APIDA-Chat: Structured Synthesis of API Search Dialogues to Bootstrap Conversational Agents
On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks
Abstract (arXiv)
Large-language-model assistants are suitable for explaining popular APIs, yet they falter on niche or proprietary libraries because the multi-turn dialogue data needed for fine-tuning are scarce. We present APIDA-Chat, an open-source pipeline that converts symbolic dialogue-act "scripts" into realistic, domain-grounded API Search conversations using a lightweight model for inexpensive training data generation. Phase I pairs a legacy dialogue planner with a high-capability teacher LLM (o4-mini) to synthesize a "gold set" of realized dialogues; then, a smaller Llama 3.2 3B student model is fine-tuned on this corpus. Phase II drops the teacher and reuses the same planner with the fine-tuned model, allowing rapid, low-cost synthesis of new dialogues without exposing source code to external services. The fine-tuned student improves BLEU from 0.38 to 0.50 and BERTScore from 0.88 to 0.91 versus the base model while running entirely on a single consumer GPU. All components are modular and publicly released to serve as a conservative baseline for future work. APIDA-Chat is open-sourced at https://github.com/Zeberhart/apida-chat and a video demo is available at https://youtu.be/YqmZBHyGbPs .
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 10 of its 12 references that are in the map. First posted on arXiv 4 Oct 2025.
Builds on
10 of 12 references.
References · 10
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
- 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,674
- 2025Synthetic Data Generation Using Large Language Models: Advances in Text and Codecited by 61
- 2024Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledgecited by 49
- 2024Using AI-Based Coding Assistants in Practice: State of Affairs, Perceptions, and Ways Forwardcited by 44
- 2023Ada-Instruct: Adapting Instruction Generators for Complex Reasoningcited by 11
- 2025Wizard of Shopping: Target-Oriented E-commerce Dialogue Generation with Decision Tree Branchingcited by 10
- 2024CoPrUS: Consistency Preserving Utterance Synthesis towards more realistic benchmark dialoguescited by 2
- 2025Single- vs. Dual-Prompt Dialogue Generation with LLMs for Job Interviews in Human Resourcescited by 2
- 2021Dialogue Management for Interactive API Searchcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language Models
- 2026TAMUSA-Chat: A Domain-Adapted Large Language Model Conversational System for Research and Responsible Deployment
- 2026ATOD: An Evaluation Framework and Benchmark for Agentic Task-Oriented Dialogue Systems
- 2025InfoQuest: Evaluating Multi-Turn Dialogue Agents for Open-Ended Conversations with Hidden Context
- 2025SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation
- 2024Simulating Task-Oriented Dialogues with State Transition Graphs and Large Language Models
- 2026ToolRACER: A Robust Agentic Conversation Emulation Resource for Agent Training and Evaluation
- 2025MMAT-1M: A Large Reasoning Dataset for Multimodal Agent Tuning