cs.AI · 2026-10-26 · No. 154
Artificial Intelligence, 2026-10-26.
50 new papers in cs.AI. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
50 entries-
01
SemantEq: Faithful Bidirectional Equivalence of Formal Statements
Xinrui Li, Pawan Sasanka Ammanamanchi, Siddharth Bhat, Rianna Jamdar, Yongxi Lin, Stella Biderman
cs.AI · cs.LG
Statement autoformalization translates mathematics from natural language into a proof assistant such as Lean 4, and models now do it at scale. As provers get stronger, the burden of correctness shifts from the proof to the statement, that is, to whether the formal statement faithfully translates its source. Given a trusted reference formalization, the natural test is logical equivalence, and it proves too much. $P \leftrightarrow Q$ holds...
-
02
Closing the Modality Gap via Simplex-Constrained Representations
Shubham Gupta, Siva Reddy, Perouz Taslakian, Valentina Zantedeschi, Cem Subakan
cs.AI · cs.CV
While multimodal contrastive models like CLIP and CLAP successfully learn shared representations, their embeddings typically exhibit a persistent \emph{modality gap}. We propose addressing this separation through a purely geometric approach: changing the embedding domain from the unit sphere, $S^{d-1}$, to the probability simplex, $Δ^{d-1}$. Although both manifolds share the same intrinsic dimension, the simplex acts as a structural prior;...
-
03
NgramRL: Accelerating RL Post-Training for Structured Generation via Rollout-Aware N-gram Speculative Decoding
Nilesh Prasad Pandey, Jangseon Park, Jason Kong, Onat Gungor, Tajana Rosing
cs.AI
Reinforcement learning (RL) post-training improves the reasoning capabilities of large language models, but its cost is dominated by autoregressive rollout generation, which can exceed 70% of training time. Existing speculative-decoding methods are poorly suited to this setting: model-based drafters consume scarce GPU memory and may become misaligned as the policy evolves, while existing model-free methods do not explicitly exploit repetition...
-
04
Advancing SVD-based LLM Compression via Layer-Wise Error Model Search
Moritz Thoma, Maximilian Groezinger, Maximilian Forstenhäusler, Emad Aghajanzadeh, Manoj Rohit Vemparala, Christos...
cs.AI
Low-rank SVD-based compression offers a powerful strategy to reduce the computational costs of LLMs. However, existing methods face two key limitations: (i) global rank allocation, where uncalibrated error proxies fail to capture complex error propagation, and (ii) decomposition quality, where Fisher-based estimators suffer from severe rank collapse. In this work, we address these limitations by introducing Layer-wise Error Modeling Search...
-
05
Do "True" and "False" Add Up to One? Complement Consistency in LLM-Agent Opinion Simulations
Anouar Imel, Jin Qi
cs.AI · cs.CL · cs.MA · cs.SI
In LLM-agent opinion simulations, each agent reports the probability that a claim is true after seeing its own previous probability and the probabilities reported by its neighbors, and that number becomes its state in the next round. If the number describes the agent's position rather than the sentence it was shown, then rewriting the claim as its complement and replacing every probability p with 1 - p should return the complementary answer,...
-
06
From Deliberately Constructed Systemic Representations of the World of Activity to Dialogue: A Five-Level Communication Architecture for Strong Language-Based ASI
Maxim Osovsky
cs.AI
This paper proposes a five-level organization of message formation and understanding within thinking and activity in which ASI participates. Its central thesis is that a language model's context is fundamentally incapable of presenting the foundations of utterance formation for examination and verification. These foundations are established in advance by acquired schemas, systemic representations of the world of activity, and connections...
-
07
A Foundation Model for Policy In-Context Longitudinal Causal Effect Estimation
Wenxin Chen, Kyra Gan, Mingyu Lu, Zilin Jing, Fei Wang, Hoifung Poon, Tristan Naumann, Peniel Argaw
cs.AI
Longitudinal causal effect estimation is complicated by time-varying confounding and treatment-confounder feedback loops. Existing methods generally require data-specific nuisance-model fitting, and many are tailored to prespecified treatment sequences or prediction horizons, leading to time-consuming computation at deployment. We introduce *Policy In-Context Longitudinal causal Effect estimation with Prior-data Fitted Networks*...
