Papers

• InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning (2026)
  Yuchen Yan et al.
  1.94
• InfoPO: Information-Driven Policy Optimization for User-Centric Agents (2026)
  Fanqi Kong et al.
  1.94
• GEMS: Agent-Native Multimodal Generation with Memory and Skills (2026)
  Zefeng He et al.
  1.94
• STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability (2026)
  Haipeng Luo et al.
  1.94
• TacoMAS: Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systems (2026)
  Chen Xu et al.
  1.89
• Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration (2026)
  Bowei He et al.
  1.72
• ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas (2026)
  Xiaoyu Tian et al.
  1.67
• Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs (2025)
  Jaemin Kim et al.
  1.28
• Sherlock: Self-Correcting Reasoning in Vision-Language Models (2025)
  Yi Ding et al.
  1.28
• Building Math Agents with Multi-Turn Iterative Preference Learning (2024)
  Wei Xiong et al.
  —