Image de couverture de livre

Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Cao, Zongwan, Wen, Bingbing, Wang, Lucy Lu
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Characterizing LLM Abstention Behavior in Science QA with Context Perturbations
par: Wen, Bingbing, et autres
Publié: (2024)

Estimating the Usefulness of Clarifying Questions and Answers for Conversational Search
par: Sekulić, Ivan, et autres
Publié: (2024)

Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation
par: Baan, Joris, et autres
Publié: (2026)

VAGUE: Visual Contexts Clarify Ambiguous Expressions
par: Nam, Heejeong, et autres
Publié: (2024)

STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes
par: Xu, Chenjun, et autres
Publié: (2026)

Demystifying Reinforcement Learning in Agentic Reasoning
par: Yu, Zhaochen, et autres
Publié: (2025)

Varying Shades of Wrong: Aligning LLMs with Wrong Answers Only
par: Yao, Jihan, et autres
Publié: (2024)

RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models
par: Feng, Andrew Zhuoer, et autres
Publié: (2026)

Self-Distilled Agentic Reinforcement Learning
par: Lu, Zhengxi, et autres
Publié: (2026)

Know Your Limits: A Survey of Abstention in Large Language Models
par: Wen, Bingbing, et autres
Publié: (2024)

Agentic Reinforcement Learning with Implicit Step Rewards
par: Liu, Xiaoqian, et autres
Publié: (2025)

Agentic Reinforcement Learning for Search is Unsafe
par: Yang, Yushi, et autres
Publié: (2025)

Context Embeddings for Efficient Answer Generation in RAG
par: Rau, David, et autres
Publié: (2024)

CommVQA: Situating Visual Question Answering in Communicative Contexts
par: Naik, Nandita Shankar, et autres
Publié: (2024)

Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models
par: Zhu, Wenhui, et autres
Publié: (2025)

Answer When Needed, Forget When Not: Language Models Pretend to Forget via In-Context Knowledge Unlearning
par: Takashiro, Shota, et autres
Publié: (2024)

Answer Convergence as a Signal for Early Stopping in Reasoning
par: Liu, Xin, et autres
Publié: (2025)

Q&A Prompts: Discovering Rich Visual Clues through Mining Question-Answer Prompts for VQA requiring Diverse World Knowledge
par: Wang, Haibo, et autres
Publié: (2024)

ARIAL: An Agentic Framework for Document VQA with Precise Answer Localization
par: Mohammadshirazi, Ahmad, et autres
Publié: (2025)

Journalism-Guided Agentic In-Context Learning for News Stance Detection
par: Lee, Dahyun, et autres
Publié: (2025)

Surrogate Signals from Format and Length: Reinforcement Learning for Solving Mathematical Problems without Ground Truth Answers
par: Xin, Rihui, et autres
Publié: (2025)

Answer Only as Precisely as Justified: Calibrated Claim-Level Specificity Control for Agentic Systems
par: Huang, Tianyi, et autres
Publié: (2026)

DeltaMem: Towards Agentic Memory Management via Reinforcement Learning
par: Zhang, Qi, et autres
Publié: (2026)

StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning
par: Wang, Daoyu, et autres
Publié: (2026)

From Answers to Rationales: Self-Aligning Multimodal Reasoning with Answer-Oriented Chain-of-Thought
par: Tan, Wentao, et autres
Publié: (2025)

From Correctness to Preference: A Framework for Personalized Agentic Reinforcement Learning
par: zhang, Ranxu, et autres
Publié: (2026)

Knowledge Generation for Zero-shot Knowledge-based VQA
par: Cao, Rui, et autres
Publié: (2024)

CRAFT: Calibrated Reasoning with Answer-Faithful Traces via Reinforcement Learning for Multi-Hop Question Answering
par: Liu, Yu, et autres
Publié: (2026)

TR-ICRL: Test-Time Rethinking for In-Context Reinforcement Learning
par: Jiang, Wenxuan, et autres
Publié: (2026)

Context Matters: Pushing the Boundaries of Open-Ended Answer Generation with Graph-Structured Knowledge Context
par: Banerjee, Somnath, et autres
Publié: (2024)

Do Images Clarify? A Study on the Effect of Images on Clarifying Questions in Conversational Search
par: Siro, Clemencia, et autres
Publié: (2026)

Agentic Reinforcement Learning for Real-World Code Repair
par: Zhu, Siyu, et autres
Publié: (2025)

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
par: Zhang, Guibin, et autres
Publié: (2025)

On Many-Shot In-Context Learning for Long-Context Evaluation
par: Zou, Kaijian, et autres
Publié: (2024)

MolMem: Memory-Augmented Agentic Reinforcement Learning for Sample-Efficient Molecular Optimization
par: Wang, Ziqing, et autres
Publié: (2026)

SimpleVQA: Multimodal Factuality Evaluation for Multimodal Large Language Models
par: Cheng, Xianfu, et autres
Publié: (2025)

Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs
par: Lu, Meng, et autres
Publié: (2025)

ClarQ-LLM: A Benchmark for Models Clarifying and Requesting Information in Task-Oriented Dialog
par: Gan, Yujian, et autres
Publié: (2024)

Agentic Reinforced Policy Optimization
par: Dong, Guanting, et autres
Publié: (2025)

MixAtlas: Uncertainty-aware Data Mixture Optimization for Multimodal LLM Midtraining
par: Wen, Bingbing, et autres
Publié: (2026)