← authors · overview

• Improving RL Exploration for LLM Reasoning through Retrospective Replay
  2025 · 19 citations
• Towards Understanding the Capability of Large Language Models on Code Clone Detection: A Survey
  2023 · 9 citations
• ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use
  2025 · 3 citations
• ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use
  2025 · 3 citations
• SafeAligner: Safety Alignment against Jailbreak Attacks via Response Disparity Guidance
  2024 · 2 citations
• VLSBench: Unveiling Visual Leakage in Multimodal Safety
  2024 · 1 citations
• AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments
  2026
• Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments
  2025
• Mitigating Position Bias in Transformers via Layer-Specific Positional Embedding Scaling
  2026
• Can Deep Research Agents Retrieve and Organize? Evaluating the Synthesis Gap with Expert Taxonomies