LLM Agent Training

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

55 papers in the last four weeks, up 150% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 359

All topics

Character Training for Risk-Averse Agents
Sep 29, 2026Arav Dhoot, Punya Syon Pandey, Jamie Johnson +3Risk-Sensitive RL AI Agent Safety
UK AI Security Institute · Resolution
HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents
Sep 29, 2026Tongbo Chen, Junbo Niu, Zhengxi Lu +8Computer-Use Agents GUI Agents
Zhejiang University · Peking University · Tsinghua University
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
Sep 29, 2026Hongjin Qian, Chaofan Li, Kun Luo +11LLM Self-Refinement LLM Agent Training
Beijing Academy of Artificial Intelligence (BAAI)
AnthroDial: Benchmarking LLM Anthropomorphism in Autonomous Social Interaction
Sep 29, 2026Wentao Liu, Xi Chen, Siyu Song +13LLM Agent Evaluation LLM Agent Training
Shanghai Institute of Innovation · University of Science and Technology of China · East China Normal University +9
SkillGym: Training Skill-Use Agents with Automatic Verifiable Environment Generation
Sep 29, 2026Renxi Wang, Mingshan Hee, Fajri Koto +2Supervised Fine-Tuning LLM Agent Skill Learning
Mohamed bin Zayed University of Artificial Intelligence
MLToolBench: Learning Tool-Augmented Agents for Machine Learning Development
Sep 29, 2026Xin Yu, Lizhu Zhang, Jiamu Bai +7LLM Agent Skill Learning AI Agent Benchmarks
Towards Communication-Efficient Social Intelligence in Language Agents
Sep 28, 2026Linxiao Gong, Yijie Xu, Tianfu Wang +7LLM Agents LLM Agent Training
The Hong Kong University of Science and Technology (Guangzhou) · University of Science and Technology of China · The Hong Kong University of Science and Technology
EvoIn: Bridging Evolution and Internalization for Agent Fine-Tuning
Sep 28, 2026Shihan Dou, Shaofan Liu, Zhonghang Lu +8LLM Agent Training Self-Improving Agents
Fudan University · Renmin University of China
Action-Space Shaping for LLM Agents: Measuring and Mitigating Tool-Schema Bias
Sep 28, 2026Yinhong Liu, Zhili Tan, Zilin Wang +1LLM Agent Evaluation LLM Tool Use
University of Cambridge · Yinwang · Huawei +2
Just-In-Time Agent Memory with Runtime Agentic Research
Sep 28, 2026Bingyu Yan, Chaofan Li, Hongjin Qian +3Agent Memory Agentic RAG
Beijing Academy of Artificial Intelligence · Peking University · Hong Kong Polytechnic University
When Successful Strategies Fail: Adaptation to Environmental Novelty in Terminal Agents
Sep 27, 2026Janvijay Singh, Vaishnavi Shrivastava, Dilek Hakkani-Tur +2Long-Horizon Agent Evaluation AI Agent Benchmarks
University of Illinois Urbana-Champaign · Microsoft Research AI Frontiers
Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents
Sep 27, 2026Weiyi Xu, Xiaowen Yang, Wen Da +7Tool-Using Agents LLM Agent Trajectory Synthesis
AllSpark Team
CompoWorld: Compositional Environment Scaling for General Agents
Sep 27, 2026Xiao-Wen Yang, Weiyi Xu, Wen Da +9Tool-Augmented Language Model Agents Tool-Using Agents
AllSpark Team
ParaAgent: Reinforcing Parallel Acting in Open-World Tool Environments
Sep 27, 2026Shengbin Yue, Hongru Wang, Siyuan Wang +3LLM Agent Training Tool Use
Fudan University · University of Edinburgh · Chinese University of Hong Kong +3
SCLATE: a Substrate for Continual-Learning Agent Training and Evaluation
Sep 26, 2026Youngmok Jung, Sirajul Salekin, Henry Tran +3Continual Learning for LLM Agents Long-Horizon Agent Evaluation
Apple
PUBG Ally: A Conversational Embodied Agent as an AI Teammate
Sep 24, 2026Beomsoo Kim, Byeongju Kim, Dohyun Kim +21Game-Playing Agents AI Agent Evaluation
Breaking the Environment Wall: A Unified Framework for Preparing and Evolving Agent-Native Environments
Sep 24, 2026Yukai Wu, Yuanjing Yang, Le Zhou +8LLM Agent Self-Improvement LLM Agent Training
Shanghai Jiao Tong University · Theseus Labs · Tencent Hunyuan
From Self-Distillation to Self-Practice: Privileged Information for Multi-Turn Agents
Sep 24, 2026Xingyu Su, Abhishek Kumar, Qing Ping +5On-Policy Self-Distillation LLM Agent Training
Texas A&M University · AWS AI, Amazon
Forecast-Dojo: Replayable Environments for Benchmarking and Training LLM Forecasting Agents