-
08
Reimagining Enterprise RAG for Multi-Agent Systems: A Knowledge Layer That Organizes Before It Retrieves
Garima Agrawal, Prasun Das, Akshay Sarvade, Priyanka L, Minisha N, Sravani Joshna, Hemath Manivannan, Lavanya...
cs.AI
Enterprises are deploying agentic AI across the software development lifecycle, and they need the behavioral logic of the systems they act on, not stakeholder documentation. A seven-agent reverse-engineering pipeline recovered this logic, processing 241 repositories across 18 services into thousands of artifacts describing scope, journeys, rules and acceptance criteria. Recovery does not confer usability. Entities like offer, eligibility, and...
-
09
HarnessMM: Recursive Self-Improvement for Harness Token Efficiency
Yuhua Jiang, Chang Xu, Feifei Gao, Li Zhao
cs.AI
Agent harnesses repeatedly invoke reasoning after tool feedback, even when an earlier call has already fixed the next action. We introduce HarnessMM (Harness Minus Minus), a method for improving harness token efficiency through guarded decision reuse and recursive self-improvement (RSI). RSI iteratively refines companion harness configurations from training feedback, with validation selecting the configuration for deployment. A controller at...
-
10
ActionRAG: Evidence-Refining Graph Diffusion for Long-Term Memory in LLM Agents
Navyansh Mahla, Sashank Vandrangi
cs.AI · cs.CL
LLM agents need long-term memory that can recover precise and mutually consistent evidence from growing interaction histories, particularly when answers depend on relations among facts rather than isolated semantic matches. Current memory pipelines remain vulnerable at two stages: indexing errors can fragment repeated entities or merge distinct ones, and online retrieval often treats initial similarity scores as final even when the...
-
11
Agentic Hazard Mapper: Emulating Expert Map-Making with AI Agents for Risk Communication
Sidi Wu, Lifeng Lin, Yizi Chen, Anna Yokokubo, Lorenz Hurni
cs.AI
Hazard maps are essential tools for public risk communication, preparedness, and evacuation planning, yet effective cartographic design is not always ensured due to limited access to cartographic expertise across local governments and communities. We present Agentic Hazard Mapper, a multi-agent system that automates hazard-map production by emulating professional cartographic workflows and iterative design trade-offs while adapting design...
-
12
Retiming Robot Demonstrations with a Learned Speed Prior
Seungyong Moon, Deokjae Lee, Hansang Lee, Munkhtselmeg Battsengel, Youngin Kim, Seonghyeon Yun, Sungjin Jeon,...
cs.AI · cs.RO
The pace of a robot demonstration is often determined by the teleoperator rather than by the task itself. As a result, the same motion can appear at widely different speeds across demonstrations, and policies trained on such data may inherit operator-specific timing along with task behavior. We propose to learn a speed prior directly from large-scale demonstration data. Given a task instruction, a motion path and the images along it, it...
-
13
Do Language Models Trust Their Own Justifications? A Study on Functional Consistency
Alisson Rosa Pereira, Bruno Iochins Grisci
cs.AI · cs.LG
Large Language Models (LLMs) have been widely adopted in text classification tasks, where they not only output class predictions but also generate explanations that highlight the tokens deemed most relevant for reaching the predicted label. Yet it remains unclear whether these highlighted elements are behaviorally consistent with the model's own predictions under targeted interventions, which we refer to as functional auto-consistency. While...
-
14
WiMoT: Replay-Free Continual Wi-Fi Sensing via Moment Transport
Chunchun Yang, Yang Cao, Zhitang Chen
cs.AI
Continual Wi-Fi sensing must balance plasticity, learning new rooms or users, against stability, keeping earlier ones, yet nodes often cannot retain channel state information (CSI) for privacy and storage reasons. We propose WiMoT (Wi-Fi Moment Transport), which stores the per-class feature mean and covariance of every earlier domain instead of samples. When the representation changes, stored statistics become stale. WiMoT restricts the...
-
15
LGMT: A Tool for Testing the Logical Reasoning Reliability of LLMs
Zenghui Zhou, Xiaoke Fang, Zheng Zheng
cs.AI
Large Language Models (LLMs) increasingly serve as reasoning components in modern software systems, yet a model that answers a logical query correctly can contradict itself when the same problem is restated in an equivalent form. Static benchmarks evaluate queries in isolation and therefore fail to expose such inconsistencies. To address this limitation, we present LGMT, an open-source tool that detects reasoning inconsistencies through...
-
16
What Transfers Across Protein Pockets? Experience Reuse in Molecular Optimization for Agentic Structure-Based Drug Design
Zaifei Yang, Weiyu Chen, Yaqing Wang, James Kwok
cs.AI · q-bio.BM
LLM agents optimize a ligand in a protein pocket by editing it step by step and docking each edit. Recent agents first spend extra dockings probing the complex with controlled edits; guidance induced from these probes is reported to help more than the chemical knowledge the model already carries. The probes are then discarded with the instance that produced them, so the obvious next step is to keep them in an experience base, letting a new...
-
17
LLaCO: Continuous Diffusion for Large Language Models with Competition-Aware Semantic Scheduling
Zijian Jia, Peixuan Zhang, Genying Li, Di Wu, Yujie Fu, Si Li, Boxin Shi, Shuchen Weng
cs.AI
Continuous diffusion models have emerged as a promising non-autoregressive paradigm for text generation over continuous embedding spaces. Along the continuous trajectory, the residual token identity directly shapes the denoising objective. However, the geometric trajectory misaligns with temporal progression, triggering severe temporal compression. In this paper, we show that embedding norm decay causes Euclidean distance to yield spurious...
-
18
Beyond Channel Data: Configuration-Enriched Radio Foundation Models
Shrihari Vasudevan, H. G. Ranjani, Raaghul Ranganathan, Satwik Sahu, Thirumaran Ekambaram
cs.AI · eess.SP
This paper proposes incorporating channel configuration (CFG) information into Radio Foundation Model (RFM) pre-training and demonstrates that the resulting CFG-enriched embeddings serve as effective inductive priors for downstream tasks under label scarcity. We compare the proposed embeddings with raw channel tokens and multiple baseline models, under three different data regimes, for multiple downstream tasks ---...
-
19
IGG: A Benchmark for Interactive GUI Grounding under Visibility Constraints
Kyeongseon Kim, Jiyeon Son, Tae-Hyun Oh
cs.AI
GUI grounding benchmarks ask whether an agent can localize a target that is already visible in a static screenshot. Real interfaces often violate this assumption: a target may be off-screen, appear only after a state change or hover, remain occluded, or become actionable after a delay. This leaves the ability to recover target visibility unevaluated. To measure this reveal step, we introduce Interactive GUI Grounding (IGG), a benchmark in...
-
20
When Agents Fail: Model or Harness--Who's to Blame?
Shao Zhang, Hangfan Zhang, Yuanyuan Shi, Hao Li, Min-Le Su, Kangcong Li, Jingping Wang, Chunjiang Mu, Chen Zhang,...
cs.AI · cs.CL · cs.SE
LLM agents combine models with execution harnesses, so agentic benchmark performance reflects their joint behavior. We argue that harnesses should therefore be evaluated through their interactions with underlying models. We develop a framework combining five complementary measures: (i) Valid Completion Rate (VCR), how reliably agents finish normally and deliver evaluable results, irrespective of task correctness; (ii) Model-Harness Fit, how...
-
21
CASE: Confusion-Aware Skill Evolution for Frozen Multimodal Emotion Models
Siyu Wu, Zeyu Liang, Linghao Wang, Qiyun Zheng, Yi Yao, Ling Lo, Hongxia Xie
cs.AI
Multimodal large language models (MLLMs) have substantially advanced Multimodal Emotion Recognition (MER) by enabling fine-grained emotion understanding through reasoning over multimodal evidence. However, they still exhibit systematic confusion between semantically adjacent emotions with highly overlapping multimodal cues. Existing approaches typically address these errors through global parameter adaptation, making confusion correction...
-
22
CauProphet: Teaching Agents to Develop Causal Cognition like Humans
Kaiwen Wu, Chaochao Lu
cs.AI
Large language model (LLM) agents increasingly support long-horizon tasks by leveraging external memory and past experience. However, existing agents mainly retrieve records or summaries, lacking the ability to form and refine causal understanding of the world. Inspired by human causal cognition, we introduce CauProphet, an agent that develops and updates causal knowledge within its Causal Cognition. For each task, CauProphet combines...
