Xiangru Tang

MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science

ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory

Eigen-Agent: Adaptive Multi-Agent Scientific Reasoning with Monitor-Based RAG

MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning

Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE

CellForge: Agentic Design of Virtual Cell Models

Agent-ScanKit: Unraveling Memory and Reasoning of Multimodal Agents via Sensitivity Perturbations

ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows

Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL

RiboPO: Preference Optimization for Structure- and Stability-Aware RNA Design

Which LLM Multi-Agent Protocol to Choose?

Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards

Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving

Diagnose, Localize, Align: A Full-Stack Framework for Reliable LLM Multi-Agent Systems under Instruction Conflicts

Automating Environments For Measuring Agentic Learning

InteractComp: Evaluating Search Agents With Ambiguous Queries

KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation

DyFlow: Dynamic Workflow Framework for Agentic Reasoning

OpenHands: An Open Platform for AI Software Developers as Generalist Agents

WebDancer: Towards Autonomous Information Seeking Agency

ChemAgent: Self-updating Memories in Large Language Models Improves Chemical Reasoning

ML-Bench: Evaluating Large Language Models for Code Generation in Repository-Level Machine Learning Tasks

Data Interpreter: An LLM Agent For Data Science