Sep 24, 2026Liqin Ye, Haorui Wang, Fardin Ahmed +8LLM Agent Evaluation Forecasting Benchmarks
Georgia Institute of Technology · Amazon · University of Florida
The Fellowship of the Query: Learning Retrieval Actions
Sep 23, 2026Mohammed Al-Maamari, Saber Zerhoudi, Michael Granitzer +1LLM Fine-Tuning Agentic RAG
University of Passau Passau, Germany
Agent-Editing World Model: Rethinking World Modeling for LLM Agents
Sep 23, 2026Shuang Sun, Guoxin Chen, Fanzhe Meng +6LLM World Models World Models
Gaoling School of Artificial Intelligence, Renmin University of China
SkillGym: Internalizing Human Skills into LLMs for Real-World Problem Solving
Sep 23, 2026Zhilong Ge, Yuting Shao, Yutao Yang +6Tool-Augmented Language Model Agents LLM Agent Skill Learning
School of Computer Science and Technology, East China Normal University, Shanghai · Shanghai AI Laboratory
Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms
Sep 23, 2026Xinjie Shen, Wei Fan, Xudong Guo +5Agentic RL Reinforcement Learning
Georgia Institute of Technology · Alibaba Token Foundry, Alibaba Group
Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents
Sep 22, 2026Laizhen Li, Jiarui Li, Juanjuan Zhao +4Agent Harness Optimization LLM Agent Workflow Optimization
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Shenzhen University of Advanced Technology +1
The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks
Sep 22, 2026Wenbo Pan, Zhichao Liu, Shujie Liu +6Software Engineering Benchmarks Long-Horizon Agent Evaluation
City University of Hong Kong · Microsoft · Independent Researcher
Harness-Zero: Harness Distillation via Agent-as-Harness
Sep 21, 2026Haoran Ye, Yuxing Lu, Haonan Dong +2LLM Agent Training Knowledge Distillation
State Key Laboratory of General Artificial Intelligence, School of Intelligence Science and Technology, Peking University · College of Future Technology, Peking University · Google +1
Dependency-Aware Trajectory Refinement for Efficient Multi-Turn Agent Fine-Tuning
Sep 16, 2026Zhuo Chen, Zhen Zhang, Xinyu Wang +1LLM Inference Efficiency LLM Agent Workflow Optimization
Shanghai Engineering Research Center of Intelligent Vision and Imaging
SFT or RL for Tool-Calling Agents? A Controlled Study Across Data, Method, and Scale
Sep 15, 2026Md Tahmid Rahman Laskar, Xue-Yong Fu, Shashi Bhushan TNSupervised Fine-Tuning LLM Tool Use
Dialpad Inc.
Atria Dawn: The Dawn of Agentic Superintelligence
Sep 14, 2026Honglin Guo, Tao Gui, Kun Cai +140AI Agents for Scientific Discovery AI Agent Benchmarks
Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work
Sep 14, 2026Wenhui Chen, Shiwen Cheng, Hao Dong +40LLM Agent Training LLM Post-Training

Sep 29, 2026, cs.AIJ/K move · Enter open · S save

Character Training for Risk-Averse Agents

Arav Dhoot, Punya Syon Pandey, Jamie Johnson, Daniel Tan+2

UK AI Security Institute · Resolution

Risk-Sensitive RL AI Agent Safety LLM Agent Training

Open paper AskPDF arXiv

Risk aversion in resources could prevent misaligned AI agents from causing catastrophic harm. Misaligned but risk-averse agents would tend to favor safer strategies like making deals with humans over riskier strategies like rebelling. We train agents to be risk averse through character training, finding that persona traits provide a robust mechanism for instilling risk preferences. To do this, we construct a model constitution describing constant absolute risk aversion (CARA) over an agent's resources and instill it through on-policy distillation. Despite never seeing the benchmark's decision format during training, character-trained models are competitive with baselines trained directly on it, and generalise better than them out of distribution on two of our four models. We also modulate different aspects of the constitution, finding that token budget and model choice are the most influential aspect of character training to instill risk aversion. We conclude from these results that character training is a promising and scalable way to instil broad dispositions, which we can use to our advantage in mitigating risk from misaligned AI agents.

Momentum

Related topics

Latest papers 359