-
23
Beyond Post-Hoc Rewards: Privileged Reasoning Exploration for Multimodal Embeddings
Tianyu Yang, Yijun Tian, Lars Benedikt Kaesberg, Jan Philip Wahle, Bela Gipp, Terry Ruas, Daniel Kurzawe
cs.AI · cs.CL
Advances in Multimodal Large Language Models (MLLMs) have driven substantial progress in multimodal embeddings. Recent methods exploit generative capabilities by augmenting embedded inputs with self-generated reasoning to produce more informative embeddings. However, conventional retrieval supervision for training embedding models specifies pairwise relevance relations without explicitly guiding the reasoning used for input augmentation. Such...
-
24
ALLMTS: Automated LLM-based Medical Triage System
Michał Remigiusz Janiszewski, Artur Stopa, Łukasz Lenkiewicz, Wojciech Achtelik, Bartosz Gonczarek
cs.AI
Telephone triage is a safety critical task: from a brief intake note, a nurse must decide whether a caller needs an ambulance, an emergency department, an appointment, or self care at home. Queried directly, large language models (LLMs) are unreliable: they over-escalate routine cases and cannot justify their recommendations against an auditable clinical standard. We present the Automated LLM-based Medical Triage System (ALLMTS), which...
-
25
POSEIDON: Scaling Training Environments for Scientific Agents from Code Repositories
Qifan Zhang, Yuhan Li, Nuo Chen, Bowen Liu, Xiao Hu, Miao Peng, Chenyi Zi, Lixin Liu, Lydell Huang, Jing Tang, Jia Li
cs.AI
Training environments remain a major bottleneck for agents in data-driven scientific discovery. Existing collections of executable and verifiable training environments are small, and their construction remains difficult to scale. To address this limitation, we introduce Poseidon, an automated pipeline for generating diverse, verifiable training environments from scientific code repositories at scale. From the same repository budget, Poseidon...
-
26
When to Stop Penalizing Actions? Martingale GRPO for VLA Reinforcement Learning
Zongyao Zhao, Cheng-Jie Zhao, Ruihang Jiang, Bing Zheng, Zhaolin Wang, Yuanwei Liu
cs.AI
A failed vision-language-action (VLA) rollout does not imply that every action contributed to failure. Yet in group-relative policy optimization (GRPO), a single trajectory-level advantage is assigned to all actions in a rollout. Potentially useful recovery attempts can thus be penalized alongside the errors they aim to correct. Ideal stopping conditions for failure feedback are characterized using success-probability and policy-score...
-
27
Async-RBench: Benchmarking Asynchronous Task Execution in LLM Agents
Detao Zeng, Guilin Ou, Nuo Chen, Yunhao Feng, Hongliang Wang, Qinli Yang, Junming Shao, Zhong Zhang
cs.AI
Large language model (LLM) agents increasingly execute tasks asynchronously: a main agent continues working while its subagents run, and the task state may change before their results arrive. The main agent must decide which work to update or preserve and which checks to repeat, while avoiding prohibited changes. Final task success alone does not reveal whether these results were handled correctly, and natural asynchronous arrivals are hard...
-
28
LeafSkill: Efficient Leaf-Level Action Grounding for Recursive LLM Agents
Shen Liu, Ze Zhou, Zhenguo Xu, Shaopu Wang, Yike Gao, Chunlei Wang
cs.AI
Recursive large language model (LLM) agents solve long-horizon tasks through decomposition, execution, and environmental feedback. Yet after producing an atomic subtask, they often invoke the same large model again to translate a familiar instruction into an executable action. We observe that high-level planning is task-specific, whereas leaf-level action grounding recurs across tasks and can be checked against environment-admitted actions....
-
29
DealsFlow: An Evidence-Gated Agentic Harness for Venture Capital Deal Triage
Ming Ze Tang, David Cutting, Boyd Carson, Vasiliki Carson
cs.AI
Large language models (LLMs) can read startup pitch decks, but letting them emit investment scores directly invites score inflation, run-to-run variance and rationales that are hard to audit. We describe DealsFlow, a human-in-the-loop agentic harness deployed at a UK early-stage fund. The LLM reads the deck, cites evidence and rates each category; code combines the ratings, caps them and only ever lowers them. Three mechanisms implement this:...
