Challenge: Recent advances in Large Language Models (LLMs) have demonstrated enhanced reasoning capabilities, evolving from simple Chain-of-Thought (CoT) prompting to advanced, product-oriented solutions like OpenAI o1 .
Approach: They propose a strategy that shifts image input to critical reasoning stages and compresses redundant visual tokens via dynamic pruning.
Outcome: The proposed model achieves state-of-the-art on five mathematical reasoning benchmarks (+3.4% vs previous sota) and demonstrates iterative reasoning capabilities for complex multi-step tasks.

Similar Papers

Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs (2026.acl-short)

Copied to clipboard

Challenge: Existing multimodal reasoning models lack generalized spatial intelligence, a new study shows . a critical gap exists in the field of vision-centric reasoning, the authors argue .
Approach: They evaluate 16 multimodal reasoning models using Chain-of-Though (CoT) based thinking . they find that CoT prompting consistently degrades performance in visual spatial reasoning .
Outcome: The proposed model hallucinates visual details from textual priors even when the image is absent.
Enhancing Advanced Visual Reasoning Ability of Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Recent advances in Vision-Language (VL) research have sparked new benchmarks for complex visual reasoning, challenging models’ advanced reasoning ability.
Approach: They propose a novel multi-modal in-context learning methodology to enhance LLMs’ contextual understanding and reasoning.
Outcome: The proposed model achieves SOTA performance among all visual reasoning tasks and achieves a 'higher level of accuracy' than previous models.
Revealing the Seen, Imagining the Beyond: A Survey of Image-Grounded Chain-of-Thought Reasoning in Multimodal LLMs (2026.acl-long)

Copied to clipboard

Challenge: Recent advances in Multimodal Large Language Models (MLLMs) have shifted visual reasoning from tool-calling to end-to-end perceptionreasoning.
Approach: They synthesize the emerging paradigm of Image-Grounded Chain-of-Thought (IG-CoT) they propose a method-centric taxonomy covering prompting, supervised fine-tuning, and reinforcement learning .
Outcome: The proposed model is based on a method-centric taxonomy and benchmarks.
Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression (2026.acl-long)

Copied to clipboard

Challenge: Existing work on reducing CoT generation in reasoning impairs the necessary information for deriving the correct answer.
Approach: They propose a reasoning paradigm that takes CoT as a part of context to simplify the reasoning task for Large Language Models (LLMs).
Outcome: The proposed framework reduces the generation length of LLMs, but its effectiveness hinges on the efficiency and reliability of the contextual CoT generation.
AIM-CoT: Active Information-driven Multimodal Chain-of-Thought for Vision-Language Reasoning (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for I-MCoT fail to capture dynamic needs of vision-language models . existing methods rely on attention signals, which are unreliable under severe granularity imbalance between brief textual query and informative image.
Approach: They propose a framework that integrates specially selected visual evidence into the context of Vision-Language Models (VLMs) they propose 'AIM-CoT' to improve evidence selection and insertion triggering .
Outcome: Experiments across three benchmarks and four backbones demonstrate the proposed framework’s consistent superiority.
Chain-of-Thought Compression Should Not Be Blind: V-Skip for Efficient Multimodal Reasoning via Dual-Path Anchoring (2026.acl-long)

Copied to clipboard

Challenge: Existing efforts to mitigate this via token compression fail due to its autoregressive nature . linguistically redundant tokens are erroneously pruned, leading to hallucinations .
Approach: They propose a method that reformulates token pruning as a Visual-Anchored Information Bottleneck (VA-IB) optimization problem.
Outcome: Experiments on Qwen2-VL and Llama-3.2 families show that the proposed model achieves a speedup with negligible accuracy loss.
Simple-VGC: Enhancing Visual Grounding in Multimodal Reasoning via Adaptive Tool Composition (2026.acl-long)

Copied to clipboard

Challenge: Existing multimodal large language models suffer from systematic failures in basic visual understanding.
Approach: They propose a tool-augmented reasoning framework with three targeted compensation strategies to address these problems.
Outcome: The proposed framework improves visual grounding by re-injecting the original image to mitigate visual forgetting, the authors show . the proposed framework also improves the accuracy of the visual inputs, the researchers show - and the results are promising .
Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do (2026.acl-long)

Copied to clipboard

Challenge: Existing open-source models often yield only marginal overall improvements, possibly due to an overemphasis on mathematical reasoning at the expense of broader capabilities.
Approach: They evaluate 12 multimodal tasks using 14 non-reasoning models and 8 reasoning models.
Outcome: The proposed method is effective in multimodal reasoning tasks, the authors show . they show that it lacks the ability to maintain deep visual introspection throughout the reasoning process.
Correct, Concise and Complete: Multi-stage Training For Adaptive Reasoning (2026.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) increase test-time computation, often in the form of chain-of-thought (CoT) however, reasoning traces can become unnecessarily long, increasing computation costs without improving accuracy and sometimes even degrading performance.
Approach: They propose a multi-stage efficient reasoning method that combines supervised fine-tuning with reinforcement learning using an adaptive length penalty.
Outcome: The proposed method reduces response length by an average of 28% for 8B models and 40% for 32B models while incurring only minor performance drops of 1.6 and 2.5 points, respectively.
Multimodal Causal Reasoning Benchmark: Challenging Multimodal Large Language Models to Discern Causal Links Across Modalities (2025.findings-acl)

Copied to clipboard

Challenge: Existing MLLMs lack robustness in multimodal causal reasoning compared to their performance in textual settings.
Approach: They propose a novel multimodal chain-of-thought (CoT) reasoning benchmark that leverages siamese images and text pairs to challenge MLLMs.
Outcome: The proposed benchmark leverages siamese images and text pairs to challenge MLLMs.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations