← authors · overview

• O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL
  2026
• EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies
  2026
• ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoning
  2025
• CodeCriticBench: A Holistic Code Critique Benchmark for Large Language Models
  2025
• PersonaFeedback: A Large-scale Human-annotated Benchmark For Personalization
  2025
• Scaling Test-time Compute for LLM Agents
  2025
• Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL
  2025
• TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling
  2025
• Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution
  2025
• ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems