Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent

• URL: http://arxiv.org/abs/2509.03990v2
• Date: Mon, 08 Sep 2025 07:40:58 GMT
• Title: Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent
• Authors: Chunlong Wu, Ye Luo, Zhibo Qu, Min Wang,
• Abstract summary: Meta-Policy Reflexion (MPR) is a framework that consolidates LLM-generated reflections into a structured, predicate-like Meta-Policy Memory (MPM)<n>MPR externalizes reusable corrective knowledge without model weight updates, enforces domain constraints to reduce unsafe or invalid actions, and retains the adaptability of language-based reflection.<n> Empirical results reported in the supplied material indicate consistent gains in execution accuracy and robustness when compared to Reflexion baselines; rule admissibility further improves stability.
• Score: 6.300669721057781
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language model (LLM) agents achieve impressive single-task performance but commonly exhibit repeated failures, inefficient exploration, and limited cross-task adaptability. Existing reflective strategies (e.g., Reflexion, ReAct) improve per-episode behavior but typically produce ephemeral, task-specific traces that are not reused across tasks. Reinforcement-learning based alternatives can produce transferable policies but require substantial parameter updates and compute. In this work we introduce Meta-Policy Reflexion (MPR): a hybrid framework that consolidates LLM-generated reflections into a structured, predicate-like Meta-Policy Memory (MPM) and applies that memory at inference time through two complementary mechanisms soft memory-guided decoding and hard rule admissibility checks(HAC). MPR (i) externalizes reusable corrective knowledge without model weight updates, (ii) enforces domain constraints to reduce unsafe or invalid actions, and (iii) retains the adaptability of language-based reflection. We formalize the MPM representation, present algorithms for update and decoding, and validate the approach in a text-based agent environment following the experimental protocol described in the provided implementation (AlfWorld-based). Empirical results reported in the supplied material indicate consistent gains in execution accuracy and robustness when compared to Reflexion baselines; rule admissibility further improves stability. We analyze mechanisms that explain these gains, discuss scalability and failure modes, and outline future directions for multimodal and multi-agent extensions.

