cs.AI · 2026-08-31 · No. 101
Artificial Intelligence, 2026-08-31.
72 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
72 entries-
01
Logos: An Agent Harness on a Cross-Process Bus
Hanzhang Jia, Liheng Zeng, Hao Cheng, Yi Gao, Bo Ma
cs.AI · cs.MA
Modern agent systems assemble capabilities at runtime, and this dynamic composition has recently received a complete formal treat ment in the spatiotemporal-composability calculus, in which a capability is a component carrying a tracked inverse, and agents are assembled as plugins. This plugin form is carried by a single process sharing one context, a carrier that places all components in one physical failure domain, a fault suspends every...
-
02
InstructMesh: Selective Refinement of Generative 3D Models for Fabrication
Faraz Faruqi, Ahmed Katary, Demircan Tas, Theresa Hradilak, Ning Zhang, Jiaji Li, Fabian Manhardt, Martin Nisser,...
cs.AI
Recent advances in generative AI allow users to create 3D models from text or images. However, these models prioritize visual plausibility over geometric accuracy, often generating results with flaws that compromise their intended use post-fabrication. We present InstructMesh, an interactive post-generation refinement tool that enables selective repair of generative 3D models through region selection and targeted operations, such as opening...
-
03
When Robots Mishear Us: Mapping the Safety Risks of Voice-Controlled Embodied AI
Sihan Jia, Oliver Lemon
cs.AI · cs.CL · cs.RO
We investigate whether automatic speech recognition (ASR) errors in user input can lead to unsafe outputs from Embodied AI (EAI) models. We find that ASR errors can lead to harmful instructions being accepted and executed by EAI models, thereby reducing safety. We simulate ASR errors and combine them with existing safety benchmarks (SafeAgentBench and POEX) to evaluate how different errors affect embodied AI safety. We find that some of them...
-
04
Training Communication-Efficient Mixture-of-Experts Language Models with Layer Re-Configuration
Simeng Sun, Roger Waleffe
cs.AI
When training Mixture-of-Experts (MoE) language models with expert parallelism, all-to-all token dispatch and combine collectives can consume a substantial fraction of end-to-end training time. In this work, we study communication-efficient MoE models (CE-MoE), in which we adopt a heterogeneous layer pattern that decouples token-mixing and channel-mixing depth. Compared to conventional models which interleave MoE layers after each...
-
05
AcrossVAM1.0: Particle World Modeling for Text-Assisted Robot Video Prediction
Yafei Zhang, Nan Wu
cs.AI · cs.RO
Predicting robot videos requires both precise motion reasoning and preservation of high-frequency appearance, yet monolithic pixel models entangle these objectives and often conceal their progress behind a strong last-frame baseline. We present AcrossVAM1.0, a lightweight, text-assisted video action model that factorizes future prediction into object-centric motion and dense appearance. A frozen SAM3-DLP codec decomposes four context frames...
-
06
COVER: Identifiable Evaluation of Coalition Routing
Raghul Sugumar, Amrit Gopinath
cs.AI
When a multi-agent system changes its team, it also changes the messages and final answer it produces, so an end-to-end accuracy gap does not by itself identify a routing effect. We introduce method, an evaluation contract that fixes a public information boundary, downstream stack G, and finite legal team family before outcomes are generated. Complete coverage identifies exact finite-benchmark oracle regret conditional on that stack. For any...
-
07
Learning to Use Tools: Reinforcement Learning for Tool-Integrated Mathematical Reasoning
Minghui Xu, Zi Wang
cs.AI
Current large language models (LLMs) increasingly benefit from external tool integration, especially for tasks requiring reliable computation and verification. Motivated by this, we study calculator tool calling for improving mathematical reasoning on the Countdown task. We first analyze reasoning failures and find that calculation errors account for a substantial portion of incorrect responses. We then construct supervised fine-tuning...
-
08
Prove2Me: An Open Collaborative Platform for Scaling Math Formalization
Shuze Chen, Kunal Marwaha, Xiaoyang Lu, Henry Yuen, Tianyi Peng
cs.AI · cs.LO · cs.MA
Proof assistants such as Lean 4 promise the paradigm of formally verified mathematics, but large-scale formalization projects have faced major barriers to entry, including the need for expertise in formal verification (as well as the underlying mathematics) and the significant time required for writing formal proofs. AI coding agents have dramatically reduced these barriers; human users can now use natural language to prompt agents to write...
-
09
Program Learning with Verifiable Rewards: Symbolic Backpropagation for Post-Training LLMs
Vishvesh Bhat
cs.AI
Post training a language model to reason means updating its weights. Supervised finetuning and reinforcement learning both place the acquired capability inside the model where it cannot be inspected cannot be checked step by step and cannot be moved to another model. We argue that for tasks whose intermediate steps admit verification, reasoning is better placed outside the base models weights as an explicit program composed from deterministic...
-
10
VERA-8B: Evidence-Grounded Audit Risk Reasoning from SEC Filings
Menghan Liu, Elynn Chen
cs.AI
Across audit applications, judgments must be supported by reasonable evidence. However, standard financial language models prioritize fluency over evidence. They are built for general financial reasoning and may produce plausible but ambiguous answers, creating a grounding gap that makes them unsuitable for audit work. We address this gap with VERA-8B, a new end-to-end audit reasoning system that identifies audit risks before enforcement...
