Papers

• The PokeAgent Challenge: Competitive and Long-Context Learning at Scale (2026)
  Seth Karten et al.
  1.94
• Missing Old Logits in Asynchronous Agentic RL: Semantic Mismatch and Repair Methods for Off-Policy Correction (2026)
  Zhong Guan et al.
  1.94
• Learning POMDP World Models from Observations with Language-Model Priors (2026)
  Valentin Six et al.
  1.94
• Self-Improving Language Models with Bidirectional Evolutionary Search (2026)
  Guowei Xu et al.
  1.89
• Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions (2026)
  Mohammed Mehedi Hasan et al.
  1.72
• STAR-R1: Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMs (2025)
  Zongzhao Li et al.
  1.28
• WebOperator: Action-Aware Tree Search for Autonomous Agents in Web Environment (2025)
  Mahir Labib Dihan et al.
  1.28
• FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores (2023)
  Daniel Y. Fu et al.
  —