CAP-CoT: Cycle Adversarial Prompt for Improving Chain of Thoughts in LLM Reasoning
Chain-of-Thought (CoT) prompting has emerged as a simple and effective way to elicit step-by-step solutions from large language models (LLMs). However, CoT reasoning can be unstable across runs on long, multi-step problems, leading to inconsistent answers for unchanged task. Most prior work focuses on improving the forward reasoning chain within a single pass, with less attention to iterative and contrastive correction. To address this gap, we propose CAP-CoT, a Cycle Adversarial Prompt optimization framework designed to improve both CoT reasoning accuracy and stability of a single deployed solver. In each cycle, a forward solver generates candidate reasoning chains, an adversarial challenger constructs plausible but deliberately flawed chains using targeted error strategies, and a feedback agent contrasts the two chains and produces step-aligned structured feedback. This feedback closes the optimization loop in two directions, including updating the solver prompt based on errors exposed by the challenger, and updating the challenger prompt to generate increasingly targeted errors in subsequent cycles. Unlike safety-oriented adversarial prompting such as jailbreak or prompt-injection attacks, our adversarial component is task-semantic and aims to expose logical vulnerabilities in reasoning chains. Experiments across six benchmarks and four LLM backbones demonstrate that within two to three adversarial prompt optimization cycles, CAP-CoT consistently reduces variability across runs while improving reasoning accuracy and robustness to prompt perturbations.
Full article excerpt tap to expand
Computer Science > Artificial Intelligence arXiv:2604.23270 (cs) [Submitted on 25 Apr 2026] Title:CAP-CoT: Cycle Adversarial Prompt for Improving Chain of Thoughts in LLM Reasoning Authors:Shuxu Chen, Yitian Zhou, Jiaquan Zhang, Haoyu Bian, Aming Wu, Sungyoung Lee, Chaoning Zhang, Hyundong Shin View a PDF of the paper titled CAP-CoT: Cycle Adversarial Prompt for Improving Chain of Thoughts in LLM Reasoning, by Shuxu Chen and 7 other authors View PDF HTML (experimental) Abstract:Chain-of-Thought (CoT) prompting has emerged as a simple and effective way to elicit step-by-step solutions from large language models (LLMs). However, CoT reasoning can be unstable across runs on long, multi-step problems, leading to inconsistent answers for unchanged task. Most prior work focuses on improving the forward reasoning chain within a single pass, with less attention to iterative and contrastive correction. To address this gap, we propose CAP-CoT, a Cycle Adversarial Prompt optimization framework designed to improve both CoT reasoning accuracy and stability of a single deployed solver. In each cycle, a forward solver generates candidate reasoning chains, an adversarial challenger constructs plausible but deliberately flawed chains using targeted error strategies, and a feedback agent contrasts the two chains and produces step-aligned structured feedback. This feedback closes the optimization loop in two directions, including updating the solver prompt based on errors exposed by the challenger, and updating the challenger prompt to generate increasingly targeted errors in subsequent cycles. Unlike safety-oriented adversarial prompting such as jailbreak or prompt-injection attacks, our adversarial component is task-semantic and aims to expose logical vulnerabilities in reasoning chains. Experiments across six benchmarks and four LLM backbones demonstrate that within two to three adversarial prompt optimization cycles, CAP-CoT consistently reduces variability across runs while improving reasoning accuracy and robustness to prompt perturbations. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2604.23270 [cs.AI] (or arXiv:2604.23270v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2604.23270 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Jiaquan Zhang [view email] [v1] Sat, 25 Apr 2026 12:24:04 UTC (1,785 KB) Full-text links: Access Paper: View a PDF of the paper titled CAP-CoT: Cycle Adversarial Prompt for Improving Chain of Thoughts in LLM Reasoning, by Shuxu Chen and 7 other authorsView PDFHTML (experimental)TeX Source view license Current browse context: cs.AI < prev | next > new | recent | 2026-04 Change to browse by: cs References & Citations NASA ADSGoogle Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging…
This excerpt is published under fair use for community discussion. Read the full article at arXiv.org.
Discussion
0 commentsMore from arXiv.org