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

Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training
Sep 9, 2026Junwon Ko, Dong-Jae Lee, Minchan Kwon +2Offline RL Preference Optimization
School of Electrical Engineering, KAIST Daejeon, Republic of Korea
Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails
Sep 8, 2026Zhou Yu, Bin Bi, Shiva Kumar Pentyala +8Agent Harness Optimization Imitation Learning
Salesforce AI
Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models
Sep 8, 2026Zongjie Li, Alan Z. W, John Nicolas J +4Training Data Curation Cybersecurity
Vera Praxis Lab
Miles v0.1: Production-Level Post-Training
Sep 8, 2026RadixArk, :, Tom Chen +11Reinforcement Learning LLM Agent Training
RadixArk
Train What You Deploy:Token-Faithful Post-Training of a Production Coding
Sep 7, 2026Cheng Li, Jiexiong Liu, Yixuan Chen +1RL for Code Generation Proximal Policy Optimization
KunlunMeta
MARBO: Relational Belief Grounding for LLM Agents in Social Deduction Games
Sep 6, 2026Yechan Hwang, Sangjun Bae, Jeongmo Kim +2Game-Playing Agents Social Deduction Games
Graduate School of Artificial Intelligence, UNIST, Ulsan, South Korea.
First Things First: Teaching LLM-Based Agents to Prioritize Must-Haves before Nice-to-Haves
Sep 4, 2026Tianjie Ju, Xinyue Xu, Wanxuan Sun +4RL for Language Model Reasoning AI Agent Benchmarks
School of Computer Science, Shanghai Jiao Tong University · ByteDance
Iris: Climbing to the Search Frontier
Sep 3, 2026Ziyuan Liu, Hengqi Liu, Zichuan Wang +8Multi-Hop QA Web Search Agents
AllSpark Team
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
Sep 3, 2026Jie Wu, Zhenru Zhang, Beichen Zhang +11Software Engineering Agents LLM Agent Trajectory Synthesis
1Qwen Team, Alibaba Group · 2Tsinghua University
PersuaRL: Reinforcement Learning-Driven Multi-Expert Selection for Persuasive Dialogue Generation in Insurance
Sep 1, 2026Rohan Kirti, Akash Ghosh, Aryan Vats +5RL for Language Models LLM Agent Training
Indian Institute of Technology Patna, India · Ramakrishna Mission Vivekananda Educational and Research Institute, India · Accenture Labs, Bangalore, India
MemoryWalker: Stop Training Agents on Contexts They Never Saw
Sep 1, 2026Zinco J, Xunjie Zhu, Shen Huang +3Tool-Augmented Language Model Agents Consistency Distillation
Token Foundry, Alibaba Group
WHALE: A Simple Recipe for Joint Harness-Weight Optimization
Aug 31, 2026Haechan Kim, Yoonho Lee, Gisang Lee +2Agent Harness Optimization LLM Agent Training
KRAFTON · KAIST · Stanford University
From Final Artifacts to Trajectories: Retrospective Process Supervision for Evidence-Grounded Long-Form Generation
Aug 31, 2026Junjie Huang, Jiarui Qin, Di Yin +4LLM Agent Trajectory Synthesis Process Supervision
Shanghai Jiao Tong University · Tencent Youtu Lab
SimCRAFT: Distilling Remote Sensing Agents via Synthetic Trajectories and Contextual Retrieval-Augmented Fine-Tuning
Aug 31, 2026Haoran Wang, Jing Yao, Xu Yang +4Fine-Tuning Remote Sensing
State Key Laboratory of Remote Sensing and Digital Earth, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, China · University of Chinese Academy of Sciences, Beijing 100049, China · The Hong Kong University of Science and Technology (Guangzhou), Guangzhou 511453, China +1
CAST: Critique-Aware Supervision for Training Reliable Long-Horizon Tool-Calling Agents
Aug 31, 2026Amir Saeidi, Zehua Zhang, Rishitosh Singh +6LLM Agents LLM Agent Training
Arizona State University · Cisco Research
Beyond Task Completion: Training Capable and Safe Computer-Use Agents
Aug 27, 2026Zeyu Kang, Zhenyun Yin, Yang Zhang +5Computer-Use Agents AI Agent Safety
Shanghai Artificial Intelligence Laboratory · Harbin Institute of Technology · Fudan University +2
JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution
Aug 26, 2026Guibin Zhang, Leo Lu, Fangzhou Xie +15Tool-Augmented Language Model Agents Agent Harness Optimization
JIT-Agent Team
CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild
Aug 24, 2026Jian Yang, Haau-Sing Li, Shawn Guo +10Cybersecurity Software Security
Beihang University · ELLIS · IQuest Research +1
Competing at Every Price Point with Agentic Evolution over a Menu of LLMs
Aug 17, 2026Andrew BorthwickLLM Agents LLM Agent Training
Independent Researcher
Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report
Aug 16, 2026TaoLive AIGC LLM Team, Yuhan Sun, Wenhao Lin +7LLM Agent Training LLM Agent Harnesses
TaoLive AIGC LLM Team
Training AI Scientists to Replicate Research
Aug 13, 2026Damon Falck, Samer Sabri, Anja Surina +8AI Agents for Scientific Discovery AI Agent Benchmarks
1Inherent
One Frozen Simulator Is Not Enough: Simulator Collapse in Multi-Agent RL
Aug 12, 2026Simon Yu, Nicholas Tomlin, Marwa Abdulhai +7Multi-Agent LLM Systems Human Behavior Simulation
1Northeastern University · 2New York University · 3UC Berkeley +2
ExRole: From Team Trajectories to Executable Roles in Multi-Agent Language Models
Aug 12, 2026Zhou Liu, Chaoyang Han, Zewei Pan +2LLM Agent Training Multi-Agent LLMs
Peking University · Shanghai Jiao Tong University
From Numbers to Judgment: Specialist LLM Agents and Reinforcement Learning for European Listed Real Estate
Aug 11, 2026Pardis Taghavi, Santosh BhavaniNumerical Reasoning in Language Models Multi-Agent LLM Systems
Santosh Bhavani∗
MERA: Model Evolution and Routing with Skill Adaptation for Agentic Systems at Scale
Aug 11, 2026Yuhang Yao, Zeyu Wang, Wanyi Chen +8Continual Learning for LLM Agents LLM Fine-Tuning
Carnegie Mellon University · University of California, Los Angeles · Soochow University +3
Open Evaluation Agent: Efficient and Promptable Evaluation of Visual Generative Models
Aug 10, 2026Shulin Tian, Ziqi Huang, Fan Zhang +3Tool-Augmented Language Model Agents AI Agent Evaluation
Shanghai Artificial Intelligence Laboratory
Beyond the Capability Boundary: Zeroth-Order Optimization for Self-Evolving LLM Agents
Aug 10, 2026Bingzhen Liu, Xiaomeng Fan, Yuwei Wu +4Zeroth-Order Optimization LLM Agent Training
Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science & Technology, Beijing Institute of Technology · Guangdong Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University · Alaya Lab
Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing
Aug 7, 2026Jiacheng Miao, Jin Mu, Guanhua Chen +1AI Agent Benchmarks LLM Agent Training
Department of Biomedical Data Science, Stanford University · Department of Genetics, Stanford University · Department of Biostatistics and Medical Informatics, University of Wisconsin–Madison +3
CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training
Aug 6, 2026Amine Lbath, Manan Suri, Aurelien Delaitre +4Automated Program Repair Software Vulnerability Detection
National Institute of Standards and Technology · Université Grenoble Alpes, CNRS · University of Maryland, College Park
CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks
Aug 6, 2026Fanzhe Meng, Guoxin Chen, Jiale Zhao +6LLM Agent Training Agent Benchmarks
1Gaoling School of Artificial Intelligence, Renmin University of China · 2Independent Researcher · 3AweAI Team

Sep 9, 2026, cs.CLJ/K move · Enter open · S save

Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training

Junwon Ko, Dong-Jae Lee, Minchan Kwon, Sunghyun Baek+1

School of Electrical Engineering, KAIST Daejeon, Republic of Korea

Offline RL Preference Optimization LLM Agent Training RL Post-Training

Open paper AskPDF arXiv

LLM agents for sequential decision tasks are often post-trained with trajectory-level outcome labels, but such labels provide little supervision for preserving multiple successful branches from the same decision state. We study this problem as successful strategy coverage: how broadly a model realizes distinct successful strategies under a fixed rollout budget. We present Direct Diversity Optimization (DDO), an offline post-training method that combines Divergence-Tree Collection (DTC) with the Reference-Relative Target-Odds Objective (RTO). DTC constructs state-aligned branch sets rooted at shared decision states, and RTO trains the model to match reference-relative targets over successful alternatives. DDO achieves the strongest task success and successful strategy coverage among the compared post-training methods across BabyAI, BabaIsAI, and WebShop. It also achieves the highest recovery rate after local action replacement and higher task success and coverage than successful-only imitation and decoding-time diversification controls.

Momentum

Related topics

Latest papers 354