Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents Paper • 2509.23040 • Published Sep 27, 2025 • 12
MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning Paper • 2601.21468 • Published 7 days ago • 18
CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs Paper • 2602.03048 • Published 3 days ago • 33
V_0: A Generalist Value Model for Any Policy at State Zero Paper • 2602.03584 • Published 2 days ago • 20
Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text Paper • 2601.10355 • Published 21 days ago • 39