LLM Agent Training

LLM: Large Language Model

LLM agent training studies how to make language models act reliably over multiple steps, using tools, software, websites, or simulated worlds to complete tasks. Common approaches combine supervised fine-tuning on interaction traces with reinforcement learning from execution-verified outcomes, alongside distillation, preference learning, and feedback on individual steps. Researchers build executable environments and benchmarks such as SWE-bench, WebArena, Terminal-Bench, and τ²-Bench to provide repeatable practice and test tool use, coding, search, and long-horizon workflows. A central challenge is transferring gains beyond training environments while balancing task success with efficiency, safety, and robustness to changing tools and users.

Latest papers

590 papers130 papers in the last four weeks, up 132% on the four weeks before. 0.8% of all new papers.

HydroAgent: Closing the Gap Between Frontier LLMs and Human Experts in Hydrologic Model Calibration via Simulator-Grounded RL
May 18, 2026Zhi Li, Songkun Yan, Jie Cao +4Reinforcement Learning Model Calibration
Civil, Environmental, and Architectural Engineering, University of Colorado Boulder · Civil Engineering and Environmental Sciences, University of Oklahoma · Department of Computer Science, University of Oklahoma +3
Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs
May 17, 2026Yuxuan Lu, Ziyi Wang, Yingzhou Lu +12Tool-Augmented Language Model Agents Synthetic Data Generation
Northeastern University · Independent Researcher
OProver: A Unified Framework for Agentic Formal Theorem Proving
May 17, 2026David Ma, Kaijing Ma, Shawn Guo +7Automated Theorem Proving Lean Theorem Proving
M-A-P
FORGE: Self-Evolving Agent Memory With No Weight Updates via Population Broadcast
May 15, 2026Igor Bogdanov, Chung-Horng Lung, Thomas Kunz +3LLM Agent Memory LLM Agent Self-Improvement
Carleton University Ottawa, Ontario, Canada · Defence R&D Canada Ottawa, Ontario, Canada · Cistel Technology Ottawa, Ontario, Canada
Look Before You Leap: Autonomous Exploration for LLM Agents
May 15, 2026Ziang Ye, Wentao Shi, Yuxin Liu +6RL Exploration LLM Agents
University of Science and Technology of China · Meituan
AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs
May 15, 2026Haizhong Zheng, Yizhuo Di, Jiahui Wang +7Agentic RL Reinforcement Learning
1Carnegie Mellon University · University of Michigan · 3UC Berkeley +1
Orchard: An Open-Source Agentic Modeling Framework
May 14, 2026Baolin Peng, Wenlin Yao, Qianhui Wu +11AI Coding Agents Computer-Use Agents
Microsoft Research · Columbia University · UIUC
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining
May 14, 2026Weimin Xiong, Shuhao Gu, Bowen Ye +5GUI Agents LLM Agent Training
National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University
Agentifying Patient Dynamics within LLMs through Interacting with Clinical World Model
May 14, 2026Minghao Wu, Yuting Yan, Zhenyang Cai +9Agentic RL Clinical Decision Support
The Chinese University of Hong Kong, Shenzhen · Beijing Hospital
Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR)
May 13, 2026Marius S. Knorr, Robert Müller, Jan P. Bremer +1Healthcare RL for Language Model Reasoning
IDM gGmbH, University Medical Center Hamburg-Eppendorf, Hamburg, Germany · Aganthos
Speculative Interaction Agents: Building Real-Time Agents with Asynchronous I/O and Speculative Tool Calling
May 13, 2026Coleman Hooper, Minwoo Kang, Suhong Moon +7Tool-Using Agents LLM Agents
University of California, Berkeley · ICSI · LBNL
MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning
May 13, 2026Yuxin Liu, Ziang Ye, Yueqing Sun +6LLM Agent Training Long-Horizon LLM Agents
University of Science and Technology of China · Meituan · Institution of Automation, Chinese Academy of Sciences +1
Revisiting DAgger in the Era of LLM-Agents
May 13, 2026Changhao Li, Rushi Qiang, Jiawei Huang +4Software Engineering Agents Dataset Aggregation
1Georgia Institute of Technology · 2ETH Zurich
Beyond Cooperative Simulators: Generating Realistic User Personas for Robust Evaluation of LLM Agents
May 13, 2026Harshita Chopra, Kshitish Ghate, Aylin Caliskan +3Human Behavior Simulation LLM Agent Evaluation
University of Washington, Seattle · Georgetown University, Washington DC
Learning Agentic Policy from Action Guidance
May 12, 2026Yuxiang Ji, Zengbin Wang, Yong Wang +6Agentic RL Reinforcement Learning
1Xiamen University · 2AMAP, Alibaba Group · Work done during internship at AMAP, Alibaba Group +1
AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration - Learning from Cheap, Optimizing Expensive
May 12, 2026Taicheng Guo, Nitesh V. Chawla, Olaf Wiest +1Multi-Fidelity Optimization Large Language Model-Guided Optimization
University of Notre Dame
Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents
May 11, 2026Shijue Huang, Hangyu Guo, Guanting Dong +8Multimodal IR Tool-Using Vision-Language Agents
Hong Kong University of Science and Technology · Renmin University of China · The Chinese University of Hong Kong +3
Step Rejection Fine-Tuning: A Practical Distillation Recipe
May 11, 2026Igor Slinko, Ilia Zavidnyi, Egor Bogomolov +1Supervised Fine-Tuning LLM Agent Training
JetBrains Research
DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning
May 11, 2026Haoyu Huang, Jiaxin Bai, Shujie Liu +6Knowledge Editing Knowledge Augmentation for Language Models
1HKUST · 2HKBU · 3Microsoft Research Asia
EGL-SCA: Structural Credit Assignment for Co-Evolving Instructions and Tools in Graph Reasoning Agents
May 11, 2026Zike Yuan, Yukun Cao, Han Zhang +7Program Synthesis LLM Agent Training
Harbin Institute of Technology, Shenzhen, China · School of Computer Science and Technology, Xidian University · Peng Cheng Laboratory, Shenzhen, China
AHD Agent: Agentic Reinforcement Learning for Automatic Heuristic Design
May 9, 2026Haoze Lv, Ning Lu, Ziang Zhou +1Agentic RL Automated Heuristic Design
Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation, Department of Computer Science and Engineering, Southern University of Science and Technology · Zhongguancun Academy · The Hong Kong University of Science and Technology
CoCoDA: Co-evolving Compositional DAG for Tool-Augmented Agents
May 8, 2026Ziyang Yu, Qiyue Li, Liang ZhaoLLM Tool Use LLM Agent Training
1Emory University · 2Beijing Normal-Hong Kong Baptist University
SOD: Step-wise On-policy Distillation for Small Language Model Agents
May 8, 2026Qiyong Zhong, Mao Zheng, Mingyang Song +5Tool-Integrated Reasoning LLM Agent Training
1Zhejiang University · 2Large Language Model Department, Tencent · University of Science and Technology of China +1
LiteGUI: Lightweight GUI Agents via Multi-Solution Guided Distillation and Dual-Level Reinforcement Learning
May 8, 2026Yubin Wu, Zicheng Cai, Liping Ning +4RL for GUI Agents GUI Agents
Moore Threads AI
MedAction: Towards Active Multi-turn Clinical Diagnostic LLMs
May 8, 2026Hsin-Ling Hsu, Zizheng Wang, Donghua Zhang +9Healthcare Medical Diagnosis
National Chengchi University · Georgetown University · University of Michigan +3
MedExAgent: Training LLM Agents to Ask, Examine, and Diagnose in Noisy Clinical Environments
May 8, 2026Yicheng Gao, Xiaolin Zhou, Yahan Li +2Healthcare Medical Diagnosis
University of Southern California · Arizona State University
Dual-Agent Co-Training for Health Coaching via Implicit Adversarial Preference Optimization
May 7, 2026Da Long, Lingyi Fu, Diya Michelle Rao +3Adversarial Training Multi-Agent LLM Systems
Kahlert School of Computing University of Utah · Department of Health and Kinesiology University of Utah
Same Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM Agents
May 7, 2026Ziming Li, Jiatan Huang, Xiaoguang Guo +2LLM Agent Training Inference-Time Compute Allocation
University of Connecticut · New Jersey Institute of Technology
Recursive Agent Optimization
May 7, 2026Apurva Gandhi, Satyaki Chakraborty, Xiangjun Wang +2Agentic RL Inference-Time Scaling
Carnegie Mellon University · Amazon AGI Labs
Weblica: Scalable and Reproducible Training Environments for Visual Web Agents
May 7, 2026Oğuzhan Fatih Kar, Roman Bachmann, Yuanzheng Gong +2LLM Agent Training RL for LLM Agents
Apple