-
11
RetailAgent: Structured Adverse Timing in Self-Conditioned Multimodal LLM Trading Agents
Yupeng Zhang, Liuyuan Jiang, Hongyi Huang, Bingheng Li, Lisha Chen
cs.AI · q-fin.TR
In financial markets, a sequential policy that reacts systematically to price movements may become predictable to other market participants. This paper studies whether large language model (LLM) agents exhibit such directional structure through RetailAgent, an experimental framework in which an LLM observes anonymized intraday equity price histories and permitted state, then repeatedly chooses long (hold the stock) or flat (stay out) before...
-
12
Timing-Aware Repurchase Prediction for Web-Scale E-Commerce: Survival Models for Multi-Surface Grocery Recommendation
Akshay Kekuda, Shreeranjani Srirangamsridharan, Ishan Bhatt, Yanan Cao, Sinduja Subramaniam, Evren Korpeoglu,...
cs.AI · cs.LG
Repurchase recommenders in e-commerce are commonly framed as a binary question asking "will this customer buy this item within W days", a formulation that requires a separately trained model for every horizon of interest. We replace this stack with survival models that predict time-to-repurchase directly, and evaluate them on millions of customers from a major grocery e-commerce platform across more than thirty ablation configurations. Our...
-
13
MAP: A Benchmark on Multimodal Accessibility Planning for Real World Places
Jason Armitage, Ioannis Tsochantaridis, Linda Mazzone, Chuqiao Yan, Srini Narayanan, Sarah Ebling
cs.AI
We introduce MAP, the first benchmark to evaluate multimodal AI systems as assistants for users with accessibility requirements when planning visits to places in the real world. In our evaluation, systems are presented with requests to verify or recommend a point of interest meeting an accessibility requirement. MAP contains two novel assessments: Claim verification for accessibility planning assesses if information on places and stated...
-
14
EvoUndo: Recoverability-Constrained Self-Evolution for LLM Agent Harnesses
Tanmay Sah, Dolly Sah, Harshul Jain, Tanya Sah
cs.AI
LLM agents increasingly modify their own prompts, tools, middleware, resources, and execution harnesses at runtime. Such self-evolution can improve capability, but a successful mutation may leave persistent effects that cannot be safely reversed in states different from the one in which it was created. We introduce EvoUndo, a framework for representing, synthesizing, diagnosing, and independently verifying recoverability of model-generated...
-
15
GRACE:Gradient-guided Coreset Selection for LLM Unlearning
Praveen Bushipaka, Andrea D'Angelo, Lucia Passaro, Tommaso Cucinotta
cs.AI · cs.LG
Machine Unlearning methods for Large Language Models typically assume pre-specified forget and retain sets. In realistic settings, however, requests may provide only a few examples of undesired behavior, requiring forget and retain sets to be inferred from heterogeneous corpora. We study this data-selection problem and propose GRACE , a gradient-guided coreset selection method that constructs both forget and retain sets for LLM unlearning....
-
16
Propagating construction-time knowledge quality into medical question answering: A framework grounded in clinical guidelines
Jie Hu, Junjie Wang, Shan Lu, Yifang Hu, Gong Cheng, Yun Liu
cs.AI
Large language models have facilitated knowledge graph (KG) construction from clinical guidelines, but extracted triples vary in structural validity and evidential support. Meanwhile, graph-augmented question answering (QA) systems typically optimize query relevance during retrieval, with limited reuse of quality information produced during KG construction. This creates a disconnect between construction-time quality control and inference-time...
-
17
AGENT-O: A Semantic Agent Card Framework for Interoperable and Governed Healthcare AI Agents
Pengze Li, Cui Tao
cs.AI
AGENT-O is a modular ontology framework that defines a semantic Agent Card for representing health-oriented AI agent systems and supports assessment of reporting completeness in scientific publications. AGENT-O was developed as an OWL 2/RDF ontology covering runtime, models, workflow, tools, clinical use, evaluation, provenance, governance, and reporting assessment. Evaluation included ontology inventory, OWL-RL reasoning, three SHACL suites,...
-
18
Real-Valued Hyperdimensional Sequence Representations with Hadamard Product Binding and Shift Equivariance
Kenny Schlegel, Dmitri A. Rachkovskij, Denis Kleyko, Amy Loutfi, Stefan Streif, Evgeny Osipov
cs.AI
Encoding temporal order is a fundamental requirement for sequence representations in Hyperdimensional Computing. Fractional Power Encoding provides similarity-preserving position vectors whose inner products approximate shift-invariant kernels, and it supports shift-equivariant transformations of encoded sequence representations. However, standard formulations of Fractional Power Encoding are primarily designed for binding operations such as...
-
19
MAIL: Memory-driven, Adaptive, Incremental, and Literature-grounded Framework for Hypothesis Generation in Chemistry
Mahdi Babaei, Xueshen Li, Yutao Kuang, Jolene P. Reid, Yu Gan
cs.AI
The ever-expanding volume of the chemical literature offers unprecedented opportunities to generate novel and impactful hypotheses. However, the bottleneck lies in efficiently navigating this vast knowledge base to formulate high-quality, experimentally meaningful insights. While Large Language Models (LLMs) show promise for this task, existing methods often rely on static inspiration corpora, predefined heuristics, or laborious...
