Understanding the Effects of Distractors on Reasoning Vision-Language Models

arXiv:2511.21397 · cs.CV, cs.AI, cs.CL, cs.LG · Submitted 2025-11-26 · Read on arXiv

cs.CV, cs.AI, cs.CL, cs.LG

Submitted: 2025-11-26

Updated: 2026-09-14

Comments: EMNLP 2026

Code: https://github.com/luca-medeiros/langsegment-anything

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 96× in this paper · explained in 1 episode
• Trace — 36× in this paper · explained in 2 episodes
• Test-time Scaling — 14× in this paper · explained in 2 episodes
• Benchmark — 11× in this paper · explained in 2 episodes
• Reasoning Traces — 11× in this paper · explained in 3 episodes
• Verification — 7× in this paper · explained in 2 episodes
• Robustness — 6× in this paper · explained in 5 episodes
• Adaptation — 5× in this paper · explained in 1 episode
• Steering — 3× in this paper · explained in 2 episodes
• Agentic Task — 2× in this paper · explained in 1 episode
• Agentic Tasks — 2× in this paper · explained in 1 episode
• Failure Modes — 2× in this paper · explained in 3 episodes
• Multimodal Reasoning — 2× in this paper · explained in 5 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Human-in-the-Loop — 1× in this paper · explained in 3 episodes
• Multimodal Inputs — 1× in this paper · explained in 2 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Sparse Attention — 1× in this paper · explained in 5 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes

Sources

• gpt-oss-120b & gpt-oss-20b Model Card
• Diagnosing and Mitigating Modality Interference in Multimodal Large Language Models
• The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks
• Don't Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning
• Intern-S1: A Scientific Multimodal Foundation Model
• O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning
• DeepSeek-R1 Thoughtology: Let's think about LLM Reasoning
• SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models
• Qwen3-VL Technical Report
• LogicVista: Multimodal LLM Logical Reasoning Benchmark in Visual Contexts
• Demystifying Long Chain-of-Thought Reasoning in LLMs

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models