Large language models

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

30,670 stories · RSS feed

arXiv AI

Jun 10

PreAct-Bench: Benchmarking Predictive Monitoring in LLMs

arXiv:2606. 09890v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents capable of executing multi-step action trajectories toward a given objective.

By Hainiu Xu, Italo Luis da Silva, Jiangnan Ye, Yuhao Wang, Wei Liu, Linyi Yang, Jonathan Richard Schwarz, Nicola Paoletti, Yulan He, Hanqi Yan

llms agents benchmarks safety

arXiv AI

Jun 10

Supervised Fine-tuning with Synthetic Rationale Data Hurts Real-World Disease Prediction

arXiv:2606. 10279v1 Announce Type: new Abstract: Supervised fine-tuning with synthetic rationale data is widely assumed to improve language model performance on clinical prediction tasks by teaching models not just what to predict but why.

By Buxin Su, Bingxuan Li, Cheng Qian, Yiwei Wang, Jin Jin, Bingxin Zhao

llms fine-tuning

arXiv AI

Jun 10

A Unified Multi-Modal Framework for Intelligent Financial Systems: Integrating Reinforcement Learning, High-Frequency Trading, and Game-Theoretic Approaches with Cross-Modal Sentiment Analysis

arXiv:2606. 10412v1 Announce Type: new Abstract: The rapid evolution of financial technology demands sophisticated artificial intelligence systems capable of handling diverse challenges across multiple domains simultaneously.

By Fanrong Liu, Zhang Yuwei, Mingni Luo

llms rag nlp reinforcement-learning multimodal benchmarks

arXiv AI

Jun 10

Structure from Reasoning, Numbers from Search: On-Premise Open LLMs as Structural Priors for Coupled MIMO Controller Tuning

arXiv:2606. 11015v1 Announce Type: new Abstract: Tuning controllers for strongly coupled multi-input multi-output (MIMO) industrial processes is hard: decentralized classical auto-tuning ignores loop interaction, and local numerical optimization from natural initializations stalls in the resulting non-convex cost landscape.

By Jiaxuan Chen, Haonan Li, Yang Shu

llms benchmarks safety

arXiv AI

Jun 10

A complementary study on PlanGPT: Evaluation with defined Performance Metrics and comparison with a planner

arXiv:2606. 10489v1 Announce Type: new Abstract: Automated Planning is a subfield of Artificial Intelligence (AI) where the main objective is generating a sequence of actions, known as a plan, that helps us reach a goal state from an initial state.

By Youssef Abdelkader, Humbert Fiorino, Damien Pellier

llms benchmarks

arXiv AI

Jun 10

Interpreting and Steering a Text-to-Speech Language Model with Sparse Autoencoders

arXiv:2606. 10029v1 Announce Type: cross Abstract: Language models increasingly serve as the backbone of text-to-speech (TTS) systems, yet we understand little about the representations they build when text and generated speech tokens share a single residual stream.

By Nikita Koriagin, Georgii Aparin, Nikita Balagansky, Daniil Gavrilov

llms diffusion multimodal safety

arXiv AI

Jun 10

Reasoning or Memorization? Direction-Aware Diversity Exploration in LLM Reinforcement Learning

arXiv:2606. 10346v1 Announce Type: new Abstract: Reinforcement learning has become a key paradigm for eliciting reasoning abilities in large language models, where exploration is crucial for discovering effective solution trajectories.

By Jiangnan Xia, Yucheng Shi, Yu Yang, Kishan Panaganti, Zhenwen Liang, Ninghao Liu

llms reinforcement-learning benchmarks

arXiv AI

Jun 10

Structure-Preserving Learning Improves Geometry Generalization in Neural PDEs

arXiv:2602. 02788v2 Announce Type: replace-cross Abstract: We aim to develop physics foundation models for science and engineering that provide real-time solutions to Partial Differential Equations (PDEs) which preserve structure and accuracy under adaptation to unseen geometries.

By Benjamin D. Shaffer, Shawn Koohy, Brooks Kinch, M. Ani Hsieh, Nathaniel Trask

llms benchmarks safety

arXiv AI

Jun 10

Designed by Journalists, but Is It for Readers? Rethinking AI Disclosures and Transparency in News

arXiv:2606. 11116v1 Announce Type: cross Abstract: As newsrooms integrate generative AI, journalists face a disclosure challenge: how to communicate AI involvement in ways that maintain reader trust.

By Pooja Prajod

llms

arXiv AI

Jun 10

Soul Computing: A Theoretical Framework and Technical Architecture for Intelligent Agents with Independent Consciousness

arXiv:2606. 10413v1 Announce Type: new Abstract: Breakthroughs in large language models and multimodal generation technologies have propelled the digital reconstruction of human mental traits, emotional patterns, and long-term memory from science fiction toward engineering practice.

