MemToolAgent overview with a simple restaurant booking scenario where the agent retrieves similar memories, receives feedback on an invalid time format, and generates a reflection to update its memory
Quick Answer
MemToolAgent enhances LLM agents' tool usage by integrating memory management, achieving up to 80% improvement on benchmarks like WorkBench and NESTFUL.
Quick Take
MemToolAgent enhances LLM agents' tool usage by integrating memory management, achieving up to 80% improvement on benchmarks like WorkBench and NESTFUL. It utilizes structured memory entries and feedback for personalized responses without fine-tuning, demonstrating significant advancements in user-agent interactions.
Key Points
- Introduces a unified memory entry format for improved .
- Utilizes reflection-based memory extraction to critique past errors.
- Dynamic retrieval module selects relevant past experiences based on similarity.
- Achieves 29%, 80%, and 17% improvements on WorkBench, NESTFUL, and PEToolBench.
- No fine-tuning of LLMs is required for enhanced performance.
Article Content
From source RSS / original summaryarXiv:2606. 07909v1 Announce Type: new Abstract: Modern large language model (LLM) agents can use external tools to help users solve complex tasks. However, for problems that require learning from long-term historical events or from previous agent-environment interactions, LLM agents are required to use memory mechanisms to store and retrieve experiences.
While sophisticated memory systems exist for dialogue agents, few studies have empirically examined how to improve agents' tool-using capabilities through past user-agent conversations. We propose MemToolAgent, a framework that improves through memory management. Our approach contains a memory extraction module that processes past experiences into structured memory entries, and a retrieval module that dynamically selects a subset of the stored memory entries.
This enables more personalized and accurate responses aligned with user preferences and feedback without requiring LLM fine-tuning.
In summary, this work has three main contributions: (1) a unified memory entry format that improves both general-purpose and personalized tool use without LLM fine-tuning, (2) a reflection-based memory extraction that uses environment and user feedback to distill wrong executions into critiques to store, and (3) a retrieval module that chooses how many past experiences to use based on the memory similarity distribution.
MemToolAgent achieves 29%, 80%, and 17% relative improvements compared to strong baselines on the WorkBench, NESTFUL, and PEToolBench benchmarks, respectively.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →The Sim-to-Real Gap of Foundation Model Agents: A Unified MDP Perspective
This paper addresses the sim-to-real gap for foundation model agents by framing it within a Markov Decision Process (MDP) structure. It advocates for established solutions like domain randomization to enhance agent robustness, aiming to create standardized benchmarks for reliable real-world applications.