Related papers: Close the Loop: Synthesizing Infinite Tool-Use Data via Multi-Agent Role-Playing

Close the Loop: Synthesizing Infinite Tool-Use Data via Multi-Agent Role-Playing

URL: http://arxiv.org/abs/2512.23611v1
Date: Mon, 29 Dec 2025 17:12:39 GMT
Title: Close the Loop: Synthesizing Infinite Tool-Use Data via Multi-Agent Role-Playing
Authors: Yuwen Li, Wei Zhang, Zelong Huang, Mason Yang, Jiajun Wu, Shawn Guo, Huahao Hu, Lingyi Sun, Jian Yang, Mingjie Tang, Byran Dai,
Abstract summary: InfTool orchestrates three collaborative agents to generate diverse, verified trajectories spanning single-turn calls to complex multi-step gated calls.<n>We show that InfTool transforms a base 32B model from 19.8% to 70.9% accuracy (+258%), surpassing models 10x larger and rivaling Claude-Opus.
Score: 16.839489120513505
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Enabling Large Language Models (LLMs) to reliably invoke external tools remains a critical bottleneck for autonomous agents. Existing approaches suffer from three fundamental challenges: expensive human annotation for high-quality trajectories, poor generalization to unseen tools, and quality ceilings inherent in single-model synthesis that perpetuate biases and coverage gaps. We introduce InfTool, a fully autonomous framework that breaks these barriers through self-evolving multi-agent synthesis. Given only raw API specifications, InfTool orchestrates three collaborative agents (User Simulator, Tool-Calling Assistant, and MCP Server) to generate diverse, verified trajectories spanning single-turn calls to complex multi-step workflows. The framework establishes a closed loop: synthesized data trains the model via Group Relative Policy Optimization (GRPO) with gated rewards, the improved model generates higher-quality data targeting capability gaps, and this cycle iterates without human intervention. Experiments on the Berkeley Function-Calling Leaderboard (BFCL) demonstrate that InfTool transforms a base 32B model from 19.8% to 70.9% accuracy (+258%), surpassing models 10x larger and rivaling Claude-Opus, and entirely from synthetic data without human annotation.

Related papers

Beyond Quantity: Trajectory Diversity Scaling for Code Agents [51.71414642763219]
Trajectory Diversity Scaling is a data synthesis framework for code agents that scales performance through diversity rather than raw volume.<n> TDScaling integrates four innovations: (1) a Business Cluster mechanism that captures real-service logical dependencies; (2) a blueprint-driven multi-agent paradigm that enforces trajectory coherence; and (3) an adaptive evolution mechanism that steers toward long-tail scenarios.
arXiv Detail & Related papers (2026-02-03T07:43:03Z)
From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents [23.583947864141162]
EigenData is a hierarchical multi-agent engine that synthesizes tool-grounded dialogues together with executable per-instance checkers.<n>Building on the synthetic data, we develop an RL recipe that first fine-tunes the user model and then applies GRPO-style training.<n>Our results suggest a scalable pathway for bootstrapping complex tool-using behaviors without expensive human annotation.
arXiv Detail & Related papers (2026-01-30T06:01:23Z)
Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text [48.25052564552558]
We introduce GEM, a data synthesis pipeline that enables the generation and extraction of multi-turn tool-use trajectories from text corpora.<n>To reduce the computational cost, we further train a specialized Trajectory Synthesizer via supervised fine-tuning.<n>Experiments demonstrate that our GEM-32B achieve a 16.5% improvement on the BFCL V3 Multi-turn benchmark.
arXiv Detail & Related papers (2026-01-15T12:58:46Z)
ToolMind Technical Report: A Large-Scale, Reasoning-Enhanced Tool-Use Dataset [43.45582911794623]
We introduce ToolMind, a high-quality tool-agentic dataset with 160k synthetic data instances.<n>We employ fine-grained turn-level filtering to remove erroneous or suboptimal steps.<n>Models fine-tuned on ToolMind show significant improvements over baselines on several benchmarks.
arXiv Detail & Related papers (2025-11-12T13:01:23Z)
LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls [46.34510189812439]
LoopTool is a fully automated, model-aware data evolution framework.<n>It iteratively refines both the data and the model through three synergistic modules.<n> Experiments show that our 8B model trained with LoopTool significantly surpasses its 32B data generator.
arXiv Detail & Related papers (2025-11-12T09:34:39Z)
Klear-AgentForge: Forging Agentic Intelligence through Posttraining Scaling [46.593200463657645]
We present a comprehensive and fully open-source pipeline for training a high-performance agentic model, named Klear-Qwen3-AgentForge.<n>We design effective supervised fine-tuning (SFT) with synthetic data followed by multi-turn reinforcement learning (RL) to unlock the potential for multiple diverse agentic tasks.
arXiv Detail & Related papers (2025-11-08T09:47:27Z)
One Model to Critique Them All: Rewarding Agentic Tool-Use via Efficient Reasoning [54.580646706013965]
Reward models (RMs) play a critical role in aligning large language models with human preferences.<n>We introduce ToolRM, a family of lightweight generative RMs tailored for general tool-use scenarios.<n>To build these models, we propose a novel pipeline that constructs pairwise preference data using rule-based scoring and multidimensional sampling.
arXiv Detail & Related papers (2025-10-30T06:08:27Z)
FunReason-MT Technical Report: Overcoming the Complexity Barrier in Multi-Turn Function Calling [39.45732462111156]
We present FunReason-MT, a novel data synthesis framework for real-world multi-turn tool use.<n>FunReason-MT resolves the complexity barrier in multi-turn FC data by employing Environment-API Graph Interactions.<n>A 4B model built upon FunReason-MT generated data achieves state-of-the-art performance among comparable-sized models.
arXiv Detail & Related papers (2025-10-28T17:15:26Z)
APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay [86.01901238059261]
APIGen-MT is a framework that generates verifiable and diverse multi-turn agent data.<n>We train a family of models -- the xLAM-2-fc-r series with sizes ranging from 1B to 70B parameters.<n>Our models outperform frontier models such as GPT-4o and Claude 3.5 on $tau$-bench and BFCL benchmarks.
arXiv Detail & Related papers (2025-04-04T17:13:57Z)
iTool: Reinforced Fine-Tuning with Dynamic Deficiency Calibration for Advanced Tool Use [56.31110409360567]
Augmenting large language models with external tools is a promising approach to enhance their capabilities.<n>We show that training gains significantly decay as synthetic data increases.<n>We propose an iterative reinforced fine-tuning strategy designed to alleviate this limitation.
arXiv Detail & Related papers (2025-01-15T04:52:34Z)
ToolACE: Winning the Points of LLM Function Calling [139.07157814653638]
ToolACE is an automatic agentic pipeline designed to generate accurate, complex, and diverse tool-learning data.<n>We demonstrate that models trained on our synthesized data, even with only 8B parameters, achieve state-of-the-art performance on the Berkeley Function-Calling Leaderboard.
arXiv Detail & Related papers (2024-09-02T03:19:56Z)
Tool-Augmented Reward Modeling [58.381678612409]
We propose a tool-augmented preference modeling approach, named Themis, to address limitations by empowering RMs with access to external environments. Our study delves into the integration of external tools into RMs, enabling them to interact with diverse external sources. In human evaluations, RLHF trained with Themis attains an average win rate of 32% when compared to baselines.
arXiv Detail & Related papers (2023-10-02T09:47:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.