Lune

ACL Findings2026

Invocation Refiner: A Plug-and-Play Module for Rectifying LLM Tool Invocations

Qirui Jiao, Dian Jiao, Nan Du, Ying Shen, Liang Lin

Abstract

Large Language Models (LLMs) have shown remarkable capabilities in Tool-Integrated Reasoning (TIR). However, the practical application is often hindered by frequent errors in tool invocations, such as incorrect parameters or malformed formats. Prevailing training paradigms, such as Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), can mitigate these issues but require modification on the base LLM. This lack of modularity necessitates extensive retraining when deploying the system across different base models. To address the limitation, we introduce the Invocation Refiner, a specialized post-processing module designed to enhance the tool-use reliability of base LLMs without directly training on them. The Refiner takes the output from a frozen upstream LLM and the user's query as input, performing independent reasoning to rectify the invocation. We construct a dedicated training dataset and train this module using an advanced RL algorithm. On a diverse set of tool-use and reasoning benchmarks, our Refiner improves task completion rates and invocation accuracy over the raw outputs of various upstream LLMs. This highlights our Refiner as a plug-and-play solution for improving the operational reliability of LLM-based agents. We release our code to facilitate future research.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • DAPO: An Open-Source LLM Reinforcement Learning System at Scale cites Teaching Large Language Models to Self-Debug
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on24

  1. Toolformer: Language Models Can Teach Themselves to Use ToolsTimo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu et al.NeurIPS 2023 · 5,989 citations
  2. DAPO: An Open-Source LLM Reinforcement Learning System at ScaleQiying Yu, Zheng Zhang, Ruofei Zhu, Yufeng Yuan et al.NeurIPS 2025 · 2,828 citations
  3. Teaching Large Language Models to Self-DebugXinyun Chen, Maxwell Lin, Nathanael Schärli, Denny ZhouICLR 2024 · 1,085 citations
  4. Efficient Memory Management for Large Language Model Serving with PagedAttentionWoosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng et al.SOSP 2023 · 1,016 citations
  5. MAmmoTH: Building Math Generalist Models through Hybrid Instruction TuningXiang Yue, Xingwei Qu, Ge Zhang, Yao Fu et al.ICLR 2024 · 558 citations

Related papers

  1. Tool-Star: Empowering Multi-Tool Collaborative Web Agent via Reinforcement LearningGuanting Dong, Yifei Chen, Xiaoxi Li, Jiajie Jin et al.SIGIR 2026 · 1 citation
  2. The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use AgentsWeihao Xuan, Qingcheng Zeng, Heli Qi, Yunze Xiao et al.ACL 2026 · 4 citations
  3. UFT: Unifying Supervised and Reinforcement Fine-TuningMingyang Liu, Gabriele Farina, Asuman OzdaglarNeurIPS 2025 · 61 citations
  4. Beyond Prompt Engineering: A Reinforced Token-Level Input Refinement for Large Language ModelsGuang Huang, Yanan Xiao, Lu Jiang, Minghao Yin et al.AAAI 2025 · 2 citations
  5. Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMsJaemin Kim, Hangeol Chang, Hyunmin Hwang, Choonghan Kim et al.ICML 2026 · 1 citation
Dusk over the sea between two cliffs drawn in fine vertical lines