Yujia Bao

MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning

Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control

SFT-GO: Supervised Fine-Tuning with Group Optimization for Large Language Models

WebDART: Dynamic Decomposition and Re-planning for Complex Web Tasks

DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning

KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse

LLM Unlearning via Loss Adjustment with Only Forget Data

From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs

Improving Data Efficiency via Curating LLM-Driven Rating Systems