Large language models

Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.

28,264 stories · RSS feed

arXiv Machine Learning

Oct 5

LESSER: Post-Training Data Selection with Output-Layer Gradients

arXiv:2610.03702v1 Announce Type: new Abstract: The choice of post-training data for large language models substantially affects downstream performance. Gradient-based data selection is a popular app...

By Lyuxin David Zhang, Eric Wong, Surbhi Goel, Anton Xue

llms reinforcement-learning fine-tuning benchmarks

arXiv Machine Learning

Oct 5

MiDShip: Multimodal Dataset of Ship Cargo Hold Structures for Engineering Design

arXiv:2610.02214v1 Announce Type: cross Abstract: Ship structures govern vessel strength, safety, and manufacturability, but their design must satisfy hundreds of classification society requirements,...

By Noah J. Bagazinski, Md. Ferdous Alam, Jaya Manideep Rebbagondla, Faez Ahmed

llms multimodal safety

arXiv AI

Oct 5

Securing Computer-Use Agents Against Branch Steering Attacks

arXiv:2610.03089v1 Announce Type: cross Abstract: Modern Computer Use Agents (CUAs) directly interact with graphical user interfaces and execute third-party web tools, exposing them to indirect promp...

By Giulio Zingrillo, Hanna Foerster, Ilia Shumailov, Yiren Zhao, Robert Mullins

llms agents

arXiv AI

Oct 5

Ask, Relax, or Act? Evaluating Actionable Indeterminacy in LLM Preference Reasoning

arXiv:2610.03102v1 Announce Type: cross Abstract: An LLM agent can recognize uncertainty yet still choose the wrong next step: asking when action is already justified, or seeking clarification when t...

By Ang Li, Yue Lin, Feifei Kou, Zhan Su, Prayag Tiwari, Wenhao Li, Shuhui Zhu, Hongyuan Zha, Baoxiang Wang

llms agents benchmarks

arXiv AI

Oct 5

Foresight: planning future perception in streaming VLMs without retraining

arXiv:2610.03123v1 Announce Type: cross Abstract: Existing streaming vision-language models (VLMs) continuously perceive and reason over visual streams, but their computational pathways remain fixed...

By Ashok Prasad Neupane, Dipan Bartaula, Ankit Belbase, Saugat Adhikari, Samip Ghimire, Saroj Poudel, Binod Bhattarai, Danda Pani Paudel

llms efficiency multimodal

arXiv AI

Oct 5

The Fragility of Trigger-Tag Mechanisms for Misuse Detection in Open-Weight LLMs

arXiv:2610.03124v1 Announce Type: cross Abstract: Open-weight language models can be downloaded, modified, and deployed beyond their developers' control, limiting the effectiveness of centrally enfor...

By Toluwani Aremu, Manit Baser, Mohan Gurusamy, Nils Lukas, Dinil Mon Divakaran

llms safety

arXiv AI

Oct 5

EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace Agents

arXiv:2610.03153v1 Announce Type: cross Abstract: Workspace agents combine large language models with execution harnesses to perform stateful, multi-step tasks that access or modify external resource...

By Shiyi Kuang, Xuemei Luo, Kun Liu, Junhai Li, Rui Tian, Feng Shi, Bo Shen, Nianyu Li, Dehui Li, Ping Chen

llms agents multimodal benchmarks safety

arXiv AI

Oct 5

Not Until the Evidence Says So: Teaching LLM Investigators When to Close a Case

arXiv:2610.03190v1 Announce Type: cross Abstract: Accident, defect and outage investigations end with a decision that ordinary question answering never faces: whether the evidence gathered so far is...

By Tingzhu Bi, Ping Wang, Meng Ma

llms nlp reinforcement-learning fine-tuning safety

arXiv AI

Oct 5

DeReAct: Decomposed Reasoning and Acting for Reliable AI Agents

arXiv:2610.02351v1 Announce Type: new Abstract: ReAct-based agents typically rely on a single LLM policy to propose actions, interact with the environment, and decide when a task is complete. This co...

By Ajay Vohra, Tao Chen, Neeti Narayan, Caron Zhang

llms agents benchmarks

arXiv AI

Oct 5

Open-Endedness Bench: Measuring Epistemic Process from Agent Records

arXiv:2610.02588v1 Announce Type: new Abstract: Agents are increasingly given open-ended research tasks: discovering an empirical law from self-designed experiments, improving a heuristic whose optim...