By Jinshan Zhang, Xishi Zhou, Qiu Peng, Jianwei Yin

llms agents multimodal

arXiv AI

Jun 10

Less Context, Better Agents: Efficient Context Engineering for Long-Horizon Tool-Using LLM Agents

arXiv:2606. 10209v1 Announce Type: new Abstract: Large language models deployed as autonomous agents for enterprise workflows face a key challenge: verbose tool responses from enterprise systems can cause context overflow, stale-state errors, and high inference cost.

By Abhilasha Lodha, Mahsa Pahlavikhah Varnosfaderani, Abir Chakraborty, Abhinav Mithal

llms agents nlp efficiency benchmarks

arXiv AI

Jun 10

Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models

arXiv:2606. 10829v1 Announce Type: cross Abstract: Masked diffusion language models can reduce inference steps by revealing multiple tokens per denoising iteration, but this parallelism is fragile: positions that are individually confident may be unsafe to commit together when their predictions are coupled.

By Yusuf Sahin, Ahmed Rockey Saikia, Volkan Cevher, Paolo Favaro

llms rag diffusion benchmarks

arXiv AI

Jun 10

PhantomBench: Benchmarking the Non-existential Threat of Language Models

arXiv:2606. 11105v1 Announce Type: cross Abstract: Hallucinations, where language models (LMs) generate factually ungrounded responses, pose serious risks, as users tend to blindly rely on them.

By Haeji Jung, Hila Gonen

llms benchmarks safety

arXiv AI

Jun 10

One Lens, Many Worlds : A Capability-Typed Interface for World-Model Interpretability

arXiv:2606. 09936v1 Announce Type: cross Abstract: World models are now built on substantially different computational substrates.

By Bhavith Chandra Challagundla, Sanskar Pandey, Param Thakkar, Rishikesh Mallagundla, Yugandhar Reddy Gogireddy, Wenhao Lu, Hindol Roy Choudhury, Shravani Challagundla, Mohamed Deraz Nasr, Spursh Deshpande

llms rag diffusion safety

arXiv AI

Jun 10

IntentKV: Cross-Turn Intent-Aware KV Cache Pruning for Agent Inference

arXiv:2606. 09916v1 Announce Type: cross Abstract: Multi-turn LLM agents fan short queries into long trajectories of tool calls, search results, and intermediate reasoning.

By Junjie Li, Jiong Lou, Jie Li

llms agents efficiency

arXiv AI

Jun 10

Sample Where You Struggle: Sharpening Base Model Reasoning via Entropy-Guided Power Sampling

arXiv:2606. 09926v1 Announce Type: cross Abstract: Sampling from the sequence-level power distribution $p^\alpha$ elicits RL-level reasoning from base language models without any parameter updates, but the standard Metropolis--Hastings (MH), a Markov Chain Monte Carlo (MCMC) sampler, is both expensive and slow-mixing.

By Hong Guo, Nianhui Guo, Christoph Meinel, Haojin Yang

llms reinforcement-learning benchmarks

arXiv AI

Jun 10

What makes a harness a harness: necessary and sufficient conditions for an agent harness

arXiv:2606. 10106v1 Announce Type: cross Abstract: The term agent harness now circulates widely in software engineering with generative artificial intelligence.

By Sanderson Oliveira de Macedo

llms agents benchmarks

arXiv AI

Jun 10

Baseline-Free Policy Optimization for Neural Combinatorial Optimization

arXiv:2606. 10321v1 Announce Type: cross Abstract: Neural combinatorial optimization (NCO) trains autoregressive policies to solve routing problems.

By Carlos S. Sep\'ulveda, Gonzalo A. Ruz

llms reinforcement-learning benchmarks safety

arXiv AI

Jun 10

Position: The ML Community Must Build an AI-Augmented Peer-Review Ecosystem

arXiv:2506. 08134v4 Announce Type: replace Abstract: Peer review, the bedrock of scientific advancement in machine learning (ML), is strained by a crisis of scale.

By Qiyao Wei, Samuel Holt, Jing Yang, Markus Wulfmeier, Mihaela van der Schaar

llms

arXiv AI

Jun 10

AMEL: Accumulated Message Effects on LLM Judgments

arXiv:2605. 22714v3 Announce Type: replace Abstract: Large language models are routinely used as automated evaluators: to review code, moderate content, or score outputs, often with many items passing through one conversation.

By Sid-Ali Temkit

llms safety

Get the daily briefing