Image de couverture de livre

Imitation Learning for Multi-turn LM Agents via On-policy Expert Corrections

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Lauffer, Niklas, Deng, Xiang, Kundurthy, Srivatsa, Kenstler, Brad, Da, Jeff
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Learning Symbolic Task Decompositions for Multi-Agent Teams
par: Shah, Ameesh, et autres
Publié: (2025)

Provably Correct Automata Embeddings for Optimal Automata-Conditioned Reinforcement Learning
par: Yalcinkaya, Beyazit, et autres
Publié: (2025)

Learning with Expert Abstractions for Efficient Multi-Task Continuous Control
par: Jewett, Jeff, et autres
Publié: (2025)

Causal Imitation Learning under Expert-Observable and Expert-Unobservable Confounding
par: Shao, Daqian, et autres
Publié: (2025)

Thought Cloning: Learning to Think while Acting by Imitating Human Thinking
par: Hu, Shengran, et autres
Publié: (2023)

SpreadsheetArena: Decomposing Preference in LLM Generation of Spreadsheet Workbooks
par: Kundurthy, Srivatsa, et autres
Publié: (2026)

Using Non-Expert Data to Robustify Imitation Learning via Offline Reinforcement Learning
par: Huang, Kevin, et autres
Publié: (2025)

IDIL: Imitation Learning of Intent-Driven Expert Behavior
par: Seo, Sangwon, et autres
Publié: (2024)

Sample-Efficient Expert Query Control in Active Imitation Learning via Conformal Prediction
par: Firouzkouhi, Arad, et autres
Publié: (2025)

Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization
par: Li, Yu, et autres
Publié: (2026)

Learning Strategy Representation for Imitation Learning in Multi-Agent Games
par: Lei, Shiqi, et autres
Publié: (2024)

Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration
par: Zhao, Heyang, et autres
Publié: (2025)

Coupled Distributional Random Expert Distillation for World Model Online Imitation Learning
par: Li, Shangzhe, et autres
Publié: (2025)

Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning
par: Yalcinkaya, Beyazit, et autres
Publié: (2024)

MAPF-GPT: Imitation Learning for Multi-Agent Pathfinding at Scale
par: Andreychuk, Anton, et autres
Publié: (2024)

SENSOR: Imitate Third-Person Expert's Behaviors via Active Sensoring
par: Huang, Kaichen, et autres
Publié: (2024)

Scaling Laws for Imitation Learning in Single-Agent Games
par: Tuyls, Jens, et autres
Publié: (2023)

TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents
par: Wang, Jiaqi, et autres
Publié: (2026)

Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations
par: Hoang, Huy, et autres
Publié: (2025)

Imitation Learning via Focused Satisficing
par: Shah, Rushit N., et autres
Publié: (2025)

Boolean Satisfiability via Imitation Learning
par: Zhang, Zewei, et autres
Publié: (2025)

Adversarial Imitation Learning via Boosting
par: Chang, Jonathan D., et autres
Publié: (2024)

Identifying the Risks of LM Agents with an LM-Emulated Sandbox
par: Ruan, Yangjun, et autres
Publié: (2023)

AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
par: Ma, Chang, et autres
Publié: (2024)

Learning Representations in Video Game Agents with Supervised Contrastive Imitation Learning
par: Celemin, Carlos, et autres
Publié: (2025)

Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting
par: Hu, Michael Y., et autres
Publié: (2025)

Reinforcement Learning via Implicit Imitation Guidance
par: Dong, Perry, et autres
Publié: (2025)

Unveiling the Role of Expert Guidance: A Comparative Analysis of User-centered Imitation Learning and Traditional Reinforcement Learning
par: Gomaa, Amr, et autres
Publié: (2024)

DecompGAIL: Learning Realistic Traffic Behaviors with Decomposed Multi-Agent Generative Adversarial Imitation Learning
par: Guo, Ke, et autres
Publié: (2025)

Offline Imitation of Badminton Player Behavior via Experiential Contexts and Brownian Motion
par: Wang, Kuang-Da, et autres
Publié: (2024)

SpectR: Dynamically Composing LM Experts with Spectral Routing
par: Fleshman, William, et autres
Publié: (2025)

Imitation Learning Datasets: A Toolkit For Creating Datasets, Training Agents and Benchmarking
par: Gavenski, Nathan, et autres
Publié: (2024)

Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation
par: Li, Pengxiang, et autres
Publié: (2025)

Learning Soft Driving Constraints from Vectorized Scene Embeddings while Imitating Expert Trajectories
par: Mobarakeh, Niloufar Saeidi, et autres
Publié: (2024)

Error-Feedback Model for Output Correction in Bilateral Control-Based Imitation Learning
par: Sato, Hiroshi, et autres
Publié: (2024)

Expert-Free Online Transfer Learning in Multi-Agent Reinforcement Learning
par: Castagna, Alberto
Publié: (2025)

Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
par: Wang, Hao, et autres
Publié: (2026)

Imitation Learning from Suboptimal Demonstrations via Meta-Learning An Action Ranker
par: Fan, Jiangdong, et autres
Publié: (2024)

Quantifying Generalisation in Imitation Learning
par: Gavenski, Nathan, et autres
Publié: (2025)

Imitation Bootstrapped Reinforcement Learning
par: Hu, Hengyuan, et autres
Publié: (2023)