pairs, which reduces last-option…

  PDF

  Summarize this
• arXiv cs.LGSep 30

  Analysis of Quantized and Efficiently Adapted Protein Language Models

  Ilan Yaniv Zeisler, Sebastian Clancy, Pouriya Bayat, Saaim Raad, Ivan Kraskov +6

  Background: Protein language models (PLMs) are increasingly used for sequence generation and property prediction, but their size makes fine-tuning and deployment expensive. The effects of quantization and parameter efficient fine-tuning on performance, representations and generation remain insufficiently characterized. Results: We evaluated 4-bit quantization and low-rank adapter fine-tuning (QLoRA) across ESM-2, ESMC, ProtBERT, ProtT5, Ankh, Ankh3 and Profluent-E1. Across protein prediction tasks, many model-task pairs retained more than 90% of full fine-tuning performance. Peak GPU memory savings approached 90% for the largest models, although performance and efficiency varied by model, dataset and training configuration. QLoRA often preserved early-layer representations while inducing task-specific adaptations in middle and late layers, resembling full fine-tuning with smaller representational changes. Training speed and power effects were more varied. For unconditional generation with ProLLaMA, ProtGPT2, ProGen2, ProteinGLM and ESM3, 4-bit quantization largely preserved predicted structural and sequence-level properties, but token-level analysis revealed model-dependent…

  PDF

  Summarize this
• arXiv cs.CLSep 30

  PhysicsMate: A Curriculum-Grounded Bengali Benchmark for Secondary Physics QA with Small-Model Adaptation

  Rashid Azraf Jahin, Saadman Sajid, Khan Raiyan Ibne Reza, Sumaiya Tabassum Nimi

  Bengali secondary education lacks curriculum-grounded benchmarks for STEM question-solving, and general-purpose language models struggle with the precise terminology, unit conventions, and derivations that physics problems demand. We introduce PhysicsMate, a benchmark of 1834 question-answer pairs built from the National Curriculum and Textbook Board (NCTB) Grade 9-10 physics syllabus and grounded in a multi-relational knowledge graph of 1760 nodes and 2600 edges across ten ontological types. We Low-Rank Adapt at 0.6B, 1.7B, and 4B parameters, with a unified recipe and demonstrate a significant increase in closed-book accuracy in all scales (+5.5, +15.0, and +23.3 percentage points). A node-type analysis shows that the most benefited by adaptation is the structured curricular knowledge, which consists of physical quantities and named laws, while the least benefited is the loosely specified entity-level knowledge. The 4B model has been adapted and quantized to a small offline binary that can be used for local inference in resource constrained environments and offers a viable path to curriculum aligned physics support in environments with limited connectivity and hardware.

  PDF

  Summarize this
• arXiv cs.AISep 30

  Backdoor Containment via Expert Quarantine and Shutdown in LLMs

  Jianwei Li, Min-Seon Kim, Jung-Eun Kim

  Backdoored large language models (LLMs) can behave normally on benign inputs while producing attacker-specified outputs under hidden triggers. Existing defenses span four stages--prior-training, in-training, post-training, and inference-time--and share one of two underlying strategies: either suppress backdoor learning (by filtering poisoned data or interrupting its acquisition during optimization) or learn, then purify (by repairing model weights or gating inputs after a fully backdoored model has formed). We propose a third strategy, learn, but channel: allow backdoor formation during training but route it into a designated, quarantined component that can be disabled at deployment. To this end, we propose Quarantined Expert Shutdown QES, a computationally efficient containment strategy built in a regularization-steered MoE-like setting. Specifically, given a poisoned dataset, QES augments a Transformer-based language model with routed expert-specific LoRA branches and lightweight routers, and uses auxiliary routing objectives to attract trigger-conditioned behavior into a designated expert while preserving benign capability elsewhere. At deployment, mitigation reduces to a…

  PDF

  Summarize this
• arXiv cs.LGSep 30

  Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models

  Yue Yu, Bowen Zuo, David Crandall, Yinglun Zhu, Dongruo Zhou

  Diffusion large language models (dLLMs) generate text by denoising a sequence or successive blocks, allowing several tokens to be revealed in parallel. Reinforcement learning with verifiable rewards (RLVR) reuses terminal feedback across these decisions, even as their conditioning context changes. We propose stepwise risk-sensitive GRPO (StepRS-GRPO), which varies the risk coefficient of the group-advantage transformation across denoising states while retaining the underlying trainer. For binary rewards, we show that this transformation is exactly a prompt- and state-dependent rescaling of centered outcome advantages. A capability-based calibration suggests a coefficient scale, while endpoint and interpolation ablations guide schedule selection. Across multiple dLLM backbones and mathematical reasoning benchmarks, StepRS-GRPO improves both pass@1 accuracy and pass@k coverage over centered GRPO, while increasing answer diversity. In our ablation studies, mass-matched controls support the contributions of state allocation and schedule direction, and the gains persist after matching the root mean square (RMS) of the advantages to that of centered GRPO. Reasoning-trace diagnostics…

