← authors · overview

• Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
  2026 · 3 citations
• Would You Walk to the Car Wash? Revealing the Salience Bias of Large Language Models in Commonsense Reasoning
  2026
• ProtegoFed: Backdoor-Free Federated Instruction Tuning with Interspersed Poisoned Data
  2026
• GradSentry: Gradient Spectral Entropy for Backdoor Sample Filtering in Large Language Model Fine-Tuning
  2026
• Thinking in a Crowd: How Auxiliary Information Shapes LLM Reasoning
  2025
• DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
  2025
• DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning
  2025
• Probing then Editing Response Personality of Large Language Models
  2025
• RaSA: Rank-Sharing Low-Rank Adaptation
  2025
• Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique
  2025
• Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
  2025
• Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
  2024