-
20
Memristive-Friendly Hadamard Reservoir Computing: Structured, Multiplier-Free Recurrences at Scale
Andrea Ceni, Gianluca Milano, Carlo Ricciardi, Claudio Gallicchio
cs.AI
Reservoir Computing (RC) designs Recurrent Neural Networks around a fixed, i.e., untrained, recurrent layer, and is a natural candidate for neuromorphic hardware. Memristive-friendly reservoirs derive the neuron dynamics from memristive-device kinetics, but still rely on dense recurrent matrices, which are expensive to realize physically. In this paper, we replace the dense matrix with a structured orthogonal operator, built from sign...
-
21
LoopArena: Benchmarking Models as Runtime Controllers for Loop Engineering
Yi Wang, Haopeng Zhang, Chengxiang Huang, Rui Dai, Kaikui Liu, Piotr Koniusz, Xiangxiang Chu
cs.AI
Loop Engineering is emerging as a practice for organizing development work around coding agents. Instead of writing each prompt by hand, practitioners design loops that monitor progress, assign work, run checks, and decide what the agent should do next. Even with a capable coding agent, a loop may trust a stale progress note, skip needed verification, spend its budget in the wrong direction, or stop before the task is safe to submit. Yet the...
-
22
RECAST: Recent & Context-Aware Sampling for Test-Time Adaptation in Streaming Biosignals
Yong-Yeon Jo, Junho Song, Joon-myoung Kwon
cs.AI
Streaming biosignals vary across subjects and drift over time, so population-trained models lose accuracy during long-term monitoring. Test-time adaptation (TTA) enables online personalization by updating the model on incoming samples. But in a stream, a basic question is left open: \emph{which samples should drive each update?} Using all buffered samples blurs the update with irrelevant segments. Using only the latest segment makes the...
-
23
Finding Where the Buck Stops: An Automated Failure Attribution-Based Reflection Framework for Multi-Agent Collaboration
Xiaoqing Wang, Keman Huang, Bin Liang, Hongyu Li, Xiaoyong Du, Wuqiong Pan
cs.AI
Multi-agent systems (MAS) powered by large language models have shown promise for complex tasks but suffer from high failure rates. Current self-reflection methods for MAS require all agents to reflect upon failure, overlooking a critical reality: failures typically stem from a specific agent leading the task astray, namely the decisive error agent, while others merely fulfill their regular duties. Forcing regular-behaving agents to reflect...
-
24
Physics-Guided Flow Matching for CT Image Reconstruction
Davide Evangelista
cs.AI · cs.CV
Deep generative models have recently emerged as powerful priors for solving ill-posed inverse problems in CT, with diffusion-based approaches achieving state-of-the-art reconstruction performance. However, diffusion models typically rely on stochastic sampling procedures, long inference trajectories, and carefully tuned noise schedules, which can limit computational efficiency and numerical stability, especially at high spatial resolutions....
-
25
Regime-Aware Portfolio Management via Retrieval-Augmented LLM-Guided Expert Switching
Ahmad Asadi, Reza Safabakhsh
cs.AI
Financial markets are inherently non-stationary, making the effectiveness of individual portfolio-management strategies highly dependent on changing market conditions. This work proposes a retrieval-augmented expert-switching framework that dynamically selects portfolio management experts based on their historical performance under similar market situations. A dual-stream variational autoencoder represents asset-level and market-wide...
-
26
Beyond Task-Only Matching: Personalized Skill Routing with Counterfactual Evaluation
Tianle Wang, Yanghe Zou, Xiang Liu, Ziyao Huang, Chenchen Fu, Weiwei Wu
cs.AI
The rapid expansion of reusable skill repositories makes skill routing a critical capability for large language model (LLM) agents. Existing methods treat routing as task-only semantic matching. However, when users with incompatible constraints issue an identical request, this assumption conflates task relevance with skill suitability: a task-only router can select a semantically plausible skill that is unsuitable for the requesting user. To...
-
27
REINS: Refusal-Enhanced Inhibitory Steering with Sparse Autoencoder Features
Kai-Xuan Ding, Hao-Xiang Xu, Ji-Hua Peng, Zi-Qi Chen, Jiaqi Wang, Zhen-Hua Ling
cs.AI
Steering with Sparse Autoencoders (SAEs) offers a lightweight inference-time path for adapting the behavior of large language models without retraining. By exposing sparse and interpretable features, SAE steering provides a promising interface for safety control that guides harmful continuations toward refusal. However, we observe that complex wrappers can still undermine existing SAE steering methods on harmful prompts. To evaluate this...
-
28
Stay Within Your Bounds: Distance-Guided Decoding for Guaranteed Context-Free Grammar Compliance
Vincenzo Collura, Karim Tit, Eleonora Giunchiglia, Mike Papadakis, Maxime Cordy
cs.AI · cs.CL · cs.FL · cs.LG
Grammar-constrained decoding helps large language models produce syntactically valid structured outputs, such as code, JSON, and SQL. For context-free grammars, many practical decoders enforce local prefix feasibility: each token must keep the current prefix extendable to some valid completion. Yet, under tokenizer-grammar mismatch and finite token budgets, feasible prefixes may still fail to reach acceptance. We propose a lookahead-guided...