May 18, 2026J/K move · Enter open · S save

HydroAgent: Closing the Gap Between Frontier LLMs and Human Experts in Hydrologic Model Calibration via Simulator-Grounded RL

Zhi Li, Songkun Yan, Jie Cao, Mofan Zhang+3

Civil, Environmental, and Architectural Engineering, University of Colorado Boulder · Civil Engineering and Environmental Sciences, University of Oklahoma · Department of Computer Science, University of Oklahoma+3

Reinforcement Learning Model Calibration Hydrology LLM Agent Training RL for LLM Agents

Open paper AskPDF arXiv

Calibrating distributed hydrologic models is a critical bottleneck across operational water resources management - streamflow prediction, reservoir operation, drought monitoring, infrastructure design, and flood forecasting all depend on it. Each basin demands an expert to translate hydrograph signatures into adjustments of a high-dimensional parameter vector, and the resulting workflow does not transfer between watersheds. We ask: can frontier large language model (LLM) agents replace the human hydrologic modeler, and if not, what would it take? We benchmark nine frontier LLM agents - Claude Opus 4.6/4.7, Sonnet 4.6, GPT-5/5.4/5.4-pro, and Gemini 2.5-pro/3.1-pro/3-flash - on the operational CREST distributed hydrologic model used by the U.S. National Weather Service for flash-flood forecasting. Best-of-twenty-rounds Nash-Sutcliffe Efficiency (NSE) across four held-out gauges spanning 329-40,792 km2 ranges from -0.16 (GPT-5.4) to 0.75 (Sonnet 4.6); the ceiling reproduces across all three vendors and capability tiers, with the strongest models concentrating in the 0.65-0.75 band, and no model reaches the human-expert reference except Opus-4.7 on one gauge. We argue this gap is not a parameter-count problem but a domain-grounding problem. We then propose HYDROAGENT, fine-tuning open-weight Qwen3-4B with supervised fine-tuning on 2,576 expert calibration trajectories and Group-Relative Policy Optimization using NSE as a verifiable reward from online CREST simulations - reinforcement learning with simulation feedback (RLSF). For Earth system science, a small domain-tuned policy with simulator-in-the-loop RL is a more compute-efficient and physically faithful path than scaling generic frontier models, and the multi-modal richness of Earth data - remote sensing, in-situ time series, and forecaster narrative - makes domain agents a leveraged direction for AI in physical science.