-
30
Adaptive Control of Scientific Instruments with Nonstationary Responses through Multimodal Agents
Guoyang Shi, Hongwen Li, Yiding Yu, Zhuang Fu, Siqi Ding, Zhengyuan Chen, JianGuo Chen, Hanyue Zhao, Tianyuan Liu
cs.AI
Controlling scientific instruments requires parameters to be adjusted progressively in response to feedback from successive operations. When unobserved operating conditions evolve with operational history, responses become nonstationary, and a static mapping from actions to responses becomes inadequate for decisions across shots. Shot-to-shot tuning of neutral beam injection (NBI) ion sources in magnetic confinement fusion devices is...
-
31
FOCUS: A Lightweight Mamba-2 Model for EEG-Based Cognitive Workload Classification
Ioannis Kyprakis, Stefanos Gkikas, Chariklia Chatzaki, Zongyi Jiang, Randy Gomez, Raul Fernandez Rojas
cs.AI
Cognitive workload estimation from physiological signals is increasingly relevant in high-risk environments, where continuous and unobtrusive monitoring can inform adaptive systems and safety interventions. This paper presents FOCUS (Frequency-band Optimized Cognitive-load Ultralight SSM), a compact Mamba-2-based model for EEG-based binary workload classification under constrained data conditions. Rather than learning frequency sensitivity...
-
32
TGR-EvoDAG: A DAG-based Multi-Agent Code Evolution Framework for Generative Recommendation on Tencent
Junlin He, Junzhang Zhu, Yudong Li, Yihong Tang, Xuefeng Jiang, Wei Ma, Chengxiang Zhuo, Zang Li
cs.AI
Large Language Model (LLM) agents have enabled automated code evolution for algorithm discovery. However, current recursive self-improvement (RSI) research for sequential recommendation faces a dilemma: general-purpose frameworks lack domain-specific feedback, while recommender-specific frameworks rely on linear evolution. Crucially, naively integrating them fails when applied to Generative Recommendation (GR). Unlike end-to-end models, GR...
-
33
From Visual Affinity to Learning Credit in Multimodal Reinforcement Learning
Yuhang Han, Dingning Liu, Yujie Chen, Yaojie Zhang, Jingwei Song, Zequn Yang, Xuanming Shang, Li Ding, Zhijiang Guo,...
cs.AI
Reinforcement learning with verifiable rewards (RLVR) improves multimodal reasoning, but uniformly assigning a single response-level advantage to all tokens overlooks the distinct roles of visual observations and subsequent reasoning. Visual affinity alone is insufficient: predictive states may align with both image and prompt-context representations, and upweighting valid visual observations can amplify their negative-advantage updates when...
-
34
Beyond Gain: Measuring Skill Internalization for Agent Skill Retirement
Yanze Wang, Pengfei Yao, Tianyi Sun, Hongda Chen, Yunyun Han, Jun Sun, Chuanrui Hu, Yafeng Deng
cs.AI
LLM agents retrieve skills from public hubs that hold up to about 100,000 entries and serve many models. As models improve, a hub must find the skills a given model has internalized, meaning it can do without them, and retire them for that model, yet internalization has not been measured with known reliability. Published rules that compare runs with and without a skill retire on the gain alone. The gain is near zero both for an internalized...
-
35
Solvent: Long-Horizon Reasoning for Multi-Step Retrosynthesis
Yifei Wang, Botian Wang, YiFei Wang, Jiangtao Feng, Xinbo Zhang, Yawen Ouyang, Yixin Wu, Lihao Wang, Xiaoqing Zheng,...
cs.AI
Multi-step retrosynthesis requires recursively transforming a target molecule through successive reaction steps into purchasable building blocks, and recent work has begun to draw on large language model (LLM) reasoning to tackle the task. In its latest evolution, LLM reasoning has entered the long-horizon regime: models pursue objectives across interdependent steps, interact with environments, and adapt to feedback. This shift has markedly...
-
36
DMAIC-Bench: From Self-Reflection to Self-Restraint for Agents in Multi-Stage Analytical Tasks
Shan Peng, Shuaiqi Cheng, Miao Peng, Chenyi Zi, Jia Li
cs.AI · cs.CL · cs.LG
Multi-stage analytical tasks require LLM agents to use intermediate evidence to decide whether to continue, redirect or stop. Self-reflection, in which an agent critiques its output, is widely studied, yet a critique does not show whether evidence changed the next action. We call that capability self-restraint. Existing agent benchmarks largely measure task completion or output quality and leave it untested. DMAIC-Bench evaluates it with 97...