-
29
Generative AI Alignment with Hinduism's Theological Plurality and Sacred Representation
Dipto Das, Arpita Kundu, Nusrat Jahan Mim, Shion Guha, Syed Ishtiaque Ahmed
cs.AI · cs.CY · cs.HC
Generative AI systems are increasingly used to answer personal questions and mediate everyday practices, including religion. However, existing discussions around AI alignment and ethics have largely centered secular, Western, and Abrahamic assumptions about religion, offering limited attention to other faith-based traditions. In this paper, we examine how Hindu users engage with generative AI systems in relation to their religious knowledge,...
-
30
Expert Knowledge & Machine Understanding: Bridging Reactome's Ontology with LLM Semantic Embeddings
Susanna Bravi, Riccardo De Luca, Rosa Sicilia, Christine Nardini, Mario Santoro
cs.AI
Biological knowledgebases like Reactome provide high-quality pathways that include biological elements' relationships and textual descriptions (metadata). The quality of such pathways is granted by manual curation, that presents, however, significant scalability challenges. Lately, numerous NLP tools have been proposed to cope with this issue, leveraging textual information to automatically expand biological knowledgebases. However, little...
-
31
CrabOS: An Operating System for Human-AI Co-inhabitation
Qi Yang, Yun Ma
cs.AI · cs.HC · cs.OS
AI agents are evolving into long-running computational entities that can invoke tools, maintain memory, and complete complex tasks across applications. In real-world settings, completing a task often requires humans and AI to take turns leading its execution. Such alternation depends on the seamless handoff of the work state of the task between humans and AI. Existing agent systems, however, provide humans and AI with separate work...
-
32
Under-Mattress Temporal Sensing for Next-Day Agitation Risk Scoring in Dementia Wards
Zhen Liu, Marta Bono, Robbe Decloedt, Ajda Flisar, Maarten Van Den Bossche, Maarten De Vos
cs.AI · cs.LG
Agitation fluctuates over short time horizons in people living with dementia, yet continuous physiological information for anticipating next-day risk is limited. We assessed whether contactless under-mattress signals from the preceding night inform next-day agitation risk and whether preserving minute-level temporal structure improves performance over conventional nightly summaries. We analyzed 423 patient-nights from 65 subjects in a...
-
33
The Shape of Power: A Multilingual Framework for Social Power Reasoning in Dialogues
Farah Atif, Sougata Saha, Monojit Choudhury
cs.AI
Social power plays a fundamental role in shaping human interaction, yet computational studies of power remain limited to narrow linguistic and cultural settings. Existing datasets further lack the demographic and relational depth needed for robust cross-cultural analysis. To address this gap, we introduce a theoretically grounded framework for studying social power in naturalistic multilingual dialogue through movie screenplays. The framework...
-
34
Speculative Probing: LLM Monitoring at Speculative-Decoding Cost
Collin Zhang, Tingwei Zhang, Vitaly Shmatikov
cs.AI · cs.CL
Real-time classification during language model inference is valuable for safety filtering, behavioral analysis, and model monitoring, but current approaches force a trade-off between accuracy and efficiency. Hidden-state probes are fast but limited: they are either not context-aware: operating on a single vector and cannot model interactions across positions; or they are very costly: having dedicated classifier models (Llama Guard, Qwen...
-
35
SEPO: Evidence-Grounded Prompt Optimization via Structural Editing
Xiaoyu Ma, Haoyue Liu, Yiwen Li, Jionghao Zhu, Zhichao Wang, Ye Chen, Xiaoying Tang
cs.AI
Existing API-only prompt optimisers are often described as interpretable, but in practice, this usually means only post-hoc inspectability: each iteration still rewrites the prompt as one opaque string, leaving a trace of full-prompt diffs rather than localisable, machine-readable edits. This paper introduces SEPO (Structural, Evidence-grounded Prompt Optimization), a multi-trajectory prompt optimiser centred on edit-effect lineage feedback....
-
36
Learning to Allocate Incentives for Incentivized Advertising via Offline Model-Based Reinforcement Learning
Zilin Zhao, Han Yang, Tianpei Yang, Fangsheng Huang, Yanfei Cui, Kan Peng, Yi Li, Yiming Zong, Hao Zhang, Yinsong Xue
cs.AI
Complete your ad view and grab a 5-cent bonus! In incentivized advertising, a platform promises users a bonus before observing downstream ad revenue, encouraging them to click and complete ads. It must balance the incentive promised in advance against the revenue realized afterward: insufficient incentives forfeit monetization opportunities, whereas excessive incentives reduce net profit. Because current incentives may also shape user...
-
37
WeAgent-MMSearch: Native Text-Vision Interaction for Multimodal Search Agents
Zongkai Liu, Hui Zhang, Liqiang Niu, Zhen Cao, Han Li, Juntao Liu, Wenchao Chen, Chengduo Zhao, Chao Yu, Fandong Meng
cs.AI
Multimodal search agents extend parametric knowledge with newly emerging and long-tail evidence from the open web. Yet many existing agentic search environments often expose retrieved evidence only as text and omit tool-returned images from subsequent context, reducing visually grounded trajectories to text-only reasoning. Long-horizon interaction also compounds tool-call, response-length, timeout, and budget failures, which can discard...
