# AdaptAgent: A Multi-agent, Domain-Guided Reasoning Framework for Code Adaptation

arXiv: https://arxiv.org/abs/2608.04459 · HTML: https://mlsanity.com/paper/2608.04459/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 5 Aug 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 19 of 19)

- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [CodeT: Code Generation with Generated Tests](https://mlsanity.com/paper/2207.10397/) (2022)
- [ChatGPT as a Factual Inconsistency Evaluator for Text Summarization](https://mlsanity.com/paper/2303.15621/) (2023)
- [Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2502.10708/) (2025)
- [Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering](https://mlsanity.com/paper/2305.11541/) (2023)
- [ARJA: Automated Repair of Java Programs via Multi-Objective Genetic Programming](https://mlsanity.com/paper/1712.07804/) (2017)
- [Hybrid Automated Program Repair by Combining Large Language Models and Program Analysis](https://mlsanity.com/paper/2406.00992/) (2024)
- [Stack Overflow Considered Harmful? The Impact of Copy&Paste on Android Application Security](https://mlsanity.com/paper/1710.03135/) (2017)
- [Aligning the Objective of LLM-based Program Repair](https://mlsanity.com/paper/2404.08877/) (2024)
- [Toxic Code Snippets on Stack Overflow](https://mlsanity.com/paper/1806.07659/) (2018)
- [Recommending Stack Overflow Posts for Fixing Runtime Exceptions using Failure Scenario Matching](https://mlsanity.com/paper/2009.10174/) (2020)
- [Analyzing and Supporting Adaptation of Online Code Examples](https://mlsanity.com/paper/1905.12111/) (2019)
- [Automated Code Editing with Search-Generate-Modify](https://mlsanity.com/paper/2306.06490/) (2023)
- [An Empirical Study of C++ Vulnerabilities in Crowd-Sourced Code Examples](https://mlsanity.com/paper/1910.01321/) (2019)
- [Integrating Planning into Single-Turn Long-Form Text Generation](https://mlsanity.com/paper/2410.06203/) (2024)
- [Prompt-tuned Code Language Model as a Neural Knowledge Base for Type Inference in Statically-Typed Partial Code](https://mlsanity.com/paper/2208.05361/) (2022)
- [Developer-LLM Conversations: An Empirical Study of Interactions and Generated Code Quality](https://mlsanity.com/paper/2509.10402/) (2025)
- [Optimising the Fit of Stack Overflow Code Snippets into Existing Code](https://mlsanity.com/paper/2004.07663/) (2020)
- [Answer Summarization for Technical Queries: Benchmark and New Approach](https://mlsanity.com/paper/2209.10868/) (2022)

## Abstract (arXiv)

Developers often need to adapt into their projects the code generated from LLMs or code snippets from online forums. However, integrating them into an existing repository remains challenging in a manual process. A successful integration typically requires more than copying code as a user must produce correct adapting changes at a designated location in the target repository. We formalize this as the code adaptation problem: given a snippet, functional intent, a target repository, and an adaptation location, generate a patch that adapts the snippet into the repository. We present AdaptAgent, a multi-agent, domain-guided reasoning framework for code adaptation. Rather than relying on single-shot prompting, AdaptAgent decomposes adaptation into specialized agents that communicate via typed artifacts: an Intent Summarizer extracts adaptation goals from Q&A text; a Policy Agent derives domain policies from six adaptation categories; a Domain Planner generates a self-ordered plan; a Context Miner distills sibling-method semantics from the target codebase; and a Code Adapter realizes the plan as a minimal unified diff, iteratively refined using a compiler-based Verifier. This division of labor enables robust, policy-aligned adaptations and supports adapting code snippets into a project. On a real-world dataset, AdaptAgent outperforms strong baselines in semantic correctness and produces patches that mirror developers' actual adaptation patterns. Our ablation study shows each agent's necessity, especially planning for code-hardening and exception-handling, and intent for logic customization.