Mem-$π$: Adaptive Memory through Learning When and What to Generate

• URL: http://arxiv.org/abs/2605.21463v1
• Date: Wed, 20 May 2026 17:51:05 GMT
• Title: Mem-$π$: Adaptive Memory through Learning When and What to Generate
• Abstract summary: We present a framework for adaptive memory in large language model (LLM) agents, where useful guidance is generated on demand.<n>Mem-$$ consistently outperforms retrieval-based and prior RL-optimized memory baselines.
• Score: 65.31077328444077
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Mem-$π$, a framework for adaptive memory in large language model (LLM) agents, where useful guidance is generated on demand rather than retrieved from external memory stores. Existing memory-augmented agents typically rely on similarity-based retrieval from episodic memory banks or skill libraries, returning static entries that often misalign with the current context. In contrast, Mem-$π$ uses a dedicated language or vision-language model with its own parameters, separate from the downstream agent, to generate context-specific guidance for complex tasks. Conditioned on the current agent context, the model jointly decides when to produce guidance and what guidance to produce. We train it with a decision-content decoupled reinforcement learning (RL) objective, enabling it to abstain when generation would not help and otherwise produce concise, useful guidance. Across diverse agentic benchmarks spanning web navigation, terminal-based tool use, and text-based embodied interaction, Mem-$π$ consistently outperforms retrieval-based and prior RL-optimized memory baselines, achieving over 30% relative improvement on web navigation tasks.

Related papers

• MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents [14.16693343382686]
  Large Language Models (LLMs) lack persistent memory for long-term personalized conversations.<n>Existing graph-based memory systems suffer from information dilution, absent provenance tracking, and uniform retrieval that ignores query context.<n>We introduce MemORAI, a framework that integrates three innovations: selective memory filtering with dual-layer compression to retain user-persona-relevant content, a provenance-enriched multi-relational graph tracking factual origins at the turn level, and query-adaptive subgraph retrieval with Dynamic weighted PageRank.
  arXiv  Detail & Related papers  (2026-05-02T11:20:34Z)
• Memory-Augmented LLM-based Multi-Agent System for Automated Feature Generation on Tabular Data [52.80567461420316]
  We propose a Memory-Augmented LLM-based Multi-Agent System (textbfMALMAS) for automated feature generation.<n>MALMAS decomposes the generation process into agents with distinct responsibilities, and a Router Agent activates an appropriate subset of agents per iteration.<n>We further integrate a memory module comprising procedural memory, feedback memory, and conceptual memory, enabling iterative refinement that adaptively guides subsequent feature generation.
  arXiv  Detail & Related papers  (2026-04-22T07:09:30Z)
• TA-Mem: Tool-Augmented Autonomous Memory Retrieval for LLM in Long-Term Conversational QA [8.036549927091286]
  Large Language Model (LLM) has exhibited strong reasoning ability in text-based contexts across various domains.<n>The limitation of context window poses challenges for the model on long-range inference tasks.<n>We introduce a tool-augmented autonomous memory retrieval framework (TA-Mem)<n>The TA-Mem is evaluated on the LoCoMo dataset, achieving significant performance improvements over existing baseline approaches.
  arXiv  Detail & Related papers  (2026-03-10T07:27:01Z)
• UMEM: Unified Memory Extraction and Management Framework for Generalizable Memory [46.87954895079213]
  Self-evolving memory serves as the trainable parameters for Large Language Models (LLMs)<n>Existing methods predominately optimize memory management while treating memory extraction as a static process.<n>We propose Unified Memory Extraction and Management (UMEM) to jointly optimize a Large Language Model to simultaneous extract and manage memories.
  arXiv  Detail & Related papers  (2026-02-11T08:58:41Z)
• Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents [57.38404718635204]
  Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows.<n>Existing methods typically handle long-term memory (LTM) and short-term memory (STM) as separate components.<n>We propose Agentic Memory (AgeMem), a unified framework that integrates LTM and STM management directly into the agent's policy.
  arXiv  Detail & Related papers  (2026-01-05T08:24:16Z)
• Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution [52.76038908826961]
  We propose $textbfReMe$ ($textitRemember Me, Refine Me$) to bridge the gap between static storage and dynamic reasoning.<n>ReMe innovates across the memory lifecycle via three mechanisms: $textitmulti-faceted distillation$, which extracts fine-grained experiences.<n>Experiments on BFCL-V3 and AppWorld demonstrate that ReMe establishes a new state-of-the-art in agent memory system.
  arXiv  Detail & Related papers  (2025-12-11T14:40:01Z)
• Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory [89.65731902036669]
  Evo-Memory is a streaming benchmark and framework for evaluating self-evolving memory in large language model (LLM) agents.<n>We evaluate over ten representative memory modules and evaluate them across 10 diverse multi-turn goal-oriented and single-turn reasoning and QA datasets.
  arXiv  Detail & Related papers  (2025-11-25T21:08:07Z)
• Improving Language Agents through BREW [7.098644778864677]
  Large Language Model (LLM)-based agents are increasingly applied to tasks requiring structured reasoning, tool use, and environmental adaptation.<n>Current training paradigms for model weight optimization methods, like PPO and GRPO, remain relatively impractical with their high computational overhead for rollout convergence.<n>We introduce BREW, a framework for agent optimization for downstream tasks via construction and refinement.
  arXiv  Detail & Related papers  (2025-11-25T13:34:54Z)
• MemOS: A Memory OS for AI System [116.87568350346537]
  Large Language Models (LLMs) have become an essential infrastructure for Artificial General Intelligence (AGI)<n>Existing models mainly rely on static parameters and short-lived contextual states, limiting their ability to track user preferences or update knowledge over extended periods.<n>MemOS is a memory operating system that treats memory as a manageable system resource.
  arXiv  Detail & Related papers  (2025-07-04T17:21:46Z)
• Memory Sharing for Large Language Model based Agents [43.53494041932615]
  This paper introduces the Memory Sharing, a framework which integrates the real-time memory filter, storage and retrieval to enhance the In-Context Learning process. The experimental results demonstrate that the MS framework significantly improves the agents' performance in addressing open-ended questions.
  arXiv  Detail & Related papers  (2024-04-15T17:57:30Z)

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.