mlsanityData to 7 Oct 2026

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

arXiv 2603.09641 ↗First posted 10 Mar 2026cs.AI cs.IRcited by 0

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

LLM agents that store 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. We introduce PRECEPT, a unified framework for test-time adaptation with three tightly coupled components: (1) deterministic exact-match rule retrieval over structured condition keys, (2) conflict-aware memory with Bayesian source reliability and threshold-based rule invalidation, and (3) COMPASS, a Pareto-guided prompt-evolution outer loop. Exact retrieval eliminates partial-match interpretation errors on the deterministic path (0% by construction, vs 94.4% under Theorem~B.6's independence model at N=10) and supports compositional stacking through a semantic tier hierarchy; conflict-aware memory resolves static--dynamic disagreements and supports drift adaptation; COMPASS evaluates prompts through the same end-to-end execution pipeline. Results (9--10 seeds): PRECEPT achieves a +41.1pp first-try advantage over Full Reflexion (d>1.9), +33.3pp compositional generalization (d=1.55), 100% P1 on 2-way logistics compositions (d=2.64), +40--55pp continuous learning gains, strong eventual robustness under adversarial static knowledge (100% logistics with adversarial SK active; partial recovery on integration), +55.0pp drift recovery (d=0.95, p=0.031), and 61% fewer steps. Core comparisons are statistically significant, often at p<0.001.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 10 of its 14 references that are in the map. First posted on arXiv 10 Mar 2026.

Builds on

10 of 14 references.

References · 10

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  4. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
  5. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
  6. 2025GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learningcited by 449
  7. 2019Measuring Compositional Generalization: A Comprehensive Method on Realistic Datacited by 280
  8. 2022Rich Knowledge Sources Bring Complex Knowledge Conflicts: Recalibrating Models to Reflect Conflicting Evidencecited by 142
  9. 2025Nested Learning: The Illusion of Deep Learning Architecturescited by 69
  10. 2023Knowledge-Augmented Language Model Verificationcited by 21

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026AdaMEM: Test-Time Adaptive Memory for Language Agents
  2. 2026Generalizable Self-Evolving Memory for Automatic Prompt Optimization
  3. 2026R-APS: Compositional Reasoning and In-Context Meta-Learning for Constrained Design via Reflective Adversarial Pareto Search
  4. 2026ERSkill: Evolving for Skill-Guided Adaptive Memory Retrieval
  5. 2026Training-Free Test-Time Contrastive Learning for Large Language Models
  6. 2026AMA: Adaptive Memory via Multi-Agent Collaboration
  7. 2026SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent
  8. 2026SkillSpec: Consensus-Gated Agent Skill Evolution via Representation Specialization