Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems
Quick Answer
This paper shows that A novel tool-making pipeline for LLM agents reduces latency by 42% and error rates by 53% in a Fulfillment Center alarm-triage system.
Quick Take
By compiling repeated procedural steps into validated tools, the system enhances reliability and operational simplicity, demonstrating the potential of self-evolving agents in industrial applications.
Key Points
- Tool-making pipeline compiles repeated SOP steps into validated tools before deployment.
- Production agent reduces p50 latency by 42% and end-to-end error rates by 53%.
- Direct tool calls simplify architecture, further reducing latency by 62% in controlled tests.
- Versioned tools improve auditability and expose specification gaps and data drift.
- Demonstrates the effectiveness of self-evolving agents in enhancing system performance.
DeepSignal Analysis
What happened
A new tool-making pipeline for LLM agents has been implemented in a Fulfillment Center alarm-triage system, leading to significant reductions in latency and error rates. By compiling procedural steps into validated tools, the system enhances reliability and operational efficiency.
Key evidence
- The tool-making pipeline reduces p50 latency by 42% in the Fulfillment Center alarm-triage system.
- The implementation lowers the end-to-end error rate by up to 53% on 1,500 historical alarms by minimizing run-to-run variance.
- Versioned tools improve auditability and help identify specification gaps and upstream data drift.
Why it matters
This development indicates a shift towards more efficient LLM systems in industrial applications, potentially leading to faster and more reliable operations. The ability of self-evolving agents to create and validate tools could streamline processes and reduce operational complexities, which is crucial for industries reliant on real-time data processing.
What to watch
Future research should focus on the scalability of this approach across different industrial applications and its long-term reliability. Additionally, understanding the limitations of the tool-making pipeline and its performance in diverse environments will be essential for broader adoption.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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 self-evolving agents can make industrial LLM systems faster, more reliable, and easier to operate.
| Comments: | Preprint |
| Subjects: | Computation and Language (cs.CL); Machine Learning (cs.LG); Software Engineering (cs.SE) |
| Cite as: | arXiv:2607.08010 [cs.CL] |
| (or arXiv:2607.08010v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2607.08010 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kalle Kujanpää [view email]
[v1]
Thu, 9 Jul 2026 00:27:13 UTC (74 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →TriAgent: Divergence-Aware Committees for Cost-Efficient Financial Sentiment Analysis
TriAgent introduces a cost-efficient multi-agent system for financial sentiment analysis, combining VADER, FinBERT, and Qwen2.5. It achieves an F1 score of ~0.87 with significant savings of $9.3M/year at a 10M-user scale compared to GPT-4o-mini, while also detecting hallucinations with an AUC of 0.90.