Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents
In long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action agent must surface it and act. As trajectories grow, task requirements, environment facts, prior attempts, diagnoses, and open subgoals can be buried in the context window or pushed beyond it, failing to influence decisions when needed. We call this failure mode "behavioral state decay". We study memory as an active intervention mechanism rather than passive retrieval. A separate memory agent runs alongside an unmodified action agent, updating a structured memory bank from the rec
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 59%sandst1/remind →
- PossiblePossibly related (embedding) · 59%rajkripal/cashew →
- PossiblePossibly related (embedding) · 58%plastic-labs/honcho →
- PossiblePossibly related (embedding) · 57%We're building agents that can read millions of documents, but still forget a video they watched yesterday. →
- PossiblePossibly related (embedding) · 29%MemTensor/MemOS →
“Possibly related via embedding similarity 0.64 (not asserted). Timestamp check: artifact slightly before paper (-7d).”
- PossiblePossibly related (embedding) · 52%raiyanyahya/recall →
- PossiblePossibly related (embedding) · 53%A neural network model of free recall learns multiple memory strategies →
- PossiblePossibly related (embedding) · 55%Exploring continual learning without replay buffers: Our findings using dynamic task-similarity routing [P] →