Think, Look, and Revise: Inconsistency-Aware Visual Self-Correction in MLLMs

• URL: http://arxiv.org/abs/2608.29374v1
• Date: Sat, 29 Aug 2026 17:22:08 GMT
• Title: Think, Look, and Revise: Inconsistency-Aware Visual Self-Correction in MLLMs
• Abstract summary: Tool-augmented multimodal reasoning integrates external tools into multimodal large language models.<n>We propose ReVISE, a framework that equips MLLMs with verification and dynamic error recovery for tool-augmented reasoning.
• Score: 35.17881745040865
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Tool-augmented multimodal reasoning integrates external tools (e.g., object detection, depth estimation) into multimodal large language models (MLLMs) to address perceptual bottlenecks in complex visual tasks. However, existing approaches rarely verify tool outputs, limiting their ability to detect and recover from tool failures. We propose ReVISE, a framework that equips MLLMs with verification and dynamic error recovery for tool-augmented reasoning. ReVISE introduces (1) a curated training dataset that supervises reflective behaviors, enabling models to validate tool-derived evidence, reformulate queries when visual mismatches arise, and fall back to intrinsic grounding when external tools are unreliable; and (2) a reinforcement learning based targeted rewards that encourage internal reflection and penalize spatial misalignment. Experiments on several benchmarks demonstrate consistent improvements over existing methods, highlighting the importance of error detection and correction in tool-augmented multimodal reasoning.

Related papers

• Forgotten in Weights, Recovered by Tools: Agentic Tool Unlearning for LLM Agents [54.050506620820784]
  Agentic Tool Unlearning (ATU) aims to reduce both parametric recall and tool-mediated recovery while preserving normal tool use for retained knowledge.<n>ATU achieves a better balance between target forgetting and retained utility, making unlearning more robust under tool-augmented agent deployment.
  arXiv  Detail & Related papers  (2026-08-21T18:34:48Z)
• Beyond the Eye: Efficient Multimodal Reasoning via Self-Regulated Implicit Visual Tools [65.7098588070281]
  We propose Beyond the Eye (BEE), a novel implicit visual tool paradigm centered on self-regulated capability.<n>BEE incorporates visual tool invocation behaviors into the training objective and encourages the model to develop a self-regulated invocation mechanism.<n>BEE achieves state-of-the-art performance in fine-grained visual perception while remaining competitive in general reasoning tasks.
  arXiv  Detail & Related papers  (2026-07-13T05:32:00Z)
• ForgeryVCR: Visual-Centric Reasoning via Efficient Forensic Tools in MLLMs for Image Forgery Detection and Localization [62.03035862528452]
  ForgeryVCR is a framework that materializes imperceptible traces into explicit visual intermediates via Visual-Centric Reasoning.<n>ForgeryVCR achieves state-of-the-art (SOTA) performance in both detection and localization tasks.
  arXiv  Detail & Related papers  (2026-02-15T11:14:47Z)
• What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-Zoom [26.940122024948597]
  We introduce MED (Measure-Explain-Diagnose) to disentangle intrinsic capability changes from tool-induced effects.<n>We find that improvements are dominated by intrinsic learning, while tool-use RL mainly reduces tool-induced harm.<n>Overall, current vision tool-use RL learns to coexist safely with tools rather than master them.
  arXiv  Detail & Related papers  (2026-02-01T17:00:50Z)
• VG-Refiner: Towards Tool-Refined Referring Grounded Reasoning via Agentic Reinforcement Learning [35.49623258104176]
  VG-Refiner is first framework aiming at the tool-refined referring grounded reasoning.<n>We introduce a two-stage think-rethink mechanism that enables the model to explicitly analyze and respond to tool feedback.<n>We achieve a significant improvement in accuracy and correction ability on referring and reasoning grounding benchmarks.
  arXiv  Detail & Related papers  (2025-12-06T09:58:01Z)
• ToolCritic: Detecting and Correcting Tool-Use Errors in Dialogue Systems [4.930296454541593]
  ToolCritic is a framework that evaluates and improves tool usage in multi-turn, tool-augmented dialogues.<n>Trials show ToolCritic improves tool-calling accuracy by up to 13% over baselines.
  arXiv  Detail & Related papers  (2025-10-19T23:42:39Z)
• Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments [70.42705564227548]
  We propose an automated environment construction pipeline for large language models (LLMs)<n>This enables the creation of high-quality training environments that provide detailed and measurable feedback without relying on external tools.<n>We also introduce a verifiable reward mechanism that evaluates both the precision of tool use and the completeness of task execution.
  arXiv  Detail & Related papers  (2025-08-12T09:45:19Z)
• Advancing Tool-Augmented Large Language Models via Meta-Verification and Reflection Learning [63.2198957755528]
  We propose Tool-MVR, a novel Tool-Augmented LLM that achieves comprehensive System 2 reasoning through two key innovations.<n>Specifically, we first introduce Multi-Agent Meta-Verification (MAMV), a systematic pipeline that rigorously validates APIs, queries, and reasoning trajectories.<n>Second, we propose Exploration-based Reflection Learning (EXPLORE), which enhances tool reflection capabilities by leveraging tool feedback.
  arXiv  Detail & Related papers  (2025-06-05T04:35:49Z)
• Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger [49.81945268343162]
  We propose MeCo, an adaptive decision-making strategy for external tool use.<n>MeCo quantifies metacognitive scores by capturing high-level cognitive signals in the representation space.<n>MeCo is fine-tuning-free and incurs minimal cost.
  arXiv  Detail & Related papers  (2025-02-18T15:45:01Z)

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.