Ruiming Tang

From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents

Advancing and Benchmarking Personalized Tool Invocation for LLMs

InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation

ATGen: Adversarial Reinforcement Learning for Test Case Generation

TRACEBench: Personalized Function Calling Benchmark Based on Real-World Human Interaction

MTRec: Learning to Align with User Preferences via Mental Reward Models

CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension

P-Law: Predicting Quantitative Scaling Law with Entropy Guidance in Large Recommendation Models

ToolACE: Winning the Points of LLM Function Calling

Bridging and Modeling Correlations in Pairwise Data for Direct Preference Optimization

RevisEval: Improving LLM-as-a-Judge via Response-Adapted References

Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning

Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger

RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generation

Scenario-Wise Rec: A Multi-Scenario Recommendation Benchmark