# Adversarial Reasoning for Repair Based on Inferred Program Intent

arXiv: https://arxiv.org/abs/2505.13008 · HTML: https://mlsanity.com/paper/2505.13008/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 14 of its 84 references that are in the map.
- First posted on arXiv 19 May 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 14 of 14)

- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://mlsanity.com/paper/2401.07339/) (2024)
- [AutoCodeRover: Autonomous Program Improvement](https://mlsanity.com/paper/2404.05427/) (2024)
- [SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal](https://mlsanity.com/paper/2406.14598/) (2024)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [Impact of Code Language Models on Automated Program Repair](https://mlsanity.com/paper/2302.05020/) (2023)
- [SpecRover: Code Intent Extraction via LLMs](https://mlsanity.com/paper/2408.02232/) (2024)
- [Evaluating the Code Quality of AI-Assisted Code Generation Tools: An Empirical Study on GitHub Copilot, Amazon CodeWhisperer, and ChatGPT](https://mlsanity.com/paper/2304.10778/) (2023)
- [UniDebugger: Hierarchical Multi-Agent Framework for Unified Software Debugging](https://mlsanity.com/paper/2404.17153/) (2024)
- [SelfAPR: Self-supervised Program Repair with Test Execution Diagnostics](https://mlsanity.com/paper/2203.12755/) (2022)
- [Chain-of-Thought in Neural Code Generation: From and For Lightweight Language Models](https://mlsanity.com/paper/2312.05562/) (2023)
- [ContrastRepair: Enhancing Conversation-Based Automated Program Repair via Contrastive Test Case Pairs](https://mlsanity.com/paper/2403.01971/) (2024)
- [CigaR: Cost-efficient Program Repair with LLMs](https://mlsanity.com/paper/2402.06598/) (2024)
- [ChatDBG: Augmenting Debugging with Large Language Models](https://mlsanity.com/paper/2403.16354/) (2024)

## Built on by (most cited first, 2 of 2)

- [Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing](https://mlsanity.com/paper/2506.16136/) (2025)
- [Dissecting the SWE-Bench Leaderboards: Profiling Submitters and Architectures of LLM- and Agent-Based Repair Systems](https://mlsanity.com/paper/2506.17208/) (2025)

## Abstract (arXiv)

Automated program repair (APR) has shown promising results, particularly with the use of neural networks. Currently, most APR tools focus on code transformations specified by test suites, rather than reasoning about the program intent and the high-level bug specification. Without a proper understanding of program intent, these tools tend to generate patches that overfit incomplete test suites and fail to reflect the developers intentions. However, reasoning about program intent is challenging. In our work, we propose an approach called AdverIntent-Agent, based on critique and adversarial reasoning. Our approach is novel to shift the focus from generating multiple APR patches to inferring multiple potential program intents. Ideally, we aim to infer intents that are, to some extent, adversarial to each other, maximizing the probability that at least one aligns closely with the developers original intent. AdverIntent-Agent is a multi-agent approach consisting of three agents: a reasoning agent, a test agent, and a repair agent. First, the reasoning agent generates adversarial program intents along with the corresponding faulty statements. Next, the test agent produces adversarial test cases that align with each inferred intent, constructing oracles that use the same inputs but have different expected outputs. Finally, the repair agent uses dynamic and precise LLM prompts to generate patches that satisfy both the inferred program intent and the generated tests. AdverIntent-Agent was evaluated on two benchmarks: Defects4J 2.0 and HumanEval-Java. AdverIntent-Agent correctly repaired 77 and 105 bugs in both benchmarks, respectively.