Metraipolis › archive › dc_8a4a3429fa19
I-PTC: Interactive Programmatic Tool Calling for Stateful Tool-Augmented Agents — arXiv:2611.01446
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01446
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:52:37.008Z
- SHA-256 of the archived text
1a29cb35d5f75d65e094418d6670fd28179e5ad19523939caf63b9d318c31be3- Stable URL of this page
https://metraipolis.com/documento/dc_8a4a3429fa19
How to cite
I-PTC: Interactive Programmatic Tool Calling for Stateful Tool-Augmented Agents — arXiv:2611.01446 — arXiv (en), https://arxiv.org/abs/2611.01446 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8a4a3429fa19 (Metraipolis archive dc_8a4a3429fa19, sha256 1a29cb35d5f75d65e094418d6670fd28179e5ad19523939caf63b9d318c31be3)
BibTeX
@misc{dc8a4a3429fa19,
title = {I-PTC: Interactive Programmatic Tool Calling for Stateful Tool-Augmented Agents — arXiv:2611.01446},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01446},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8a4a3429fa19; sha256 1a29cb35d5f75d65e094418d6670fd28179e5ad19523939caf63b9d318c31be3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01446. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large language models are increasingly capable of writing and executing code, suggesting a natural paradigm for tool-augmented agents: expressing tool use as programs rather than isolated calls. Programmatic tool calling (PTC) captures this idea through loops, batching, abstraction, and structured computation, but existing PTC approaches are largely stateless, limiting their ability to reuse intermediate results and adapt over time. This is problematic for real-world tasks, where tool environments and problem-solving processes are inherently stateful. We therefore present I-PTC, an interactive framework that executes stateful PTC: models issue code snippets that call tools, maintain reusable state, and evolve the tool interface through API corrections. To evaluate the effectiveness of I-PTC and the general PTC setting, we introduce PTC-Bench, a benchmark of long-tail, production-style user requests whose difficulty comes from large initial environments, many dependent API interactions, extended planning, and recovery across follow-ups and transient failures. Experiments on PTC-Bench show that I-PTC improves performance on complex multi-step tasks with large tool sets while substantially reducing token consumption over conventional tool-calling baselines and the original PTC baseline, highlighting stateful programmatic tool calling as a promising direction for scalable tool-augmented agents. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.01446 — 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 2026-11-03T10:49:38.304Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).