# Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning

arXiv: https://arxiv.org/abs/2506.04625 · HTML: https://mlsanity.com/paper/2506.04625/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 69 references that are in the map.
- First posted on arXiv 5 Jun 2025.

## Builds on (most cited first, 30 of 35)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning](https://mlsanity.com/paper/2309.05653/) (2023)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models](https://mlsanity.com/paper/2304.09842/) (2023)
- [Tool Learning with Foundation Models](https://mlsanity.com/paper/2304.08354/) (2023)
- [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024)
- [ToolACE: Winning the Points of LLM Function Calling](https://mlsanity.com/paper/2409.00920/) (2024)
- [Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents](https://mlsanity.com/paper/2403.02502/) (2024)
- [EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction](https://mlsanity.com/paper/2401.06201/) (2024)
- [Multi-Step Reasoning with Large Language Models, a Survey](https://mlsanity.com/paper/2407.11511/) (2024)
- [StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models](https://mlsanity.com/paper/2403.07714/) (2024)
- [Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement](https://mlsanity.com/paper/2406.11176/) (2024)
- [A Survey of Large Language Models for Graphs](https://mlsanity.com/paper/2405.08011/) (2024)
- [Tool Learning in the Wild: Empowering Language Models as Automatic Tool Agents](https://mlsanity.com/paper/2405.16533/) (2024)
- [Learning to Use Tools via Cooperative and Interactive Agents](https://mlsanity.com/paper/2403.03031/) (2024)
- [What Are Tools Anyway? A Survey from the Language Model Perspective](https://mlsanity.com/paper/2403.15452/) (2024)
- [LeDex: Training LLMs to Better Self-Debug and Explain Code](https://mlsanity.com/paper/2405.18649/) (2024)

## Built on by (most cited first, 24 of 24)

- [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026)
- [SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents](https://mlsanity.com/paper/2602.14211/) (2026)
- [The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration](https://mlsanity.com/paper/2603.22862/) (2026)
- [ChainFuzzer: Greybox Fuzzing for Workflow-Level Multi-Tool Vulnerabilities in LLM Agents](https://mlsanity.com/paper/2603.12614/) (2026)
- [AutoPyVerifier: Learning Compact Executable Verifiers for Large Language Model Outputs](https://mlsanity.com/paper/2604.22937/) (2026)
- [FAMA: Failure-Aware Meta-Agentic Framework for Open-Source LLMs in Interactive Tool Use Environments](https://mlsanity.com/paper/2604.25135/) (2026)
- [RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement](https://mlsanity.com/paper/2605.09730/) (2026)
- [Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization](https://mlsanity.com/paper/2508.10164/) (2025)
- [Verification-Guided Context Optimization for Tool Calling via Hierarchical LLMs-as-Editors](https://mlsanity.com/paper/2512.13860/) (2025)
- [Teaching LLMs to Learn Tool Trialing and Execution through Environment Interaction](https://mlsanity.com/paper/2601.12762/) (2026)
- [What Makes Good Agentic Data? An ACE Lens on Data Generation for LLM Agents](https://mlsanity.com/paper/2608.27260/) (2026)
- [AGAPI-Agents: An Open-Access Agentic AI Platform for Accelerated Materials Design on AtomGPT.org](https://mlsanity.com/paper/2512.11935/) (2025)
- [MAGMA-GEN: Validated Recovery Supervision from Ambiguous Failures via Counterfactual Re-Execution](https://mlsanity.com/paper/2609.20056/) (2026)
- [Foundation of Intelligence: Review of Math Word Problems from Human Cognition Perspective](https://mlsanity.com/paper/2510.21999/) (2025)
- [DiG-Plan: Mitigating Early Commitment for Tool-Graph Planning via Diffusion Guidance](https://mlsanity.com/paper/2606.05728/) (2026)
- [Task-Aware Harness Provisioning for LLM Agents in Mission-Critical Infrastructure Operations](https://mlsanity.com/paper/2608.17433/) (2026)
- [Tool-Augmented Hybrid Ensemble Reasoning with Distillation for Bilingual Mathematical Problem Solving](https://mlsanity.com/paper/2512.19093/) (2025)
- [Agent Lifecycle Toolkit (ALTK): Reusable Middleware Components for Robust AI Agents](https://mlsanity.com/paper/2603.15473/) (2026)
- [AgentCAT: Simulating Computerized Adaptive Testing via Multi-Agent Large Language Models](https://mlsanity.com/paper/2606.21832/) (2026)
- [SkillBloat: Token Amplification Attacks via Skill Injection in LLM Coding Agents](https://mlsanity.com/paper/2608.21929/) (2026)
- [Behavior2Trip: Towards Personalized Travel Planning via User Behavior Trajectory](https://mlsanity.com/paper/2608.26807/) (2026)
- [Grounded Skill Synthesis from Code at Scale for Agentic Intelligence](https://mlsanity.com/paper/2609.05571/) (2026)
- [RSure-Agent: Reliable Use of Tool Observations for Remote Sensing Agents](https://mlsanity.com/paper/2610.04836/) (2026)
- [Plan or Retrieve First? A Scale Study of Tool Discovery Architectures](https://mlsanity.com/paper/2610.19068/) (2026)

## Abstract (arXiv)

Empowering large language models (LLMs) with effective tool utilization capabilities is crucial for enabling AI agents to solve complex problems. However, current models face two major limitations: (1) unreliable tool planning and invocation due to low-quality instruction datasets (e.g., widespread hallucinated API calls), and (2) weak tool reflection abilities (over 90% of errors cannot be corrected) resulting from static imitation learning. To address these critical limitations, we propose Tool-MVR, a novel Tool-Augmented LLM that achieves comprehensive System 2 reasoning through two key innovations. Specifically, we first introduce Multi-Agent Meta-Verification (MAMV), a systematic pipeline that rigorously validates APIs, queries, and reasoning trajectories to construct ToolBench-V, a new high-quality instruction dataset that addresses the limitation of unreliable tool planning and invocation. Second, we propose Exploration-based Reflection Learning (EXPLORE), which enhances tool reflection capabilities by leveraging tool feedback through a dynamic "Error -> Reflection -> Correction" learning paradigm, resulting in our reflection dataset ToolBench-R and addressing the critical weakness in tool reflection. Finally, we obtain Tool-MVR by finetuning open-source LLMs (e.g., Qwen-7B) on both ToolBench-V and ToolBench-R. Our experiments demonstrate that Tool-MVR achieves state-of-the-art performance on StableToolBench, surpassing both ToolLLM (by 23.9%) and GPT-4 (by 15.3%) while reducing API calls by 31.4%, with strong generalization capabilities across unseen tools and scenarios. Additionally, on our proposed RefineToolBench, the first benchmark specifically designed to evaluate tool reflection capabilities, Tool-MVR achieves a 58.9% error correction rate, significantly outperforming ToolLLM's 9.1%.