Repairing Tool Calls Using Post-tool Execution Reflection and RAG

2025-10-17 · Jason Tsay, Zidane Wright, Gaodan Fang, Kiran Kate, Saurabh Jha, Yara Rizk arxiv

Agentic systems interact with external systems by calling tools such as Python functions, REST API endpoints, or command line tools such as kubectl in Kubernetes. These tool calls often fail for various syntactic and semantic reasons. Some less obvious semantic errors can only be identified and resolved after analyzing the tool's response. To repair these errors, we develop a post-tool execution reflection component that combines large language model (LLM)-based reflection with domain-specific retrieval-augmented generation (RAG) using documents describing both the specific tool being called and troubleshooting documents related to the tool. For this paper, we focus on the use case of the kubectl command line tool to manage Kubernetes, a platform for orchestrating cluster applications. Through a larger empirical study and a smaller manual evaluation, we find that our RAG-based reflection will repair kubectl commands such that they are both more likely to successfully execute (pass rate) for 55% of our models evaluated and 36% more likely to correctly answer the user query on average. We find that troubleshooting documents improve pass rate compared to official documentation by an average of 10%.

📄 PDF Abstract BibTeX arXiv:2510.17874

Code (0)

등록된 구현이 없습니다.

TVCACHE: A Stateful Tool-Value Cache for Post-Training LLM Agents

2026-02-11 · Abhishek Vijaya Kumar, Bhaskar Kataria, Byungsoo Oh, Emaad Manzoor 외 arxiv

In RL post-training of LLM agents, calls to external tools take several seconds or even minutes, leaving allocated GPUs idle and inflating post-training time and cost. While many tool invocations repeat across parallel r…

Robust and Efficient Tool Orchestration via Layered Execution Structures with Reflective Correction

2026-02-21 · Tao Zhe, Haoyu Wang, Bo Luo, Min Wu 외 arxiv

Tool invocation is a core capability of agentic systems, yet failures often arise not from individual tool calls but from how multiple tools are organized and executed together. Existing approaches tightly couple tool ex…

Minimal Multi-Layer Modifications of Deep Neural Networks

2021-10-18 · Idan Refaeli, Guy Katz

Deep neural networks (DNNs) have become increasingly popular in recent years. However, despite their many successes, DNNs may also err and produce incorrect and potentially fatal outputs in safety-critical settings, such…

Autonomous Driving Collision Avoidance Medical Diagnosis

HyperTool: Beyond Step-Wise Tool Calls for Tool-Augmented Agents

2026-06-11 · Yaxin Du, Yifan Zhou, Yujie Ge, Jiajun Wang 외 arxiv

Tool-augmented LLM agents commonly rely on step-wise atomic tool calls, where each invocation, observation, and value transfer is exposed in the main reasoning trace. This creates an \emph{execution-granularity mismatch}…

Optimizing Agentic Workflows using Meta-tools

2026-01-29 · Sami Abuzakuk, Anne-Marie Kermarrec, Rishi Sharma, Rasmus Moorits Veski 외 arxiv

Agentic AI enables LLM to dynamically reason, plan, and interact with tools to solve complex tasks. However, agentic workflows often require many iterative reasoning steps and tool invocations, leading to significant ope…