Adversarial Reasoning for Repair Based on Inferred Program Intent

• URL: http://arxiv.org/abs/2505.13008v2
• Date: Fri, 20 Jun 2025 12:30:23 GMT
• Title: Adversarial Reasoning for Repair Based on Inferred Program Intent
• Abstract summary: We propose an approach called AdverIntent-Agent, based on critique and adversarial reasoning.<n>Our approach is novel to shift the focus from generating multiple APR patches to inferring multiple potential program intents.<n> AdverIntent-Agent was evaluated on two benchmarks: Defects4J 2.0 and HumanEval-Java.
• Score: 12.923634025700826
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Adversarial Testing of Automated Program Repair Agents for Security Vulnerabilities [14.543680943818975]
  Software agents with Large Language Models (LLMs) are designed for Automated Program Repair (APR) tasks.<n>Can we trust an APR agent to produce both correct and secure code in such situations?<n>What if attackers target production APR agents with adversarial issues that seem benign but may influence the agents to produce correct but insecure code?
  arXiv  Detail & Related papers  (2026-09-14T17:53:49Z)
• Finding Where the Buck Stops: An Automated Failure Attribution-Based Reflection Framework for Multi-Agent Collaboration [14.41671360589919]
  DoCtOR (Diagnose-then-Correct PPO-enhanced Reflection) is a novel reflection framework that enhances multi-agent collaboration.<n>DoCtOR achieves 22%, 26%, and 27% improvements over initial success rates on HotPotQA, ChartQAPro, and Mind2Web datasets.
  arXiv  Detail & Related papers  (2026-08-28T12:26:03Z)
• Latent Programming Horizons in Coding Agents [6.8463578914435645]
  coding agent solving a software-engineering task spends dozens of steps reasoning, editing code, and running tests.<n>We show that the residual streams of language models under coding agents linearly encode properties of the evolving program.<n> Probes trained to predict the outcome of future edits achieve performance above chance up to roughly 25 steps in advance.
  arXiv  Detail & Related papers  (2026-07-06T15:08:26Z)
• Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories [51.22051230894794]
  Evaluation based on final answers shows whether an agent succeeds, but not which parts of the trajectory make the answer unreliable.<n>We collect 2,790 real trajectories from two agent frameworks, three backbone models, and three benchmarks, convert raw logs into semantic spans, and annotate harmful error spans through expert review.<n>We propose DRIFT, a claim-centric auditing framework that tracks agent claims, checks their support in trajectory evidence, and marks spans where unsupported or conflicting claims affect the answer path.
  arXiv  Detail & Related papers  (2026-06-01T10:50:26Z)
• Project Prometheus: Bridging the Intent Gap in Agentic Program Repair via Reverse-Engineered Executable Specifications [14.657771106188115]
  Current solutions relying on natural language summaries or adversarial sampling often fail to provide the deterministic constraints required for surgical repairs.<n>We introduce textscPrometheus, a novel framework that bridges this gap by prioritizing textitSpecification Inference over code generation.<n>Our framework achieved a total correct patch rate of textbf93.97% (639/680)
  arXiv  Detail & Related papers  (2026-04-19T14:27:27Z)
• Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents [35.76774274440008]
  STING (Sequential Testing of Illicit N-step Goal execution) is an automated red-teaming framework.<n>It constructs a step-by-step illicit plan grounded in a benign persona and iteratively probes a target agent with adaptive follow-ups.<n>We introduce an analysis framework that models multi-turn red-teaming as a time-to-first-jailbreak random variable.
  arXiv  Detail & Related papers  (2026-02-18T10:31:19Z)
• Alita-G: Self-Evolving Generative Agent for Agent Generation [54.49365835457433]
  We present ALITA-G, a framework that transforms a general-purpose agent into a domain expert.<n>In this framework, a generalist agent executes a curated suite of target-domain tasks.<n>It attains strong gains while reducing computation costs.
  arXiv  Detail & Related papers  (2025-10-27T17:59:14Z)
• Red Teaming Program Repair Agents: When Correct Patches can Hide Vulnerabilities [22.02073334787359]
  We propose SWExploit, which generates adversarial issue statements to make APR agents produce patches that are functionally correct yet vulnerable.<n>Based on our evaluation, we are the first to challenge the traditional assumption that a patch passing all tests is inherently reliable and secure.
  arXiv  Detail & Related papers  (2025-09-30T07:38:57Z)
• Where LLM Agents Fail and How They can Learn From Failures [62.196870049524364]
  Large Language Model (LLM) agents have shown promise in solving complex, multi-step tasks.<n>They amplify vulnerability to cascading failures, where a single root-cause error propagates through subsequent decisions.<n>Current systems lack a framework that can comprehensively understand agent error in a modular and systemic way.<n>We introduce the AgentErrorTaxonomy, a modular classification of failure modes spanning memory, reflection, planning, action, and system-level operations.
  arXiv  Detail & Related papers  (2025-09-29T18:20:27Z)
• VulAgent: Hypothesis-Validation based Multi-Agent Vulnerability Detection [55.957275374847484]
  VulAgent is a multi-agent vulnerability detection framework based on hypothesis validation.<n>It implements a semantics-sensitive, multi-view detection pipeline, each aligned to a specific analysis perspective.<n>On average, VulAgent improves overall accuracy by 6.6%, increases the correct identification rate of vulnerable--fixed code pairs by up to 450%, and reduces the false positive rate by about 36%.
  arXiv  Detail & Related papers  (2025-09-15T02:25:38Z)
• Do AI models help produce verified bug fixes? [62.985237003585674]
  Large Language Models are used to produce corrections to software bugs.<n>This paper investigates how programmers use Large Language Models to complement their own skills.<n>The results are a first step towards a proper role for AI and LLMs in providing guaranteed-correct fixes to program bugs.