-
38
String: An Agentic OS Where Every App Is a Markdown File
Jookyung Song, Nojun Kwak, Simyung Chang
cs.AI
LLM agents have become a new class of software user, but every surface they work through was designed for someone else. Pages are built for human eyes, which can skim and ignore; tool schemas for programs, which pay nothing to carry definitions they never call. An agent has neither luxury: it re-reads, and pays again for, everything it is shown on every turn. We present String, an open-source runtime that gives this user an interface of its...
-
39
Coverage, Not Credit: Failure-Credit Routing of Zeroth-Order Perturbation Budgets Does Not Improve On-Pool Sample Efficiency for LLM Agents
Yuxu Ge
cs.AI
Trajectory-level credit assignment can localize which module of a tool-using LLM agent causes failures using only verifiable signals. We ask whether such failure credit should route a fixed zeroth-order/evolution-strategies (ZO/ES) perturbation budget. Across a synthetic environment and frozen Qwen2.5-1.5B/3B and SmolLM2-1.7B agents, three task families, six allocation schemes, a credit-noise sweep, paired seeds, and exact sign-flip tests, we...
-
40
PhenoIntel: A Lifecycle-Aligned Multi-Agent Web Application for Verified, Accessible Plant Phenotype Analysis
Narendren S, Soumyashree Kar
cs.AI
Existing conversational plant-phenotyping platforms are difficult for plant scientists to use and lack the reliability scientific research demands: failed analyses are reported as valid measurements rather than flagged as missing, statistical tests run without checking assumptions, predictions carry no uncertainty estimate, and specialised hardware limits accessibility. We present PhenoIntel, a lifecycle-aligned multi-agent web platform that...
-
41
Automated Analysis Framework for Multilingual Climate-Health Literature Based on Multi-Agent Large Language Model
Yuze Sun, Shihui Zhang, Jiancheng Pan, Yunjia Ye, Wentao Luo, Jiahao Li, Quan Zhang, Wenjia Cai, Xiaomeng Huang
cs.AI
The rapid proliferation of interdisciplinary and multilingual scientific literature has left traditional manual analysis and single-algorithm methods plagued by low efficiency, poor scalability, and insufficient domain adaptability. Targeting the literature analysis needs of the typical interdisciplinary climate-health field, this study proposes a multi-agent large language model automated analysis framework for multilingual scientific...
-
42
Should I Use This Synthetic Dataset for Training? How to Test with Minimal Real Data
Zhenyu Tao, Wei Xu, Xiaohu You, Petar Popovski, Osvaldo Simeone
cs.AI
Digital twins (DTs) and learned world models are increasingly used to generate synthetic data that augment the scarce real datasets available for training artificial intelligence (AI) models in engineering systems. Owing to the inevitable simulation-to-reality (sim-to-real) gap, however, augmentation may fail to improve the performance of the trained model on the real data distribution. This paper addresses the resulting decision problem:...
-
43
GOD: Govern, Observe, and Direct - A Real-Time Control Room for Agent Societies
Yige Luo, Ran Guan
cs.AI · cs.MA
Generative-agent systems are easier to start than to inspect. A run can contain many agents, locations, messages, commands, and model calls, yet the operator often gets either a finished replay or raw logs. That makes it hard to ask why an agent moved, test a small intervention, or package a run for another researcher. GOD is a local-first control room for agent societies. From the same browser workflow, an operator can issue targeted...
-
44
When Evidence Shapes Collaboration: Knowledge-Conditioned Topology Generation for Multi-Agent Systems
Yangxiao Jiang, Jiarun Fan, Mingcong Xu, Yanxi Guo, Jiwen Feng, Shanqing Xu, Mengchen Qian, Wei Chen, Xiaojin Zhang
cs.AI
Multi-Agent Systems (MAS) have recently moved from static workflows toward dynamically generated collaboration topologies. However, existing topology generation methods rely primarily on the parametric knowledge of large language models, with external search or retrieval used only as a reactive tool rather than an explicit determinant of collaboration structure. This leads to structure-knowledge misalignment, where systems exhibit redundant...
-
45
Learning from Hard Prompts: Difficulty-aware Advantage Amplification in Dynamic Sampling
Siyuan Gan, Yuhan Li, Xiran Wang, Linjian Meng, Boyan Wang, Zhen Zhao, Jing Huo, Lei Bai, Yang Gao
cs.AI
Decoupled Clip and Dynamic Sampling Policy Optimization (DAPO) is a prominent variant of Group Relative Policy Optimization (GRPO). DAPO introduces several improvements over GRPO. Among these, Dynamic Sampling contributes the most to DAPO's accuracy gains relative to GRPO. To improve accuracy, Dynamic Sampling enhances training stability by eliminating zero policy gradients from zero advantages. Specifically, it avoids such zero gradients by...
-
46
openJiuwen: Beyond Static Harnesses for Long-Horizon Coding Agents
openJiuwen Team, Tao Yu, Xinyu Zhang, Qianqian Chen, Xiaoneng Xiang, Chia Kwangyang, Xingchen Huang, Ran Chen,...
cs.AI
Long-horizon coding agents operate over evolving repository states while increasingly relying on heterogeneous capabilities, delegated agents, and multi-agent coordination. These trends pose two complementary challenges for the agent harness. First, developers need to compose capabilities, reconfigure execution logic, and scale increasingly complex agent systems without repeatedly rebuilding orchestration. Second, complex coding tasks...
