Metraipolis › archive › dc_58cb84db4d47
ToolLIFT: Lifting Tool-Specific Trajectories into Function-Level Graphs for Generalizable Tool Planning — arXiv:2608.03468
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.03468
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:16:22.689Z
- SHA-256 of the archived text
9ec6a8322bd143d4108da02580d03fbf7f7e5063502bdbf27970dde18a376559- Stable URL of this page
https://metraipolis.com/documento/dc_58cb84db4d47
How to cite
ToolLIFT: Lifting Tool-Specific Trajectories into Function-Level Graphs for Generalizable Tool Planning — arXiv:2608.03468 — arXiv (en), https://arxiv.org/abs/2608.03468 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_58cb84db4d47 (Metraipolis archive dc_58cb84db4d47, sha256 9ec6a8322bd143d4108da02580d03fbf7f7e5063502bdbf27970dde18a376559)
BibTeX
@misc{dc58cb84db4d47,
title = {ToolLIFT: Lifting Tool-Specific Trajectories into Function-Level Graphs for Generalizable Tool Planning — arXiv:2608.03468},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.03468},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_58cb84db4d47; sha256 9ec6a8322bd143d4108da02580d03fbf7f7e5063502bdbf27970dde18a376559},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03468. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.03468 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-31T12:05:52.799Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).