Tool-Use Planning

Follow this topic Ask about this topic

Momentum

0 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 12

All topics

ToolLIFT: Lifting Tool-Specific Trajectories into Function-Level Graphs for Generalizable Tool Planning
Aug 4, 2026Xiuhui You, Jiayi Luo, Zichao Shen +2Tool-Use Planning Tool Use
School of Computer Science and Engineering · Beihang University
Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents
Jun 10, 2026Kushal Raj Bhandari, Ling Yue, Ching-Yun Ko +4Inference-Time Search LLM Agent Workflow Optimization
Rensselaer Polytechnic Institute, Troy, NY 12180 USA · IBM Research, Yorktown Heights, NY 10598 USA
Beyond APIs: Probing the Limits of MLLMs in Physical Tool Use
Jun 9, 2026Zhixin Ma, Yutong Zhou, Yongqi Li +2Tool Use in VLMs Tool-Use Planning
Singapore Management University · The Hong Kong Polytechnic University
QueryWeaver: Reliable Multi-Tool Query Execution Planning via LLM-Based Graph Generation
Jun 6, 2026Aishwarya Chakravarthy, Vidhi Kulkarni, Duen Horng ChauTool-Augmented Language Model Agents Tool-Use Planning
School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, GA, USA.
DiG-Plan: Mitigating Early Commitment for Tool-Graph Planning via Diffusion Guidance
Jun 4, 2026Yansi Li, Zhuosheng ZhangDiffusion-Based Planning LLM Planning
School of Computer Science, Shanghai Jiao Tong University
DisasterBench: Benchmarking LLM Planning under Typed Tool Interface Constraints
May 27, 2026Zhitong Chen, Kai Yin, Weifeng Zhang +7Tool-Use Planning AI Agent Benchmarks
Texas A&M University · University of Toronto
SPIN: Structural LLM Planning via Iterative Navigation for Industrial Tasks
May 13, 2026Yusuke Ozaki, Dhaval PatelLLM Agent Workflow Optimization Tool-Use Planning
University at Albany · Kwansei Gakuin University · IBM, New York
GRAFT: Graph-Tokenized LLMs for Tool Planning
May 12, 2026Xinyi Gao, Xinyu Ren, Junliang Yu +3Tool-Use Planning Language Modeling
The University of Queensland · Griffith University
Tools as Continuous Flow for Evolving Agentic Reasoning
May 8, 2026Tairan Huang, Siyu Shang, Qiang Chen +2Tool-Use Planning AI Agent Benchmarks
Central South University · The Hong Kong University of Science and Technology
Bridging Perception and Action: A Lightweight Multimodal Meta-Planner Framework for Robust Earth Observation Agents
May 6, 2026Jinghui Xu, Boyi Shangguan, Mengke Zhu +10Remote Sensing Tool-Use Planning
State Key Laboratory of Space Information System and Integrated Application, Beijing 100095, China · Beijing Institute of Satellite Information Engineering, Beijing 100095, China · Shenzhen International Graduate School, Tsinghua University, Shenzhen, China +2
SceneOrchestra: Efficient Agentic 3D Scene Synthesis via Full Tool-Call Trajectory Generation
Apr 21, 2026Yun He, Kelin Yu, Matthias ZwickerLLM Agent Orchestration Tool-Use Planning
University of Maryland, College Park
PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning
Feb 14, 2026Yu Li, Guangfeng Cai, Shengtian Yang +5LLM-Guided RL Tool-Use Planning
School of Computer Science and Engineering, Southeast University, Nanjing, China · Huawei Noah’s Ark Lab, China

Aug 4, 2026, cs.AIJ/K move · Enter open · S save

ToolLIFT: Lifting Tool-Specific Trajectories into Function-Level Graphs for Generalizable Tool Planning

Xiuhui You, Jiayi Luo, Zichao Shen, Qingyun Sun+1

School of Computer Science and Engineering · Beihang University

Tool-Use Planning Tool Use

Open paper AskPDF arXiv

Historical tool-use trajectories provide valuable experience for large language model (LLM) agents to plan and coordinate tool usage. Existing approaches directly construct tool-level graphs from these trajectories, but the resulting graphs remain tied to specific tools and are hard to generalize across tool sets. To tackle this challenge, we find that despite differences in the tools involved, analogous tasks often share a common function-level workflow structure, which serves as a potentially more transferable abstraction for tool planning. Based on this insight, we propose ToolLIFT, a framework that lifts tool-specific trajectories into a function-level workflow graph (FWG) for generalizable tool planning. Specifically, we first propose a trajectory-lifting mechanism that encodes workflow structures in the FWG and shares collaboration experience across tools. Then, building on the global structure of the FWG, we introduce decoupled workflow planning and tool selection to align individual tool choices with the overall workflow. Lastly, to ensure reliable tool dataflow, we adopt Reinforcement Learning (RL) and propose source-gated and skill-specific rewards to maintain source-traceable information flow across tool calls. Experiments on two in-distribution (ID) and three out-of-distribution (OOD) benchmarks show that ToolLIFT consistently outperforms state-of-the-art baselines, demonstrating strong generalization to unseen tool sets.

Momentum

Related topics

Latest papers 12