-
47
AERA: Adaptive Evidence Residual Allocation for Efficient Test-Time Reasoning
Ziming Wang, Ivor Tsang, Hangwei Qian
cs.AI
Test-time scaling improves language-model reasoning by generating additional candidate solutions, but allocating the same inference budget to every problem is computationally wasteful. Existing adaptive stopping methods commonly rely on confidence, agreement, or answer stability, implicitly assuming that stronger current evidence indicates that further computation is unnecessary. We show that this assumption can fail: checkpoint-level...
-
48
SABER: Stability-Aware Early Exit for LLM Reasoning via Adversarial Branch Probing
Wanli Cheng, Haiya Xiang, Juntao Li, Hongling Wang, Wenliang Chen
cs.AI
Large Reasoning Models (LRMs) achieve strong reasoning capabilities, yet long-chain reasoning becomes inefficient once the intermediate answer stabilizes across reasoning steps: additional reasoning yields little marginal benefit while incurring substantial inference cost. Existing early-exit methods based on confidence or entropy poorly capture reasoning stability, while consistency-based approaches rely on multi-step trajectory agreement,...
-
49
When Teacher Guidance Misleads: Reward-Aligned On-Policy Distillation
Siyuan Gan, Yuhan Li, Xiran Wang, Linjian Meng, Boyan Wang, Zhen Zhao, Jing Huo, Yang Gao
cs.AI
On-policy distillation (OPD) has recently emerged as a popular post-training paradigm for large language models (LLMs), providing an efficient way to transfer the knowledge and capabilities of teacher models into student models. However, teacher guidance on student-generated prefixes is not always reliable. Training should optimize the model to generate responses that are more likely to be correct, or equivalently, to get higher outcome...
-
50
The Illusion of $\textit{What If}$: Evaluating the Breakdown of Counterfactual Reasoning in LLMs
Yucheng Wang, Yuetian Du, Zhengyi Liu, Rongyu Zhang, Bing Zhao, Boyu Yang, Ming Kong, Lin Qu, Hu Wei, Jie Liu, Qiang Zhu
cs.AI
Counterfactual reasoning requires models to reason beyond the observed world and explain how altered conditions propagate through downstream consequences. Existing benchmarks largely target bounded settings with fixed variables or single gold outcomes, overlooking open-domain scenarios requiring causal-process evaluation. To this end, we present $\textbf{WhatIfBench}$, a diagnostic benchmark for open-domain, open-form, long-horizon...
-
51
Cross-Session Decomposition Attacks: Scaling Risk and Intent-Aligned Retrieval Defense
Disen Liao, Yihan Wang, Freda Shi, Yaoliang Yu
cs.AI
Scaling laws are usually read as a capability story: lower language-modeling loss yields more useful models. We study a safety consequence of this mechanism in \emph{cross-session decomposition attacks}, where benign-looking subqueries are asked across independent interactions and later recomposed toward a forbidden objective. We formalize this setting as \emph{compositional safety risk} and prove a conditional risk-transfer bound: when the...
-
52
CASTANET: Causality-Aware Spatio-Temporal Adversarial Network Using Traffic Incident Effects
Toshiya Kitahara, Ryu Shirakami, Koh Takeuchi, Hisashi Kashima
cs.AI
Predicting non-periodic traffic congestion caused by sudden incidents (e.g., accidents and road damage) is crucial for advanced intelligent transportation systems. However, incident-driven congestion is difficult to forecast because incidents are extremely sparse, occur at specific times and locations, and have heterogeneous impacts depending on the traffic context. While recent deep learning approaches have significantly improved periodic...
-
53
A Deep Learning-Based Stacking Ensemble Framework for Turbofan Engine Remaining Useful Life Prediction
Limon Bin Hossain, Md. Salehin Seyam, Md Rashedul Islam, Abdur Rahman, Md Sharifuzzaman
cs.AI
This study proposes a two-level stacking ensemble framework for Remaining Useful Life (RUL) prediction of turbofan engines, evaluated on the NASA C-MAPSS benchmark using the FD001 and FD003 subsets. The framework integrates four heterogeneous deep learning base learners: Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), CNN-LSTM, and CNN-GRU, whose out-of-fold predictions are combined by an XGBoost meta-learner to capture...
-
54
From Documents to Reasoning: A Validated Synthetic Data Pipeline and Semantic-Aware Fine-Tuning for Financial Numerical Reasoning
Lokendra Birla, Milind Savagaonkar, Visnu Srinivasan, Sowmya Rasipuram, Shubhashis Sengupta
cs.AI
Financial question answering (QA) has emerged as a key benchmark for evaluating the performance of Large Language Models (LLMs) on domain-specific tasks involving complex data formats such as tables, charts, and rich textual narratives. While recent advancements have enabled models to reason across modalities and perform multi-step arithmetic operations, limitations remain in performance consistency, and evaluation reliability. In particular,...
