CaptchaMind: Training CAPTCHA Solvers via Reinforcement Learning with Explicit Reasoning Supervision

• URL: http://arxiv.org/abs/2605.19538v1
• Date: Tue, 19 May 2026 08:38:44 GMT
• Title: CaptchaMind: Training CAPTCHA Solvers via Reinforcement Learning with Explicit Reasoning Supervision
• Abstract summary: We introduce Captcha-based Captcha-based RLMind, achieving 82.9% average success rate across eight tasks and 72.9% on real-world instances.<n>We present RLMind, an RLMind solver trained explicit reasoning process supervision, achieving 82.9% average success rate across eight tasks and 72.9% on real-world instances.
• Score: 50.35579781554922
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: CAPTCHAs are widely deployed as human verification mechanisms and frequently block intelligent agents from completing end-to-end automation in real-world web environments. Solving modern CAPTCHAs requires robust multi-step visual reasoning and interaction capabilities, yet training-based approaches have remained absent due to the lack of large-scale training data and process-level annotations. We introduce CaptchaBench, the first CAPTCHA benchmark designed to support large-scale training, comprising 16,000 programmatically generated samples across eight task categories with detailed region and process-level annotations. Systematic evaluation on CaptchaBench reveals that existing methods fail consistently on tasks requiring fine-grained visual detail capture and region-level comparison. We therefore present CaptchaMind, an RL-based solver trained with explicit reasoning process supervision, achieving 82.9% average success rate across eight tasks and 71.0% on real-world instances, substantially outperforming all existing methods without closed-source APIs.

Related papers

• SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks [73.92333717662558]
  SpatialWorld is a benchmark for evaluating the interactive spatial understanding of multimodal agents in complex real-world tasks.<n>It features 760 human-annotated tasks across diverse domains (e.g., household routines, travel, social collaboration)<n>For reliable evaluation, each task includes a human-validated initial state, a reference trajectory, and a terminal-state verifier.
  arXiv  Detail & Related papers  (2026-06-08T15:51:51Z)
• CAPTCHA Solving for Native GUI Agents: Automated Reasoning-Action Data Generation and Self-Corrective Training [18.35670595652216]
  ReCAP is a CAPTCHA-capable native GUI agent that can robustly solve modern, interactive CAPTCHA challenges.<n>We develop an automated data collection and curation pipeline that generates large-scale CAPTCHA interaction trajectories.<n>As CAPTCHA solving often requires multi-step interaction and recovery from intermediate mistakes, we further leverage failed trajectories to construct self-correction data.<n>Across held-out test sets, ReCAP improves CAPTCHA-solving success from roughly 30% to 80%, while maintaining strong performance on general GUI-agent benchmarks.
  arXiv  Detail & Related papers  (2026-03-23T23:35:59Z)
• COGNITION: From Evaluation to Defense against Multimodal LLM CAPTCHA Solvers [17.70082722524941]
  multimodal large language models (MLLMs) undermine the security guarantees of visual CAPTCHA.<n>We evaluate 7 leading commercial and open-source MLLMs across 18 real-world CAPTCHA task types.<n>We reveal that MLLMs can reliably solve recognition-oriented and low-interaction CAPTCHA tasks at human-like cost and latency.
  arXiv  Detail & Related papers  (2025-12-02T01:23:10Z)
• Empowering RepoQA-Agent based on Reinforcement Learning Driven by Monte-carlo Tree Search [70.63903518295785]
  We introduce RepoSearch-R1, a novel agentic reinforcement learning framework driven by Monte-carlo Tree Search.<n>Based on RepoSearch-R1, we construct a RepoQA-Agent specifically designed for repository question-answering tasks.
  arXiv  Detail & Related papers  (2025-10-30T09:10:36Z)
• Spatial CAPTCHA: Generatively Benchmarking Spatial Reasoning for Human-Machine Differentiation [15.668734718800065]
  We present a novel human-verification framework that leverages fundamental differences in spatial reasoning between humans and MLLMs.<n>Unlike existing CAPTCHAs which rely on low-level perception tasks that are vulnerable to modern AI, Spatial CAPTCHA generates dynamic questions requiring geometric reasoning, perspective-taking, and mental rotation.<n> Evaluation on a corresponding benchmark, Spatial-CAPTCHA-Bench, demonstrates that humans vastly outperform 10 state-of-the-art MLLMs, with the best model achieving only 31.0% Pass@1 accuracy.
  arXiv  Detail & Related papers  (2025-10-04T16:19:21Z)
• WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning [73.91893534088798]
  WebSailor is a complete post-training methodology designed to instill this crucial capability.<n>Our approach involves generating novel, high-uncertainty tasks through structured sampling and information obfuscation.<n>WebSailor significantly outperforms all open-source agents in complex information-seeking tasks.
  arXiv  Detail & Related papers  (2025-09-16T17:57:03Z)
• SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling [58.05959902776133]
  We introduce Single-Pass.<n>with Reference-Guided Evaluation (SPARE), a novel structured framework that enables efficient per-step annotation.<n>We demonstrate SPARE's effectiveness across four diverse datasets spanning mathematical reasoning (GSM8K, MATH), multi-hop question answering (MuSiQue-Ans), and spatial reasoning (SpaRP)<n>On ProcessBench, SPARE demonstrates data-efficient out-of-distribution generalization, using only $sim$16% of training samples compared to human-labeled and other synthetically trained baselines.
  arXiv  Detail & Related papers  (2025-06-18T14:37:59Z)
• Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents [23.715342148854006]
  Open CaptchaWorld is the first web-based benchmark and platform specifically designed to evaluate the visual reasoning and interaction capabilities of MLLM-powered agents.<n>Results show that humans consistently achieve near-perfect scores, state-of-the-art MLLM agents struggle significantly, with success rates at most 40.0% by Browser-Use Openai-o3.<n>This highlights Open CaptchaWorld as a vital benchmark for diagnosing the limits of current multimodal agents and guiding the development of more robust multimodal reasoning systems.
  arXiv  Detail & Related papers  (2025-05-30T17:59:55Z)
• Affordance-Guided Reinforcement Learning via Visual Prompting [51.361977466993345]
  Keypoint-based Affordance Guidance for Improvements (KAGI) is a method leveraging rewards shaped by vision-language models (VLMs) for autonomous RL.<n>On diverse real-world manipulation tasks specified by natural language descriptions, KAGI improves the sample efficiency of autonomous RL and enables successful task completion in 30K online fine-tuning steps.
  arXiv  Detail & Related papers  (2024-07-14T21:41:29Z)
• EnSolver: Uncertainty-Aware Ensemble CAPTCHA Solvers with Theoretical Guarantees [1.9649272351760065]
  We propose Enr, a family of solvers that use deep ensemble uncertainty to detect and skip out-of-distribution CAPTCHAs. We prove novel theoretical bounds on the effectiveness of our solvers and demonstrate their use with state-of-the-art CAPTCHA solvers.
  arXiv  Detail & Related papers  (2023-07-27T20:19:11Z)
• Deep-CAPTCHA: a deep learning based CAPTCHA solver for vulnerability assessment [1.027974860479791]
  This research investigates the weaknesses and vulnerabilities of the CAPTCHA generator systems. We develop a Convolutional Neural Network called Deep-CAPTCHA to achieve this goal. Our network's cracking accuracy leads to a high rate of 98.94% and 98.31% for the numerical and the alpha-numerical test datasets.
  arXiv  Detail & Related papers  (2020-06-15T11:44:43Z)

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.