Related papers

• CREM: Compression-Driven Representation Enhancement for Multimodal Retrieval and Comprehension [49.6969505536365]
  We propose CREM, with a unified framework that enhances multimodal representations for retrieval while preserving generative ability.<n>CREM achieves state-of-the-art retrieval performance on MMEB while maintaining strong generative performance on multiple comprehension benchmarks.
  arXiv  Detail & Related papers  (2026-02-22T08:09:51Z)
• Rethinking the Trust Region in LLM Reinforcement Learning [72.25890308541334]
  Proximal Policy Optimization (PPO) serves as the de facto standard algorithm for Large Language Models (LLMs)<n>We propose Divergence Proximal Policy Optimization (DPPO), which substitutes clipping with a more principled constraint.<n>DPPO achieves superior training and efficiency compared to existing methods, offering a more robust foundation for RL-based fine-tuning.
  arXiv  Detail & Related papers  (2026-02-04T18:59:04Z)
• ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval [64.14282916266998]
  Composed Image Retrieval aims to retrieve target images based on a hybrid query comprising a reference image and a modification text.<n>We propose ReCALL, a model-agnostic framework that follows a diagnose-generate-refine pipeline.<n>Experiments on CIRR and FashionIQ show that ReCALL consistently recalibrates degraded capabilities and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-02T04:52:54Z)
• Policy-Conditioned Policies for Multi-Agent Task Solving [53.67744322553693]
  In this work, we propose a paradigm shift that bridges the gap by representing policies as human-interpretable source code.<n>We reformulate the learning problem by utilizing Large Language Models (LLMs) as approximate interpreters.<n>We formalize this process as textitProgrammatic Iterated Best Response (PIBR), an algorithm where the policy code is optimized by textual gradients.
  arXiv  Detail & Related papers  (2025-12-24T07:42:10Z)
• From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory [48.22750809620306]
  Large Language Models (LLMs) based agents have demonstrated remarkable potential in autonomous task-solving.<n>In this paper, we introduce a novel agent-centric, trainable, multi-layered graph memory framework.<n>We show how context memory enhances the ability of LLMs to utilize information.
  arXiv  Detail & Related papers  (2025-11-11T03:36:33Z)
• Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting [92.57796055887995]
  We introduce ECHO, a prompting framework that adapts hindsight experience replay from reinforcement learning for language model agents.<n> ECHO generates optimized trajectories for alternative goals that could have been achieved during failed attempts.<n>We evaluate ECHO on stateful versions of XMiniGrid, a text-based navigation and planning benchmark, and PeopleJoinQA, a collaborative information-gathering enterprise simulation.
  arXiv  Detail & Related papers  (2025-10-11T18:11:09Z)
• Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models [18.829572148850563]
  We introduce ACE (Agentic Context Engineering), a framework that treats contexts as evolving playbooks.<n>Across agent and domain-specific benchmarks, ACE consistently outperforms strong baselines.<n> ACE could adapt effectively without labeled supervision and instead by leveraging natural execution feedback.
  arXiv  Detail & Related papers  (2025-10-06T09:30:18Z)
• Reflection-Enhanced Meta-Optimization Integrating TextGrad-style Prompt Optimization with Memory-Driven Self-Evolution [0.0]
  We propose a framework that integrates a memory-augmented Reflection RetrievalRAG module and a Self-Adaptive meta-controller.<n>REMO achieves more stable and robust tuning, albeit at the cost of increased computational overhead.
  arXiv  Detail & Related papers  (2025-08-26T07:25:45Z)
• Who Sees What? Structured Thought-Action Sequences for Epistemic Reasoning in LLMs [1.090218572228214]
  This study investigates the potential of structured examples to improve the performance of LLM-based agents within a ReAct framework.<n>We propose a structured solution-processing pipeline that generates three categories of examples: optimal goal paths (G-type), informative node paths (E-type) and step-by-step optimal decision sequences contrasting alternative actions (L-type)<n>While L-type examples slightly reduce clarification requests and overall action steps, they do not yield consistent improvements.
  arXiv  Detail & Related papers  (2025-08-20T09:36:53Z)
• SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning [25.02860760920562]
  Multimodal large language models (MLLMs) have shown promising capabilities in reasoning tasks, but struggle with complex problems requiring explicit self-reflection and self-correction.<n>Existing reflection methods are simplistic and struggle to generate meaningful and instructive feedback.<n>We propose Multimodal Self-Reflection enhanced reasoning with Group Relative Policy Optimization (SRPO), a two-stage reflection-aware reinforcement learning framework.
  arXiv  Detail & Related papers  (2025-06-02T14:21:44Z)
• MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering [57.156093929365255]
  Gym-style framework for systematically reinforcement learning, evaluating, and improving autonomous large language model (LLM) agents.<n>MLE-Dojo covers diverse, open-ended MLE tasks carefully curated to reflect realistic engineering scenarios.<n>Its fully executable environment supports comprehensive agent training via both supervised fine-tuning and reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-12T17:35:43Z)
• In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents [70.12342024019044]
  Large Language Models (LLMs) have made significant progress in open-ended dialogue, yet their inability to retain and retrieve relevant information limits their effectiveness.<n>We propose Reflective Memory Management (RMM), a novel mechanism for long-term dialogue agents, integrating forward- and backward-looking reflections.<n>RMM shows more than 10% accuracy improvement over the baseline without memory management on the LongMemEval dataset.
  arXiv  Detail & Related papers  (2025-03-11T04:15:52Z)
• Meta-Reflection: A Feedback-Free Reflection Learning Framework [57.14485943991588]
  We propose Meta-Reflection, a feedback-free reflection mechanism that requires only a single inference pass without external feedback.<n>Motivated by the human ability to remember and retrieve reflections from past experiences, Meta-Reflection integrates reflective insights into a codebook.<n>To thoroughly investigate and evaluate the practicality of Meta-Reflection in real-world scenarios, we introduce an industrial e-commerce benchmark named E-commerce Customer Intent Detection.
  arXiv  Detail & Related papers  (2024-12-18T12:20:04Z)
• Scrutinize What We Ignore: Reining In Task Representation Shift Of Context-Based Offline Meta Reinforcement Learning [10.792687309720169]
  offline meta reinforcement learning (OMRL) has emerged as a promising approach for interaction avoidance and strong generalization performance.<n>Previous context-based approaches rely on the intuition that alternating optimization between the context encoder and the policy can lead to performance improvements.<n>We name this issue task representation shift and theoretically prove that the monotonic performance improvements can be guaranteed with appropriate context encoder updates.
  arXiv  Detail & Related papers  (2024-05-20T13:14:26Z)
• REBEL: Reinforcement Learning via Regressing Relative Rewards [59.68420022466047]
  We propose REBEL, a minimalist RL algorithm for the era of generative models.<n>In theory, we prove that fundamental RL algorithms like Natural Policy Gradient can be seen as variants of REBEL.<n>We find that REBEL provides a unified approach to language modeling and image generation with stronger or similar performance as PPO and DPO.
  arXiv  Detail & Related papers  (2024-04-25T17:20:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.