Article

GenReasoner: Generative Visual Agent Planning

2026-06-11

Abstract excerpt

<title>Abstract</title> <p>When humans face problems beyond their immediate capabilities, they rely on tools, providing a promising paradigm for improving visual reasoning in multimodal large language models (MLLMs). Effective reasoning, therefore, hinges on knowing which tools to use, when to invoke them, and how to compose them over multiple steps, even when faced with new tools or new tasks. We introduce GenRe...

Topics

Open a Topic to create a Post that cites this publication.

Uncategorized literature

Identifiers and source

Literature Corpus work: e12e28e0-6491-5164-8d53-4260888a57e3
DOI: 10.21203/rs.3.rs-9035628/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

GenReasoner: Generative Visual Agent PlanningDOI 10.21203/rs.3.rs-9035628/v1Read

From Pre-Trained Language Models to Agentic AI: Evolution and Architectures for Autonomous IntelligenceSemantic proximity Read

Reasoning in Large Language Models: From Chain-of-Thought to Massively Decomposed Agentic ProcessesSemantic proximity Read

Reverse Prompting: A Memory-Efficient Paradigm for LLM Agents Through Structural RegenerationSemantic proximity Read

A Survey on Post-Training of Multimodal Large Language ModelsSemantic proximity Read

iRAT: Replanning and Controlled Retrieval for Robust LLM ReasoningSemantic proximity Read

HAR-Agent: Multilingual Multimodal Activity Recognition via Knowledge-Distilled LLM ReasoningSemantic proximity Read

Beyond Words: The Evolution of Large Language Models in Context-AwareSemantic proximity Read

PlanAgent: Embodied Visual-Language Model for Grounded Task planning with Environment MapSemantic proximity Read

FineRegion-LM: Enhancing Large Vision-Language Models for Fine-Grained Region-Level UnderstandingSemantic proximity Read

iRAT: Improved Retrieval-Augmented Thinking for Context-Aware Replanning-Based ReasoningSemantic proximity Read

A Survey on AI Search with Large Language ModelsSemantic proximity Read

Dimension-Direct Routing: Achieving 25% Depth Improvement in Multi- Model LLM Systems via Explicit Capability FactorizationSemantic proximity Read