Papers

• Self-Authored Verification Is Unreliable in Heuristic Self-Improving Agents (2026)
  Diandian Guo et al.
  4.39
• PREPING: Building Agent Memory without Tasks (2026)
  Yumin Choi et al.
  1.94
• The Role of Feedback Alignment in Self-Distillation (2026)
  Semih Kara et al.
  1.94
• Think Again or Think Longer? Selective Verification for Budget-Aware Reasoning (2026)
  Sajib Acharjee Dip et al.
  1.94
• Search Self-play: Pushing the Frontier of Agent Capability without Supervision (2025)
  Hongliang Lu et al.
  1.28
• Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding (2024)
  Yueqian Wang et al.
  —