Learning API Functionality from In-Context Demonstrations for Tool-based Agents

Bhrij Patel, Ashish Jagmohan, Aditya Vempaty


Abstract
Digital tool-based agents, powered by Large Language Models (LLMs), that invoke external Application Programming Interfaces (APIs) often rely on documentation to understand API functionality. However, such documentation is frequently missing, outdated, privatized, or inconsistent—hindering the development of reliable, general-purpose agents. In this work, we propose a new research direction: learning of API functionality directly from in-context demonstrations. This task is a new paradigm applicable in scenarios without documentation. Using API benchmarks, we collect demonstrations from both expert agents and from self-exploration. To understand what information demonstrations must convey for successful task completion, we extensively study how the number of demonstrations and the use of LLM-generated summaries and evaluations affect the task success rate of the API-based agent. Our experiments across 3 datasets and 6 models show that learning functionality from in-context demonstrations remains a non-trivial challenge, even for state-of-the-art LLMs. We find that providing explicit function calls and natural language critiques significantly improves the agent’s task success rate due to more accurate parameter filling. We analyze failure modes, identify sources of error, and highlight key open challenges for future work in documentation-free, self-improving, API-based agents.
Anthology ID:
2025.findings-emnlp.994
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
18318–18336
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.994/
DOI:
Bibkey:
Cite (ACL):
Bhrij Patel, Ashish Jagmohan, and Aditya Vempaty. 2025. Learning API Functionality from In-Context Demonstrations for Tool-based Agents. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 18318–18336, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Learning API Functionality from In-Context Demonstrations for Tool-based Agents (Patel et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.994.pdf
Checklist:
 2025.findings-emnlp.994.checklist.pdf