-
55
AI Alignment through a Game-theoretic Lens: A Survey
Yanan Cai, Zhongrui Zhao, Zhigang Lu, Ickjai Lee, Wei Emma Zhang, Minhui Xue, Yihong Zhang, Shuchao Pang, Wei Xiang
cs.AI · cs.CL · cs.GT
As large language models and increasingly capable AI agents are deployed in high-risk settings, aligning them with complex human values has become a central challenge. Existing alignment methods, while effective in improving helpfulness, harmlessness, and controllability, often struggle to capture real-world preferences that are context-dependent, non-transitive, and shaped by dynamic multi-party interactions. This survey reviews AI alignment...
-
56
Rubric-to-Code Credit Assignment for Reinforcement Learning
Rui Jin, Jikai Chen, Yihan Chen, Hao Zhou, Demin Zhu, Kaichen Yang, Dong Wang, Chenyi Zhuang
cs.AI
Interactive web application generation requires models to produce usable HTML, CSS, and JavaScript applications from natural language requests. Unlike conventional code generation, application quality depends on multiple user-facing functional requirements, each often tied to localized code regions such as event handlers, state updates, DOM fragments, or CSS selectors. Standard GRPO collapses these structured outcomes into a single...
-
57
Resource Constraints and Performance in Agentic AI Systems
Amaz Salman, Malka Halgamuge, Teo Susnjak
cs.AI
Progress toward more autonomous AI increasingly depends on agentic systems that combine a language model with tools, memory, state management, and multi-step execution. These mechanisms shape both task capability and operational burden. We compare OpenClaw and NanoBot as complete agentic systems using a paired primary benchmark and a more detailed instrumented subset of paired prompts. In the primary benchmark, the rate of full task...
-
58
HyQuant: Hybrid-Precision Quantization for LLM Attention
Jiatong Ding, Bingxin Xing, Yu Zhang, Dian Ding, Xiaodong Yi, Xianbin Ouyang, Feihu Zhou, Kun Zhang, Zhenyu Guo, Hao...
cs.AI
Quantization has been widely adopted in LLM training and inference to reduce cost and improve efficiency. However, low-bit quantization of the \emph{attention} module often introduces large errors at very low bit-widths, causing performance degradation. Existing methods mainly rely on smoothing techniques to handle outliers, while we propose a hybrid quantization design to better balance accuracy and efficiency. Specifically, we propose...
-
59
See, Hypothesize, Validate: Multimodal Agentic Framework for Discovering Governing PDEs
Sarang Manoj Pekhale, Amartya Roy, Rajat Sarkar, Souvik Chakraborty
cs.AI
Discovering governing partial differential equations (PDEs) from observational data remains a core challenge across the sciences. Existing sparse-regression, symbolic-regression, and LLM-based approaches can be constrained by predefined libraries, noise sensitivity, hallucination, or limited iterative refinement. We introduce \textbf{MAGE} (\textbf{M}ultimodal \textbf{A}gentic \textbf{G}overning \textbf{E}quation Discovery), an agentic...
-
60
CoRe-MoE: Compact Reusable MoE for Continual Multimodal Instruction Tuning
Runze Liu, Naibin Gu, Mingxu Ai, Yuqing Li, Peng Fu, Zheng Lin, Weiping Wang
cs.AI
Continual multimodal instruction tuning requires multimodal large language models to acquire new task abilities sequentially while preserving previously learned knowledge. LoRA-MoE provides a promising solution by introducing expert-based capacity, but repeatedly learning and maintaining full LoRA experts leads to substantial parameter overhead. This raises a natural question: is full expert expansion necessary for every new task? To answer...
-
61
SpikeOPD: Stable On-Policy Distillation for Autoregressive Spiking Language Models
Enqiao Lu, Xingrui Yu, Yiwei Fu, Zhenglin Wan, Pengfei Zhou, Wangbo Zhao, Muqing Jian, Xueyi Zhang, Yang You, Ivor Tsang
cs.AI
Spiking neural networks (SNNs) offer a path to energy-efficient language modeling through sparse encoding and event-driven computation, but training capable spiking language models from scratch remains difficult. A practical alternative is ANN-to-SNN migration through knowledge distillation (KD), where a pretrained artificial neural network (ANN) teacher supervises an SNN student. Existing migration approaches distill on fixed corpus...
-
62
From Uncertainty to Clinical Risk: Severity-Aware Conformal Planning for Interactive Medical Diagnosis
Yue Zhou, Haiyang Zhou, Jin Zhang, Kong Wang, Yongxin Ni, Youhua Li, Hanwen Du
cs.AI
Interactive medical diagnosis dynamically acquires patient information through multiple rounds of questioning, supporting accurate, efficient, and safe clinical decisions under incomplete evidence. Existing methods commonly guide information acquisition with predictive uncertainty or label ambiguity, but overlook the asymmetric clinical risk of missing severe diseases and lack unified long-horizon planning over whether to continue asking...
-
63
An Empirical Evaluation of Cross-City POI Recommendation on a Large-Scale Benchmark
Peibo Li, Yang Song, Hao Xue, Maarten de Rijke, Flora D. Salim
cs.AI · cs.IR
Cross-city point-of-interest (POI) recommendation is crucial for navigating unfamiliar urban environments, yet its progress has historically been constrained by data limitations. Using the recently proposed large-scale benchmark Trip World, we empirically re-examine whether conclusions drawn on small prior benchmarks still hold under worldwide coverage, low home-destination region overlap, and large, semantically rich POI inventories. Our...
