PRECEPT: Planning Resilience via Experience, Context Engineering & Probing Trajectories A Unified Framework for Test-Time Adaptation with Compositional Rule Learning and Pareto-Guided Prompt Evolution

ArXi:2603.09641v1 Announce Type: new LLM agents that knowledge as natural language suffer steep retrieval degradation as condition count grows, often struggle to compose learned rules reliably, and typically lack explicit mechanisms to detect stale or adversarial knowledge.