AgenticQwen: Training Small Agentic Language Models with Dual Data Flywheels for Industrial-Scale Tool Use

• URL: http://arxiv.org/abs/2604.21590v1
• Date: Thu, 23 Apr 2026 12:14:52 GMT
• Title: AgenticQwen: Training Small Agentic Language Models with Dual Data Flywheels for Industrial-Scale Tool Use
• Abstract summary: We introduce the AgenticQwen family of models, trained via multi-round reinforcement learning (RL) on synthetic data and a limited amount of open-source data.<n>Our training framework combines reasoning RL and agentic RL with dual data flywheels that automatically generate increasingly challenging tasks.<n>The models achieve strong performance on multiple agentic benchmarks, and in our industrial agent system, close the gap with much larger models on search and data analysis tasks.
• Score: 13.583197273673974
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern industrial applications increasingly demand language models that act as agents, capable of multi-step reasoning and tool use in real-world settings. These tasks are typically performed under strict cost and latency constraints, making small agentic models highly desirable. In this paper, we introduce the AgenticQwen family of models, trained via multi-round reinforcement learning (RL) on synthetic data and a limited amount of open-source data. Our training framework combines reasoning RL and agentic RL with dual data flywheels that automatically generate increasingly challenging tasks. The reasoning flywheel increases task difficulty by learning from errors, while the agentic flywheel expands linear workflows into multi-branch behavior trees that better reflect the decision complexity of real-world applications. We validate AgenticQwen on public benchmarks and in an industrial agent system. The models achieve strong performance on multiple agentic benchmarks, and in our industrial agent system, close the gap with much larger models on search and data analysis tasks. Model checkpoints and part of the synthetic data: https://huggingface.co/collections/alibaba-pai/agenticqwen. Data synthesis and RL training code: https://github.com/haruhi-sudo/data_synth_and_rl. The data synthesis pipeline is also integrated into EasyDistill: https://github.com/modelscope/easydistill.

Related papers

• AI Scientist via Synthetic Task Scaling [2.056976961583532]
  We provide a novel synthetic environment generation pipeline targeting machine learning agents.<n>Our pipeline automatically synthesizes machine learning challenges compatible with the SWE-agent framework.<n>We tackle MLGym, a benchmark for machine learning tasks.
  arXiv  Detail & Related papers  (2026-03-17T23:43:16Z)
• 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)
• Mock Worlds, Real Skills: Building Small Agentic Language Models with Synthetic Tasks, Simulated Environments, and Rubric-Based Rewards [13.784988950752195]
  Existing open-source agentic training data are narrow in task variety and easily solved.<n>Real-world APIs lack diversity and are unstable for large-scale reinforcement learning rollout processes.<n>We address these challenges with SYNTHAGENT, a framework that jointly synthesizes diverse tool-use training data and simulates complete environments.
  arXiv  Detail & Related papers  (2026-01-30T03:43:42Z)
• Agent2World: Learning to Generate Symbolic World Models via Adaptive Multi-Agent Feedback [51.22403664895878]
  Agent2World is a tool-augmented multi-agent framework that achieves strong inference-time world-model generation.<n>It also serves as a data engine for supervised fine-tuning, by grounding generation in multi-agent feedback.
  arXiv  Detail & Related papers  (2025-12-26T18:54:14Z)
• Intention-Conditioned Flow Occupancy Models [80.42634994902858]
  Large-scale pre-training has fundamentally changed how machine learning research is done today.<n>Applying this same framework to reinforcement learning is appealing because it offers compelling avenues for addressing core challenges in RL.<n>Recent advances in generative AI have provided new tools for modeling highly complex distributions.
  arXiv  Detail & Related papers  (2025-06-10T15:27:46Z)
• 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)
• xLAM: A Family of Large Action Models to Empower AI Agent Systems [111.5719694445345]
  We release xLAM, a series of large action models designed for AI agent tasks. xLAM consistently delivers exceptional performance across multiple agent ability benchmarks.
  arXiv  Detail & Related papers  (2024-09-05T03:22:22Z)
• Retrieval-Augmented Reinforcement Learning [63.32076191982944]
  We train a network to map a dataset of past experiences to optimal behavior. The retrieval process is trained to retrieve information from the dataset that may be useful in the current context. We show that retrieval-augmented R2D2 learns significantly faster than the baseline R2D2 agent and achieves higher scores.
  arXiv  Detail & Related papers  (2022-02-17T02:44:05Z)
• InPars: Data Augmentation for Information Retrieval using Large Language Models [5.851846467503597]
  In this work, we harness the few-shot capabilities of large pretrained language models as synthetic data generators for information retrieval tasks. We show that models finetuned solely on our unsupervised dataset outperform strong baselines such as BM25. retrievers finetuned on both supervised and our synthetic data achieve better zero-shot transfer than models finetuned only on supervised data.
  arXiv  Detail & Related papers  (2022-02-10T16:52:45Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.