Amazing stuff!
"... Meta AI introduced a Proactive Memory Agent that runs alongside a typical agent to maintain and selectively highlight information relevant to the current problem. The memory agent increased the action agent’s performance on all benchmarks the authors tested. ...
The authors built larger and smaller systems that paired an action agent with a memory agent. The action agents were based on Claude Sonnet 4.5, Claude Opus 4.6, or Qwen3.5-122B-A10B (which presumably is much smaller). The memory agents were based on Claude Opus 4.6 or, in the smaller system ..."
From the abstract:
"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 recent trajectory and deciding whether to inject a memory-grounded reminder or remain silent. The module is plug-and-play with frontier action agents and existing agent harnesses. Across Terminal-Bench 2.0 and τ2-Bench, it improves pass@1 for both weaker and stronger action agents, with gains of +8.3 pp on Terminal-Bench and +6.8 pp on τ2-Bench.
Ablations show that selective intervention outperforms passive bank exposure, always-on injection, advisor-only guidance, and general retrieval. As an early step toward open-weight memory policies, we train Qwen3.5-27B on SETA using SFT and GRPO, improving validation reward and achieving partial transfer to Terminal-Bench."
No comments:
Post a Comment