  arXiv  Detail & Related papers  (2025-07-21T17:30:16Z)
• IntenTest: Stress Testing for Intent Integrity in API-Calling LLM Agents [9.46115420774436]
  We introduce IntenTest, an API-centric stress testing framework that uncovers intent integrity violations in LLM agents.<n>IntenTest generates realistic tasks based on toolkits' documentation and applies targeted mutations to expose subtle agent errors.<n>We show that IntenTest effectively uncovers intent integrity violations, significantly outperforming baselines in both error-exposing rate and query efficiency.
  arXiv  Detail & Related papers  (2025-06-09T08:09:08Z)
• AgentXploit: End-to-End Redteaming of Black-Box AI Agents [54.29555239363013]
  We propose a generic black-box fuzzing framework, AgentXploit, to automatically discover and exploit indirect prompt injection vulnerabilities.<n>We evaluate AgentXploit on two public benchmarks, AgentDojo and VWA-adv, where it achieves 71% and 70% success rates against agents based on o3-mini and GPT-4o.<n>We apply our attacks in real-world environments, successfully misleading agents to navigate to arbitrary URLs, including malicious sites.
  arXiv  Detail & Related papers  (2025-05-09T07:40:17Z)
• Towards Adaptive Software Agents for Debugging [0.40964539027092917]
  We propose an adaptive agentic design, where the number of agents and their roles are determined dynamically.<n>Our initial evaluation shows that, with the adaptive design, the number of agents that are generated depends on the complexity of the buggy code.<n> Regarding the effectiveness of the fix, we noticed an average improvement of 11% compared to the one-shot prompting.
  arXiv  Detail & Related papers  (2025-04-25T12:48:08Z)
• When Disagreements Elicit Robustness: Investigating Self-Repair Capabilities under LLM Multi-Agent Disagreements [56.29265568399648]
  We argue that disagreements prevent premature consensus and expand the explored solution space.<n>Disagreements on task-critical steps can derail collaboration depending on the topology of solution paths.
  arXiv  Detail & Related papers  (2025-02-21T02:24:43Z)
• AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning [93.77763753231338]
  Adversarial Contrastive Prompt Tuning (ACPT) is proposed to fine-tune the CLIP image encoder to extract similar embeddings for any two intermediate adversarial queries. We show that ACPT can detect 7 state-of-the-art query-based attacks with $>99%$ detection rate within 5 shots. We also show that ACPT is robust to 3 types of adaptive attacks.
  arXiv  Detail & Related papers  (2024-08-04T09:53:50Z)
• Dissecting Adversarial Robustness of Multimodal LM Agents [70.2077308846307]
  We manually create 200 targeted adversarial tasks and evaluation scripts in a realistic threat model on top of VisualWebArena.<n>We find that we can successfully break latest agents that use black-box frontier LMs, including those that perform reflection and tree search.<n>We also use ARE to rigorously evaluate how the robustness changes as new components are added.
  arXiv  Detail & Related papers  (2024-06-18T17:32:48Z)
• A Unified Debugging Approach via LLM-Based Multi-Agent Synergy [39.11825182386288]
  FixAgent is an end-to-end framework for unified debug through multi-agent synergy. It significantly outperforms state-of-the-art repair methods, fixing 1.25$times$ to 2.56$times$ bugs on the repo-level benchmark, Defects4J.
  arXiv  Detail & Related papers  (2024-04-26T04:55:35Z)
• ContrastRepair: Enhancing Conversation-Based Automated Program Repair via Contrastive Test Case Pairs [23.419180504723546]
  ContrastRepair is a novel APR approach that augments conversation-driven APR by providing contrastive test pairs. We evaluate ContrastRepair on multiple benchmark datasets, including Defects4j, QuixBugs, and HumanEval-Java.
  arXiv  Detail & Related papers  (2024-03-04T12:15:28Z)
• Malicious Agent Detection for Robust Multi-Agent Collaborative Perception [52.261231738242266]
  Multi-agent collaborative (MAC) perception is more vulnerable to adversarial attacks than single-agent perception. We propose Malicious Agent Detection (MADE), a reactive defense specific to MAC perception. We conduct comprehensive evaluations on a benchmark 3D dataset V2X-sim and a real-road dataset DAIR-V2X.
  arXiv  Detail & Related papers  (2023-10-18T11:36:42Z)
• Invalidator: Automated Patch Correctness Assessment via Semantic and Syntactic Reasoning [6.269370220586248]
  In this paper, we propose a novel technique to automatically assess the correctness of APR-generated patches via semantic and syntactic reasoning. We have conducted experiments on a dataset of 885 patches generated on real-world programs in Defects4J. Experiment results show that INVALIDATOR correctly classified 79% overfitting patches, accounting for 23% more overfitting patches being detected by the best baseline.
  arXiv  Detail & Related papers  (2023-01-03T14:16:32Z)
• Fault-Aware Neural Code Rankers [64.41888054066861]
  We propose fault-aware neural code rankers that can predict the correctness of a sampled program without executing it. Our fault-aware rankers can significantly increase the pass@1 accuracy of various code generation models.
  arXiv  Detail & Related papers  (2022-06-04T22:01:05Z)
• Efficient Intent Detection with Dual Sentence Encoders [53.16532285820849]
  We introduce intent detection methods backed by pretrained dual sentence encoders such as USE and ConveRT. We demonstrate the usefulness and wide applicability of the proposed intent detectors, showing that they outperform intent detectors based on fine-tuning the full BERT-Large model. We release our code, as well as a new challenging single-domain intent detection dataset.
  arXiv  Detail & Related papers  (2020-03-10T15:33:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.