PPaperPicks

Benfeng Xu

11 papers at tracked venues · 8 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents
  2. GraphSynthQA: Knowledge-Graph-Guided Query Synthesis and Step-Level Preference Optimization for Web Agents
  3. MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools
  4. WildGraphBench: Benchmarking GraphRAG with Wild-Source Corpora
  5. Automated Creativity Evaluation for Large Language Models: A Reference-Based Approach
  6. From Real to Synthetic: Synthesizing Millions of Diversified and Complicated User Instructions with Attributed Grounding
  7. MIRROR: Multi-agent Intra- and Inter-Reflection for Optimized Reasoning in Tool Learning
  8. Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability
  9. Benchmarking Large Language Models on Controllable Generation under Diversified Instructions
  10. Disentangled Learning with Synthetic Parallel Data for Text Style Transfer
  11. KNN-Instruct: Automatic Instruction Construction with K Nearest Neighbor Deduction