Tool-Augmented Language Model Agents

Follow this topic Ask about this topic

Momentum

17 papers in the last four weeks, up 42% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 132

All topics

AgenticQwen: Training Small Agentic Language Models with Dual Data Flywheels for Industrial-Scale Tool Use
Apr 23, 2026Yuanjie Lyu, Chengyu Wang, Haonan Zheng +4Tool-Augmented Language Model Agents Agentic RL
Alibaba Group, Hangzhou, China
When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors
Apr 23, 2026Chenghao Yang, Yuning Zhang, Zhoufutu Wen +4Tool-Augmented Language Model Agents LLM Agent Evaluation
School of Cyber Science and Technology, USTC · Anhui Province Key Laboratory of Digital Security · 3M-A-P +1
Rethinking Scale: Deployment Trade-offs of Small Language Models under Agent Paradigms
Apr 21, 2026Xinlin Wang, Mats BrorssonMulti-Agent LLM Systems Tool-Augmented Language Model Agents
Proximus Luxembourg S.A. · rue du Puits Romain · L-8070 Bertrange, Luxembourg +3
GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)
Apr 18, 2026Jiaqing Liang, Jinyi Han, Weijia Li +15Tool-Augmented Language Model Agents LLM Agent Memory
Advantage AI Agent Lab (A3 Lab)
Evaluating Tool-Using Language Agents: Judge Reliability, Propagation Cascades, and Runtime Mitigation in AgentProp-Bench
Apr 17, 2026Bhaskar GurramAI Agent Reliability Tool-Augmented Language Model Agents
Zasti Inc., Ashburn, VA, USA
Agent-Facing Information Design in LLM Tool Registries: A Preregistered Test of Rhetoric, Position and Structure
Apr 12, 2026Haochuan Kevin Wang, Zechen ZhangTool-Use Evaluation Tool-Augmented Language Model Agents
Massachusetts Institute of Technology, Cambridge, MA, USA.
LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks
Mar 20, 2026Xiang Long, Li Du, Yilong Xu +11Computer-Use Agent Benchmarks Tool-Augmented Language Model Agents
Samsung Research, Beijing, China · HKUST (Guangzhou) · City University of Hong Kong +1
Automated Standardization of Legacy Biomedical Metadata Using an Ontology-Constrained LLM Agent
Mar 10, 2026Josef Hardi, Martin J. O'Connor, Marcos Martinez-Romero +3Tool-Augmented Language Model Agents
Division of Computational Medicine, Stanford University, Stanford, CA, USA · Department of Biology, University of Pennsylvania, Philadelphia, USA
Beyond Semantic Similarity: Reducing Unnecessary API Calls via Behavior-Aligned Retriever
Aug 20, 2025Yixin Chen, Ying Xiong, Shangyu Wu +4In-Context Example Selection In-Context Retrieval
City University of Hong Kong · Mohamed Bin Zayed University of Artificial Intelligence · McGill University
CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval
Date pendingVaishali Senthil, Ashutosh Hathidara, Sebastian SchreiberTool-Augmented Language Model Agents LLM Tool Use
SAP Labs
Palmyra x6 Technical Report: An Agentic, Tool-Use Model Post-Trained via Anchored Supervised Fine-Tuning
Date pendingPeng Du, Kiran Kamble, Rakshith Vasudev +5Supervised Fine-Tuning Tool-Augmented Language Model Agents
Writer AI Research, Writer, Inc.
Graph-of-Skills: Dependency-Aware Structural Retrieval for Massive Agent Skills
Date pendingDawei Liu, Zongxia Li, Hongyang Du +4Tool-Augmented Language Model Agents Graph-Based Retrieval
University of Pennsylvania · University of Maryland · Brown University +2

Apr 23, 2026, cs.CLJ/K move · Enter open · S save

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

Yuanjie Lyu, Chengyu Wang, Haonan Zheng, Yuanhao Yue+3

Alibaba Group, Hangzhou, China

Tool-Augmented Language Model Agents Agentic RL Synthetic Data Generation RL for Language Model Reasoning LLM Tool Use LLM Agent Training+1

Open paper AskPDF arXiv

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.

Momentum

Related topics

Latest papers 132