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

Computer Science > Artificial Intelligence [Submitted on 6 Jun 2026] 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 Suleyman Armagan Er, Danilo Ribeiro, Yogesh Virkar, Surafel Lakew, Adi Kalyanpur, James Gung, Thomas Delteil, Arshit Gupta 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 tool use 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. Comments: 8 pages, 5 figures Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL) ACM classes: I.2.7; I.2.6 Cite as: arXiv:2606.07909 [cs.AI]   (or arXiv:2606.07909v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.07909 Focus to learn more Submission history From: Danilo Neves Ribeiro [view email] [v1] Sat, 6 Jun 2026 00:15:00 UTC (1,080 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)