LLM Agent Training

LLM: Large Language Model

Follow this topic Ask about this topic

Momentum

54 papers in the last four weeks, up 145% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28

Latest papers 354

All topics

Environmental Feedback Modeling Matters: Rethinking Feedback Treatment in Agentic Hindsight Self-Distillation
Oct 8, 2026Hangxi Guo, Fengyuan Liu, Yue Wang +4LLM Agent Training Self-Distillation
The Chinese University of Hong Kong, Shenzhen · Shanghai AI Laboratory · University of Science and Technology of China +2
StoreBench: A Live-Commerce Environment for Evaluating and Training Autonomous Operator Agents
Oct 7, 2026Daksh Raghuvanshi, Ved Vedere, Yifan WangAI Agent Benchmarks Long-Horizon LLM Agents
AfterQuery
SOTA: Stock Options Trading Agents Guided by Option-Implied Return Distributions
Oct 7, 2026Yizhen Xie, Mengyang LiuAlgorithmic Trading Quantitative Finance
Carnegie Mellon University · Amazon
Training Advisors for LLM Agents from Task Outcomes
Oct 7, 2026Sergei Polezhaev, Barys Liskavets, Ori Press +1LLM Agent Training RL for LLM Agents
Nebius AI
MIMESIS: Learning User Simulators as Training Environments for Interactive Agents
Oct 7, 2026Hoang Phan, Dat Huynh, Andrey Zhmoginov +7User Simulation LLM Agent Training
Meta Superintelligence Labs · New York University · University of Wisconsin - Madison
Verify Less, Evolve More: Training Idea-Level Critics for Verification-Efficient ML Evolving Agents
Oct 6, 2026Jiamu Bai, Lizhu Zhang, Xin Yu +9LLM Agent Training
Penn State University · Meta
GraphOPD: Graph-Augmented On-Policy Distillation for LLM Agents
Oct 6, 2026Bohan Lin, Liyi Chen, Zhuoning Guo +5LLM Agent Training On-Policy Distillation
University of Science and Technology of China · Xiaohongshu · The Hong Kong University of Science and Technology (HKUST-GZ)
AdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World Model
Oct 6, 2026Sarim Hashmi, Mukul Ranjan, Kshitij Mishra +3Adversarial Training Sim-to-Real Transfer
Mohamed bin Zayed University of Artificial Intelligence · Amazon · Massachusetts Institute of Technology
RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents
Oct 5, 2026Mohamed Dhouib, Clement Elliker, Alexi Canesse +5Prompt Injection Defense LLM Agents
LIX, École polytechnique, Institut Polytechnique de Paris, CNRS · AMIAD (Agence Ministérielle pour l’IA de Défense) · IRT SystemX +1
Imagine to Act: High-Fidelity Data Synthesis via Image Editing World Model for Scalable GUI Agent Training
Oct 5, 2026Yongxin Ning, Runliang Niu, Qianli Xing +4World Models Synthetic Data Generation
School of Artificial Intelligence, Jilin University · College of Computer Science, Jilin University · OPPO
Selecting Long-Horizon Trajectories for Reliable and Efficient Terminal-Agent Training
Oct 5, 2026Cuong Dang, Hoang Anh Just, Ruoxi JiaSupervised Fine-Tuning Trajectory Generation
Department of Electrical and Computer Engineering Virginia Tech Blacksburg, VA, USA
Sibyl: An Efficient Small-large Model Collaboration Framework for Long-horizon Tasks
Oct 4, 2026Zhewei Fang, Yuxin Zhang, Zhenwei Shao +8LLM Agent Training Long-Horizon LLM Agents
Hangzhou Dianzi University · Fudan University · The Hong Kong University of Science and Technology +3
ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience
Oct 4, 2026Haodong Lu, Dong GongContinual Learning for LLM Agents Test-Time Training
University of New South Wales (UNSW Sydney)
Harness Annealing: Learning to Act with Less External Control
Oct 1, 2026Yingxuan Yang, Huacan Chai, Ying WenLanguage Model-Based Control Agent Harness Optimization
Shanghai Jiao Tong University · University of California, Berkeley
Federated Agent Optimization
Oct 1, 2026Qiang Yang, Zhiqiang Kou, Xueyi Zhang +6LLM Agent Training Federated Learning
The Hong Kong Polytechnic University, Hong Kong SAR, China · National University of Singapore, Singapore · The University of Tokyo, Japan +2
It Takes Workflows to Evolve Better Workflows
Oct 1, 2026Xuehang Guo, Haoyu Wang, Haifeng Chen +3LLM Agent Workflow Optimization Multi-Agent Collaboration
William & Mary · NEC Corporation of America · University of Illinois Urbana-Champaign
PG-SFT: Balancing Capability Acquisition and Retention in Offline Agent Fine-Tuning
Oct 1, 2026Ronghua Li, Zi Liang, Zhishan Li +1Supervised Fine-Tuning LLM Agent Training
The University of Hong Kong · The Hong Kong Polytechnic University · Independent Researcher
PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents
Sep 30, 2026Yinghui He, Yapei Chang, Khushi Bhardwaj +4Language Model Distillation LLM Agent Training
Princeton University · NVIDIA · University of Maryland
ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents
Sep 30, 2026Yong Du, Tongbo Chen, Zhengxi Lu +5On-Policy Self-Distillation Computer-Use Agents
Zhejiang University · Ant Group
PhantomEnvironments: Training LLM Agents in Fictional Worlds
Sep 30, 2026Anmol Kabra, Swathi Saravana Selvam, Albert Gong +5Multi-Hop QA Reinforcement Learning
Cornell University · Stanford University
Agent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training
Sep 30, 2026Kunlun Zhu, Xuyan Ye, Yibo Li +3Agent Failure Analysis LLM Agent Training
Apodex
Learning Reliable GUI Agents under Imperfect Priors
Sep 30, 2026Bo Han, Qianyi Wang, Shuai Liu +9GUI Agents LLM Agent Training
Xi’an Jiaotong University · MiLM Plus, Xiaomi Inc.
WorkGenesis: Building the Worlds That Teach Agents to Work
Sep 30, 2026Xinyu Zhu, Fenyi Liu, Yuzhu Cai +4LLM Agent Training Synthetic Data Generation for Language Models
Shanghai Jiao Tong University · Endless Frontier · Beihang University
GraphForge: Training Working Agents with Graph-Anchored Workspace Synthesis
Sep 30, 2026Qisheng Su, Hanchen Wang, Guanru Zhu +10AI Agent Benchmarks LLM Agent Training
University of Science and Technology of China · Shanghai Innovation Institute · Fudan University +1
Explicit Trajectory Diversity for RL-Based Post-Training of LLM Agents
Sep 30, 2026Huaiyu Fu, Heng Cao, Hao Wang +2LLM Agent Training RL Post-Training
Microsoft
GraphCert: Bootstrap Agentic Graph Reasoning with Certified Evidence Rubrics
Sep 30, 2026Weiqi Jiang, Yuchen Ying, Rui Wang +5LLM Reasoning with Graphs RL for Language Model Reasoning
Zhejiang University, Hangzhou, China · Nanyang Technological University, Singapore · Hangzhou City University, Hangzhou, China
EVOKE: Eliciting World Knowledge in Agents for Transferable Decision-Making
Sep 29, 2026Yuhan Guo, Jinming Liu, Liang Xu +8LLM Agent Training Generalization in RL
Shanghai Jiaotong University · Eastern Institute of Technology, Ningbo · Zhongguancun Academy, Beijing, China +1
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)

Oct 8, 2026, cs.AIJ/K move · Enter open · S save

Environmental Feedback Modeling Matters: Rethinking Feedback Treatment in Agentic Hindsight Self-Distillation

Hangxi Guo, Fengyuan Liu, Yue Wang, Yuhua Qi+3

The Chinese University of Hong Kong, Shenzhen · Shanghai AI Laboratory · University of Science and Technology of China+2

LLM Agent Training Self-Distillation Self-Training for Language Models

Open paper AskPDF arXiv

Reinforcement learning is commonly used to train language agents in interactive environments, but cannot be directly applied when rewards are unavailable. Recent methods use environmental feedback as privileged context for hindsight self-distillation, but our analysis suggests that simply conditioning the teacher on feedback is insufficient, motivating us to rethink how environmental feedback is used in agentic self-distillation. Given that environmental feedback contains rich supervision for modeling how the environment responds to agent actions, we introduce \textit{agentic SElf-distilLation with environmental Feedback modeling} (SELF), a framework that jointly optimizes environmental feedback modeling and hindsight self-distillation. SELF learns to predict environmental responses while distilling guidance from a feedback-conditioned self-teacher into the policy. Our analysis reveals a mutually reinforcing mechanism: environmental feedback modeling strengthens hindsight supervision and policy learning, while self-distillation enhances the model's ability to model environmental feedback. With Qwen3-8B, SELF outperforms SDPO and GRPO by 6.4 and 4.1 percentage points in

τ

-bench success rate, and by 10.71 and 3.57 percentage points in AppWorld task goal completion, respectively. These results show that SELF uses environmental feedback more effectively within agentic self-distillation, improving agent capabilities.

Momentum

Related topics

Latest papers 354