By Chengyang Shi, Xianglin Ji, Jintao Huang, Jicheng Wang, Yifeng He, Jiachen Liu

llms agents benchmarks

arXiv Machine Learning

Oct 5

Generalization of Transformer-Based Neural Quantum States via In-Context Learning

arXiv:2610.03463v1 Announce Type: cross Abstract: Neural quantum states based on modern deep learning architectures have emerged as powerful representations for quantum many-body systems. In particul...

By Zhen Qin, Qing Qu, Alfred O. Hero III

llms

arXiv Machine Learning

Oct 5

FALCON: A Model and Dataset Agnostic Framework for Synthetic Data Generation for NL2SQL Pairs

arXiv:2610.03625v1 Announce Type: cross Abstract: Relational databases are among the most widely deployed forms of structured knowledge, and natural language access to them requires grounding languag...

By Darian Lee, Shannon Rumsey, Jack St. Clair, Xinyi Tang, Aditya Bansal, Yuanming Shi

llms benchmarks safety data-engineering

arXiv AI

Oct 5

Batched Speech Decisions Without Decoding: Single-Token Supervision Lets a Frozen LLM Hear Beyond the Transcript

arXiv:2610.02638v1 Announce Type: new Abstract: Full-duplex voice agents make many small, closed decisions, which current systems answer by slow autoregressive decoding. We propose DuplexJev, which f...

By Jie Jin, Ziyin Ma, Min Yin, Jinyu Chen, Haigang Song, Zhikun Pang, Xiaowen Zhang

llms agents efficiency multimodal

arXiv AI

Oct 5

A GHOST in Long-Horizon Agents: Governance Hazard from Overlooked Safety Constraints across Turns

arXiv:2610.02664v1 Announce Type: new Abstract: Long-horizon agents are now playing an increasingly significant role in assisting humans with complex problem-solving. However, it is exactly their ext...

By XinPeng Shen, Lan Zhang, Yixiao Huang, Haoran Cheng, Jiewei Lai, Leilei Chen, Haoxiang Deng

llms agents safety

arXiv AI

Oct 5

DataWeave: Deploying Human-LLM Analytics for Exploratory Structured Data Analysis

arXiv:2610.02679v1 Announce Type: new Abstract: Data journalism, the practice of using data analysis to surface newsworthy stories, depends increasingly on the ability of reporters and investigative...

By Raquib Bin Yousuf, Harith Laxman, Vitaliy Shkremetko, Eunice Son, Shambhavi Verma, Brian O'Leary, Venketesh Subramony, Sylvain Nazef, Jacquelyn Elias, Ron Coddington, Chris Contakes, Michael Riley, Naren Ramakrishnan

llms agents data-engineering

arXiv AI

Oct 5

Learning to Revise Reasoning with Segment-wise On-Policy Distillation

arXiv:2610.02703v1 Announce Type: new Abstract: On-policy distillation (OPD) improves large language model reasoning by training students on their own rollouts with dense token-wise supervision from...

By Yuxiang Zhang, Ding Cao, Shuting Cui, Lei Wang, Weijieying Ren, Tianxiang Zhao

llms efficiency benchmarks

arXiv AI

Oct 5

Law And Order: Tax Law Autoformalization

arXiv:2610.02792v1 Announce Type: new Abstract: Legal systems are increasingly implemented through software, yet scalable methods for translating legal texts into accurate symbolic representations re...

By Sophia Simeng Han, Yoshiki Takashima, Anjiang Wei, Zhaoyu Li, Michael Genesereth

llms

arXiv AI

Oct 5

Are you Synthesizing or Recalling? Evaluating LLMs on Algorithmic Code Retrieval

arXiv:2610.02438v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong performance in code generation, where success depends on both recalling relevant algorithmic kn...

By Nickil Maveli, Antonio Vergari, Shay B. Cohen

llms fine-tuning benchmarks

arXiv AI

Oct 5

FinDialogLens: Event Extraction over Multi-Party Dialogue for Missed-Trade Identification in Financial Chatrooms

arXiv:2610.02455v1 Announce Type: cross Abstract: Multi-party financial chatrooms are vital for sales-and-trading professionals, but their complexity makes manual recovery of missed trades infeasible...

By Chin-Lun Fu, Hong Ni, Behrouz Madahian

llms fine-tuning

arXiv AI

Oct 5

From Fragments to Global Maps: Learning Vectorized Map Aggregation with Large Language Models

arXiv:2610.02513v1 Announce Type: cross Abstract: Large-scale vectorized HD maps provide structured road information that is essential for perception, localization, and planning in autonomous driving...

By Ziwei Li, Yi-Tang Chen, Xiaoqi Wang, Wenbin He, Han-Wei Shen, Liu Ren

llms agents nlp robotics

Get the daily briefing