Cover Image

TRACE: A Framework for Analyzing and Enhancing Stepwise Reasoning in Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Imani, Shima, Moon, Seungwhan, Mathias, Lambert, Zhang, Lu, Damavandi, Babak
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SymPyBench: A Dynamic Benchmark for Scientific Reasoning with Executable Python Code
by: Imani, Shima, et al.
Published: (2025)

PRiSM: An Agentic Multimodal Benchmark for Scientific Reasoning via Python-Grounded Evaluation
by: Imani, Shima, et al.
Published: (2025)

Doppelgänger's Watch: A Split Objective Approach to Large Language Models
by: Ghasemlou, Shervin, et al.
Published: (2024)

Proactive Assistant Dialogue Generation from Streaming Egocentric Videos
by: Zhang, Yichi, et al.
Published: (2025)

Stepwise Think-Critique: A Unified Framework for Robust and Interpretable LLM Reasoning
by: Xu, Jiaqi, et al.
Published: (2025)

Pixel-Grounded Retrieval for Knowledgeable Large Multimodal Models
by: Kim, Jeonghwan, et al.
Published: (2026)

TRACE: Textual Reasoning for Affordance Coordinate Extraction
by: Park, Sangyun, et al.
Published: (2025)

Vision Language Model for Interpretable and Fine-grained Detection of Safety Compliance in Diverse Workplaces
by: Chen, Zhiling, et al.
Published: (2024)

Stepwise Reasoning Error Disruption Attack of LLMs
by: Peng, Jingyu, et al.
Published: (2024)

Stepwise Self-Consistent Mathematical Reasoning with Large Language Models
by: Zhao, Zilong, et al.
Published: (2024)

TRACE: A Multi-Agent System for Autonomous Physical Reasoning for Seismology
by: Liu, Feng, et al.
Published: (2026)

Policy-Guided Stepwise Model Routing for Cost-Effective Reasoning
by: Si, Wenwen, et al.
Published: (2026)

Promoting Efficient Reasoning with Verifiable Stepwise Reward
by: Yue, Chuhuai, et al.
Published: (2025)

A Medical Multimodal Diagnostic Framework Integrating Vision-Language Models and Logic Tree Reasoning
by: Zang, Zelin, et al.
Published: (2025)

STRIDE-ED: A Strategy-Grounded Stepwise Reasoning Framework for Empathetic Dialogue Systems
by: Ji, Hongru, et al.
Published: (2026)

Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors
by: Daheim, Nico, et al.
Published: (2024)

StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason
by: Zhang, Kaiyi, et al.
Published: (2025)

StepWiser: Stepwise Generative Judges for Wiser Reasoning
by: Xiong, Wei, et al.
Published: (2025)

Orcust: Stepwise-Feedback Reinforcement Learning for GUI Agent
by: Lu, Junyu, et al.
Published: (2025)

From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models
by: Zhou, Chenyue, et al.
Published: (2025)

Constrained Language Model Policy Optimization via Risk-aware Stepwise Alignment
by: Zhang, Lijun, et al.
Published: (2025)

TRACE: Learning to Compute on Circuit Graphs
by: Zheng, Ziyang, et al.
Published: (2025)

TRACE: Capability-Targeted Agentic Training
by: Kang, Hangoo, et al.
Published: (2026)

Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models
by: Cui, Yingqian, et al.
Published: (2025)

Large Language Models as Zero-shot Dialogue State Tracker through Function Calling
by: Li, Zekun, et al.
Published: (2024)

TRACE the Evidence: Constructing Knowledge-Grounded Reasoning Chains for Retrieval-Augmented Generation
by: Fang, Jinyuan, et al.
Published: (2024)

TRACE: A Conversational Framework for Sustainable Tourism Recommendation with Agentic Counterfactual Explanations
by: Banerjee, Ashmi, et al.
Published: (2026)

SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking
by: Huang, Weiyang, et al.
Published: (2026)

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model
by: Li, Tianle, et al.
Published: (2025)

3DGSNav: Enhancing Vision-Language Model Reasoning for Object Navigation via Active 3D Gaussian Splatting
by: Zheng, Wancai, et al.
Published: (2026)

Latent Veracity Inference for Identifying Errors in Stepwise Reasoning
by: Kim, Minsu, et al.
Published: (2025)

HMVLM: Multistage Reasoning-Enhanced Vision-Language Model for Long-Tailed Driving Scenarios
by: Wang, Daming, et al.
Published: (2025)

GeoThought: A Dataset for Enhancing Mathematical Geometry Reasoning in Vision-Language Models
by: Shi, Nannan, et al.
Published: (2025)

AgroCoT: A Chain-of-Thought Benchmark for Evaluating Reasoning in Vision-Language Models for Agriculture
by: Wen, Yibin, et al.
Published: (2025)

Med-VRAgent: A Framework for Medical Visual Reasoning-Enhanced Agents
by: Guo, Guangfu, et al.
Published: (2025)

TRUST: A Decentralized Framework for Auditing Large Language Model Reasoning
by: Huang, Morris Yu-Chao, et al.
Published: (2025)

Bridging Stepwise Lab-Informed Pretraining and Knowledge-Guided Learning for Diagnostic Reasoning
by: Hu, Pengfei, et al.
Published: (2024)

CausalStep: A Benchmark for Explicit Stepwise Causal Reasoning in Videos
by: Li, Xuchen, et al.
Published: (2025)

Towards Stepwise Domain Knowledge-Driven Reasoning Optimization and Reflection Improvement
by: Liu, Chengyuan, et al.
Published: (2025)

Teaching AI Stepwise Diagnostic Reasoning with Report-Guided Chain-of-Thought Learning
by: Luo, Yihong, et al.
Published: (2025)