6 papers · 2 filters
Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents
Yihao Hu, Zhihao Wen, Yitong Lin +5
Successful tool-use trajectories are not necessarily useful supervision. Even successful interactions may underrepresent multi-step dependencies or contain actions that are unjusti…
Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction
Pan Wang, Yihao Hu, Hang Wang +6
Self-correction is particularly useful when a failure constrains the next repair. Coding agents benefit from this property because compilers, tests, and execution traces turn many…
Learning Preference Adaptation for Large Language Model Personalization via Verbal Reinforcement Learning
Yuting Liu, Wei Wu, Jianzhe Zhao +1
Natural language user preferences provide an interpretable interface for LLM personalization. However, universal preference summaries often contain information irrelevant to a part…
How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel
Chang Liu, Chaoyang Ning, Dayi Jiang +32
Traditional industrial agents rely on modular pipelines, including Router, Retriever, Planner, Executor, Responder, Reviewer, and other components. These systems often fracture int…
SEAL: Synergistic Co-Evolution of Agents and Learning Environments
Yihao Hu, Zhihao Wen, Xiujin Liu +3
Large Language Model (LLM) agents are increasingly improved through interaction, yet most self-evolution methods adapt either the policy or the learning environment in isolation. W…
Text as a Universal Interface for Transferable Personalization
Yuting Liu, Jian Guan, Jia-Nan Li +4
We study the problem of personalization in large language models (LLMs). Prior work predominantly represents user preferences as implicit, model-specific vectors or parameters, yie…