-
37
Lifelong Context Adaptation through Bidirectional Memory-Skill Learning
Tianyi Xu, Huazheng Wang
cs.AI
Lifelong LLM agents must learn from an expanding history of interactions while making each decision within a bounded context window. Memory makes past experience available, but the agent may still need to infer how to solve each new task from the retrieved records. Skills provide reusable procedures, yet may omit the task-specific facts needed to apply them. Because retrieved memory and skills shape the agent's behavior, they also influence...
-
38
Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution
Zhiyong Cao, Hengjie Zhu, Yongxin Wang, Xuchen Li, Jintao Li, Shuxia Liu, Dunqiang Liu, Bo Wang, Kairan Zhang, Cong...
cs.AI
LLM agents are increasingly used to solve real-world problems, and their effectiveness depends on both the underlying models and the harnesses that support their operation. However, most existing benchmarks focus on model capabilities and overall agent performance, with limited attention to the evaluation of agent harnesses. To address this gap, we introduce TraceTrial-Bench, which organizes harness reliability into seven components covering...
-
39
MedCaseAgent: From Multimodal Clinical Evidence to Rare Disease Case Reports
Hongkang Chu, Yifan Shen, Tianjiao Yu, Zhuoqing Zhong, Jianguo Cao, Meihuan Huang, Xu Cao
cs.AI
Although Large Language Models (LLMs) have demonstrated potential in clinical documentation, generating the rigorous, evidence-based reasoning required for unprecedented, atypical, and rare disease case reports remains a significant challenge. We present MedCaseAgent, an end-to-end agentic reasoning paradigm that bridges this gap by synthesizing publication-quality reports from unstructured clinical notes. MedCaseAgent leverages a...
-
40
RSIHub: A Composable Framework for Agent-Evolution Methods
Zimu Wang, Xiaobo Wang, Siyu Ye, Jiaqi Li, Silin Chen, Yuling Shi, Ruobing Wang, Jingjing Zhang, Chaofan Wang, Kai...
cs.AI
Agent-evolution methods use execution feedback to improve prompts, skills, tools, and orchestration, but their implementations often rebuild the same experimental machinery. We present RSIHub, an open-source framework for building, comparing, and extending these methods on shared infrastructure. Recipes compose reusable operators and declare mutable resources; RSIHub supplies execution, evaluation, recovery, and lineage. Researchers can focus...
-
41
Minimum Description Length Unsupervisedly Separates Law-Grade from Statistical-Grade Knowledge in a Self-Improving Science Agent - and Reveals 86% of Its Own Discoveries Are Statistical
Wenbin Mao, Pei Zou
cs.AI
AI systems that discover scientific relations now generate candidate "laws" at scale, but the bottleneck has shifted from generation to vetting: which candidates deserve belief? We show that a deployed self-improving science agent - one that has admitted 252 relations through held-out prediction courts - already computes the quantity that answers this question: the Minimum Description Length compression ratio used for model selection doubles,...
-
42
Spatial Heuristic Strategy based Diffusion Reinforcement Learning for Online 3D Bin Packing
Tong Li, Qingyang Xu
cs.AI
Traditional heuristic methods have accumulated mature experience in core objectives, such as space utilization and layout compactness of 3D bin packing, relying on artificially designed rule-based logic. However, they exhibit obvious limitations in generalization ability and adaptability to dynamic scenarios. Diffusion reinforcement learning, which integrates the spatial search capability of reinforcement learning and the data distribution...
-
43
Financial Context-Rich Strategy for Actor-Critic based Agents: A Deep Reinforcement Learning Approach for Stock Trading
Hrishikesh Singh, Aarti Sharma, Millie Pant
cs.AI · q-fin.CP · q-fin.PM
In modern financial markets, more than 3/4th of the large volume trade is executed by algorithmic trading based on advanced trading strategies to attain higher precision and speed than traditional human traders. The conventional strategies focused on price-based indicators are inadequate in capturing the market dynamism arising from real-world events such as social sentiments, political instability, or sudden economic shifts. With the rise of...
