Jiajun Chai

ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models

LogiConBench: Benchmarking Logical Consistencies of LLMs

SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning

SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning

From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory

MTIR-SQL:Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL

MAD-Logic: Multi-Agent Debate Enhances Symbolic Translation and Reasoning

SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without Training

Enhancing Logical Reasoning of Large Language Models via Phased Fine-Tuning

Personal Tokens Matter: Towards Token-Aware Training for Personalized LLMs

Understanding and Leveraging Expert-level Monosemanticity in Finetuning MoE LLMs

Learning and Planning Multi-Agent Tasks via an MoE-based World Model

INS: Interaction-aware Synthesis to Enhance Offline Multi-agent Reinforcement Learning

DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy

Empowering LLM Agents with Zero-Shot Optimal Decision-Making through Q-learning