CoEM: Empowering Long-Context Reasoning with Commit-on-Evidence Memory
Long-context reasoning is essential for complex and long-horizon tasks, yet the performance of large language models (LLMs) degrades as context length increases. Recent approaches address this by processing input chunk by chunk while maintaining a bounded textual memory in model context. However, premature information compression can discard critical details essential for subsequent reasoning. In…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