-
44
Training an MoE LLM in MXFP4: How We Closed the Gap to BF16
Han Wang, Zhitao Wang, Natalia Frumkin, Xuanwu Yin, Alireza Khodamoradi, Dong Li, Emad Barsoum
cs.AI
Training large language models (LLMs) in sub-8-bit arithmetic promises substantial gains in memory bandwidth and compute throughput, yet FP4 formats introduce quantization error severe enough to destabilize optimization if left unaddressed. We present ALTO, an open-source training recipe for GPT-OSS-20B, a 20-billion-parameter mixture-of-experts (MoE) model, on the MLPerf Small MoE Training benchmark under the MXFP4 microscaling format. The...
-
45
Correct Answers, Closed Gates: SolveBind for GUI Agents at the Verification Barrier
Xinhao Song, Haoxuan Peng, Su Su, Hongliang Wu, Sirui Song, Gongshen Liu, Linfeng Zhang, Dongrui Liu
cs.AI
Websites and applications deploy CAPTCHAs and anti-automation mechanisms that use behavioral signals such as interaction trajectories and timing, not outcomes alone, to distinguish humans from automated agents. We call these protected GUI environments, where correctly solving a verification task is insufficient for end-to-end task completion. Agents must turn solver outputs into accepted interactions and adapt execution to runtime feedback...
-
46
RxnExBench: Benchmarking Vision-Language Models for Structured Chemical Reaction Extraction from Scientific Literature
Jiaxing Sun, Junyuan Gao, Ruikang Zhang, Hao Zheng, Lingli Ge, Xiao An, Jiang Wu, Huazheng Zeng, Jiahe Song, Chen...
cs.AI
Screen Tables and Substrate Scopes are information-dense figures widely used in synthetic chemistry literature, yet automated extraction of structured reaction data from them remains challenging. We introduce RxnExBench, a multimodal benchmark for fine-grained reaction-level evaluation. Built from high-impact chemistry journals, it contains 3,565 expert-annotated reactions and 2,361 molecular structures. The dataset adopts a unified schema...
-
47
PEAR: Adaptive Advantage Reshaping for Perception and Exploration in Large Vision-Language Models
Junxin Wang, Yingfeng Luo, Xiangchen Song, Weiqiao Shan, Runsong Zhao, Xinyu Liu, Shunjie Xing, Yifu Huo, Dingyang...
cs.AI
Effective multimodal reasoning requires a model to reliably utilize visual information while sufficiently exploring diverse reasoning paths. To achieve this goal, prior work combines visual dependency and token entropy to reshape sequence-level advantages, but scaling the contribution of token entropy by visual dependency can leave high-entropy tokens with low visual dependency underweighted, despite their important role in reasoning...
-
48
Watermarking Diffusion Language Models with Learned Foresight and Balanced Bands
Hyojun Kim, Hyeseon An, Yo-Sub Han
cs.AI
Green-red watermarks favor tokens from a green list that a secret key derives from the preceding tokens. Diffusion language models, however, often choose a token before its preceding tokens, and the token later shapes its neighbors' green lists. Prior work therefore tilts each choice to raise the expected number of green tokens at its own and its neighbors' positions. Building on this objective, we first learn two components that prior work...
-
49
SWE-Shift: Evaluating Coding Agents in Evolving Workspaces
Victor Shea-Jay Huang, Rongqing Li, Zhangyue Yin, Kelong Mao, Yaqi Zhao, Xinyuan Wang, Yao Yin, Lirui Luo, Renrui...
cs.AI · cs.CL · cs.LG
Repository-level coding benchmarks largely assume that tasks and environments remain unchanged throughout execution. In software development, code, dependencies, runtime state, and requirements can change while an agent is still working. We introduce SWE-Shift, a benchmark for evaluating coding agents under such mid-execution changes. From the same saved history and workspace, a Clean continuation proceeds without intervention, while a...
-
50
Evidence-Grounded SLM Behavioral Prediction Architecture for Future Assistance Use
Adeyemi Adeseye, Aisvarya Adeseye, Hannu Tenhunen, Jouni Isoaho
cs.AI
Users often exhibit changes in interaction behavior before explicitly seeking assistance, enabling systems to anticipate future assistance use. This is especially important in high-stakes environments, where delayed assistance can have operational, financial, or safety consequences. However, conventional Large Language Models (LLMs) are often unsuitable for continuous on-device behavioral prediction because of their computational and memory...
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.