Retrieval as Traversal: Value-Indexed Memory for Stateful Long-Context Agents
Long-context models repeatedly solve closely related retrieval problems. Attention or global retrieval can retain large stores, but each forward pass again searches for what matters. Recurrent compression avoids this search only by deciding earlier what information to preserve. Neither mechanism directly exploits that useful memories at neighbouring retrieval steps may substantially overlap. We…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
