TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking
This addresses safety risks in AI agents during memory evolution, though it appears incremental as it builds on existing paradigms with a novel framework.
The paper tackles the problem of agent safety alignment vulnerability during test-time memory evolution, known as Agent Memory Misevolution, by proposing TAME, a dual-memory evolutionary framework that mitigates this issue and achieves a joint improvement in trustworthiness and task performance.
Test-time evolution of agent memory serves as a pivotal paradigm for achieving AGI by bolstering complex reasoning through experience accumulation. However, even during benign task evolution, agent safety alignment remains vulnerable-a phenomenon known as Agent Memory Misevolution. To evaluate this phenomenon, we construct the Trust-Memevo benchmark to assess multi-dimensional trustworthiness during benign task evolution, revealing an overall decline in trustworthiness across various task domains and evaluation settings. To address this issue, we propose TAME, a dual-memory evolutionary framework that separately evolves executor memory to improve task performance by distilling generalizable methodologies, and evaluator memory to refine assessments of both safety and task utility based on historical feedback. Through a closed loop of memory filtering, draft generation, trustworthy refinement, execution, and dual-track memory updating, TAME preserves trustworthiness without sacrificing utility. Experiments demonstrate that TAME mitigates misevolution, achieving a joint improvement in both trustworthiness and task performance.