-
64
KLOD: Locality-Preserving Knowledge Editing via Non-Target Distribution Preservation
Hojun Jeong, Gyunyeop Kim, Sangwoo Kang
cs.AI
Fine-tuning-based knowledge editing is simple and architecture-agnostic, but standard cross-entropy increases the edited target probability without explicitly constraining changes in the non-target output distribution. In sequential editing, such unconstrained redistribution can accumulate as distributional drift and contribute to locality degradation. We propose KLOD, a bounded and distribution-preserving objective for fine-tuning-based...
-
65
RealSWE: A Compositional Evaluation of Coding Agents under Realistic User Requests
Gyuhyeong Kim, Hyojung Gwon, Jeonghyeon Kim, Kyuhong Shim, Sunjae Lee
cs.AI · cs.LG
Coding agents are now commonly evaluated on the SWE-bench family of benchmarks, whose tasks are built from curated GitHub issues--long, structured, and information-rich. Real user requests, however, are typically far shorter and less structured. To characterize this gap, we define a six-category information taxonomy and four dimensions of linguistic style, and apply them to real user prompts from SWE-chat and problem statements from SWE-bench...
-
66
Evidential-Based Higher-Order Set Argumentation Framework
Shuai Tang
cs.AI · math.LO
Evidential argumentation extends Dung's abstract argumentation by requiring arguments and interactions to be backed by chains of evidence rooted in prima-facie elements. However, existing formalisms lack a unified treatment of evidential support, higher-order relations (attacks and supports targeting arbitrary elements), and collective interactions (sources as sets). In this paper, we introduce the Evidential-Based Higher-Order Set...
-
67
AcCoRD: Evaluating User-Agent Collaboration Under Realistic User Preference Dynamics
Tejas Srinivasan, Shikib Mehri, Nandita Shankar Naik, Anirban Das, William M. Campbell, Jesse Thomason
cs.AI
User preferences in user-agent collaboration are rarely static and fully-specified upfront: preferences are formed, revealed, adjusted, and relaxed during interaction. Existing benchmarks for evaluating user-agent collaboration focus almost exclusively on resolving underspecified preferences, thereby failing to capture the richer dynamics of real-world interaction. We introduce AcCoRD, a user-agent collaboration benchmark requiring agents to...
-
68
CURA: Certified Runtime Alarms for Computer-Use Agents
Divake Kumar, Sina Tayebati, Devashri Naik, Amanda Sofie Rios, Nilesh Ahuja, Omesh Tickoo, Ranganath Krishnan, Amit...
cs.AI · cs.CV · cs.LG
Self-report is the cheapest oversight channel a deployer has, and on capable computer-use agents (CUAs) it fails precisely where oversight matters. On 361 OSWorld tasks our pipeline, a read-only feasibility gate, a planner, and a GUI executor, reaches a mean task score of 82.9, above the 72.4 human reference, yet 64 of its 71 failures (90%) end with a success claim, 61 acknowledging no blocker, and the explicit failure affordance is never...
-
69
CEDAR: Automata as Verifiable Interfaces for Language-Guided Embodied Action
Lekai Chen, Alvaro Velasquez, Ashutosh Trivedi
cs.AI · cs.CL · cs.FL
Natural-language tasking of embodied agents is rarely just goal specification: users also impose constraints that must persist while the world changes. Code-generating LLM agents can produce plausible behaviors for such instructions, but their free-form programs provide no stable object to verify, compose with new constraints, or repair from a failing trace. We present CEDAR, a counterexample-guided framework that grounds instructions as...
-
70
ReToolSQL: Agentic Reinforcement Learning for Robust Text-to-SQL
Pratik Kakkar, Chandra Dhir, Ravi Shankar, Pareekshit Reddy Gaddam, Anup Shirgaonkar
cs.AI
Recent work has shown that reinforcement learning from execution feedback can substantially improve text-to-SQL performance, often enabling smaller models to match or exceed much larger systems. However, most existing approaches treat SQL generation as a single-turn task, limiting the model's ability to recover from errors through iterative refinement. We present ReToolSQL, a two-stage training framework for text-to-SQL that combines (i) a...
-
71
Credo: Reusable Declarative Primitives for Agentic Workflows
Duo Lu, Andrew Crotty, Uğur Çetintemel
cs.AI · cs.DB
An LLM application depends on both a model and a harness: the program that determines what each call sees, how many calls to make, and which answers to trust. Coding agents can now discover strong harnesses by searching over candidate programs, but the resulting artifact is an opaque block of imperative code whose logical steps, runtime signals, physical execution decisions, and prompt strategies remain implicit and task-specific, forcing...
-
72
Why Didn't It Check? Unsupported Final Claims and Their Repair in Two Tool-Equipped Language Models
Justin Bronder
cs.AI · cs.CL
A language model with access to tools can commit to a final claim unsupported by the evidence it has seen, even when a single available tool call would resolve the uncertainty and its instructions explicitly forbid assumptions and guesses. We separate this failure into two precisely defined quantities: occurrence, how often the model makes an unsupported claim on its own, measured from the visible evidence and final claim without using the...
This edition is part of The Daily Abstract — cs.AI archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.