  PDF

  Summarize this
• arXiv cs.CLSep 30

  Lingtai: What Concept Geometry Reveals--and Does Not Reveal--About LLM Inference

  Jiangang Chen

  Observing what a large language model computes during autoregressive inference--online and without training probes--remains difficult. We introduce Lingtai, a training-free concept telemetry layer: at each generation step, residual states are projected onto a domain-specific bank of named concept anchors, constructed without labeled concept examples, outcome labels, gradient fitting, or activation-space optimization, producing a structured per-step concept-coordinate signal. Across code generation and grade-school mathematical reasoning, this signal exhibits a robust association with predictive uncertainty: the association survives problem-identity and token-position controls and is not attributable to a single token type, is not explained by a simple correct/incorrect mixture on GSM8K, and is not reproduced by matched random anchors; it is markedly weaker or direction-inconsistent in K-means and PCA projections. Two structures emerge: a recurring uncertainty-linked activity signal whose functional geometry is task-conditioned (distinct activity-entropy shapes on HumanEval, MBPP, and GSM8K), and an execution-specific trajectory identity with strong local inertia but weak…

  PDF

  Summarize this
• arXiv cs.AISep 30

  When More Data Is Not Enough: The Context-Sufficiency Frontier in Generative AI Personalization

  Merieme Askour, Ayoub Merimi

  Personalization has long relied on customer data to infer what an individual is likely to value. We call this customer evidence: the customer's historical behavior and preferences. Generative AI extends personalization by allowing providers to supply changing situational information at the moment a response is produced, without encoding every condition in advance. We define this provider-side context as information about what is possible, permitted, or advisable now. This flexibility creates a new problem: once context becomes easy to supply, more is not necessarily better. We develop a theory of context sufficiency in which the relevance of context to the customer's current intent matters more than its volume. The theory identifies four states, insufficiency, sufficiency, saturation, and interference, and introduces the Context-Sufficiency Frontier to locate the minimal relevant set. In a full-factorial experiment with a generative recommender at a large home-furnishing retailer, relevant context improved appropriateness, while irrelevant context reduced it and destabilized retrieval. The framework shifts personalization from supplying more context toward identifying what the…

  PDF

  Summarize this
• arXiv cs.AISep 30

  Agent Evaluation Reliability: More Tasks Won't (Always) Fix An Agent Leaderboard

  Michael Hardy, Ruhana Azam, Anka Reuel, Mykel Kochenderfer, Sanmi Koyejo

  Agent evaluations are increasingly used to compare LLMs and inform deployment decisions, yet ranks can reflect not only the model but also the effects of the evaluation conditions such as the scaffolds or tasks. This makes reliability claim-dependent: an evaluation that reliably ranks deployed systems may not reliably rank underlying models. We ask which conclusions current agent evaluations reliably support and what additional evaluation would improve them. We develop a Bayesian variance-decomposition framework for sparse, imbalanced agent leaderboards and apply it to 22 benchmarks from the Holistic Agent Leaderboard and Harbor Index. The framework separates signal, performance differences relevant to the intended claim, from noise, irrelevant variation that can still change rankings. We find: (1) Reliability depends on the measurement goal. Fixed model-scaffold systems are ranked reliably (0.935-0.994), while underlying-model reliability is substantially lower (0.148-0.841). (2) Scaffold choice can change conclusions. Inter-scaffold reliability measures whether scaffolds preserve model rankings, showing that scaffold effects vary substantially across evaluations. (3) More tasks…

  PDF

  Summarize this
• arXiv cs.CLAgentsSep 30

  Self-Evolving Coding Rules for AI Coding Agents

  Zhengyuan Jiang, Reachal Wang, Yuepeng Hu, Yupu Wang, Yuqi Jia +1

  The performance of AI coding agents is highly dependent on their underlying coding rules. However, existing coding rules are typically hand-crafted and fixed, making the process labor-intensive and often suboptimal. In this work, we propose RuleEvolve, a self-evolving framework for coding rules. RuleEvolve maintains a pool of candidate coding rules and iteratively improves them. In each iteration, it employs an LLM-powered mutator module to generate variants from existing candidates, and then uses a judge module to evaluate these variants and update the pool with the best-performing ones. Extensive evaluations across two coding-agent frameworks, four backbone LLMs, and three benchmarks demonstrate that RuleEvolve outperforms both manual engineering and existing prompt optimization baselines in terms of functional correctness of the generated code, code length, and/or generation cost (e.g., tokens used).

  AICode models90PDF

  Summarize this

• Speech emotion24+84.6%
• Federated learning43+13.2%
• Forecasting time125+7.8%
• Algorithmic trading260.0%
• Databases60.0%
• Linear bandits102−1.9%
• Robotics181−6.2%
• Anomaly detectors25−7.4%