Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems

[2607.08010] Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems Skip to main content Search Submit Donate Log in Computer Science > Computation and Language arXiv:2607.08010 (cs) [Submitted on 9 Jul 2026 ( v1 ), last revised 24 Aug 2026 (this version, v2)] Title: Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems Authors: Kalle Kujanpää , Ning Liu , Shahnawaz Alam , Yeshwanth Reddy Sura , Tianyu Yang , Kristina Klinkner , Shervin Malmasi View PDF HTML (experimental) Abstract: Production LLM agents often waste latency and reliability by regenerating code for the same procedural steps on every request. We replace this inference-time coding loop with an agentic tool-making pipeline that compiles repeated SOP steps into validated, versioned tools before deployment. The tool-maker grounds synthesis in the live environment as it collects execution traces, observes backend schemas and values, generates candidate tools, and repairs them against labeled cases. At runtime, the production agent calls these tools directly and falls back to code generation only when needed. We deploy the approach in a Fulfillment Center alarm-triage system, where an agent diagnoses alarms against a 44-node SOP over heterogeneous metric backends. In production, tool calls reduce p50 latency by 42%. On 1,500 historical alarms, they reduce end-to-end error rate by up to 53% by suppressing run-to-run variance in repeated steps. Because tools return compact structured verdicts, they also enable a simpler direct-call architecture, reducing p50 latency by a further 62% in a controlled ablation. Versioned tools also improve auditability and expose specification gaps and upstream data drift. Our results show that agents that build and maintain their own tool libraries, a key element of self-evolving agents, can make industrial LLM systems faster, more reliable, and easier to operate. Comments: To appear at EMNLP 2026 Industry Track Subjects: Computation and Language (cs.CL) ; Machine Learning (cs.LG); Software Engineering (cs.SE) Cite as: arXiv:2607.08010 [cs.CL] (or arXiv:2607.08010v2 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2607.08010 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Kalle Kujanpää [ view email ] [v1] Thu, 9 Jul 2026 00:27:13 UTC (74 KB) [v2] Mon, 24 Aug 2026 22:30:34 UTC (77 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.CL < prev | next > new | recent | 2026-07 Change to browse by: cs cs.LG cs.SE References & Citations SciX 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 Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems#670674
• Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems#353123
• Quine: Realizing LLM Agents as Native POSIX Processes#2733
• MetaChain: A Fully-Automated and Zero-Code Framework for LLM Agents#428171
• AGENTSERVESIM: A Hardware-aware Simulator for Multi-Turn LLM Agent Serving#267698