Image de couverture de livre

Coding Agents with Multimodal Browsing are Generalist Problem Solvers

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Soni, Aditya Bharat, Li, Boxuan, Wang, Xingyao, Chen, Valerie, Neubig, Graham
Format:	Preprint
Publié:	2025
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

Go-Browse: Training Web Agents with Structured Exploration
par: Gandhi, Apurva, et autres
Publié: (2025)

Beyond Browsing: API-Based Web Agents
par: Song, Yueqi, et autres
Publié: (2024)

CodeScout: An Effective Recipe for Reinforcement Learning of Code Search Agents
par: Sutawika, Lintang, et autres
Publié: (2026)

MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents
par: Li, Shilong, et autres
Publié: (2025)

Training Versatile Coding Agents in Synthetic Environments
par: Zhu, Yiqi, et autres
Publié: (2025)

OpenHands: An Open Platform for AI Software Developers as Generalist Agents
par: Wang, Xingyao, et autres
Publié: (2024)

Training Software Engineering Agents and Verifiers with SWE-Gym
par: Pan, Jiayi, et autres
Publié: (2024)

Hybrid-Gym: Training Coding Agents to Generalize Across Tasks
par: Xie, Yiqing, et autres
Publié: (2026)

Effective Strategies for Asynchronous Software Engineering Agents
par: Geng, Jiayi, et autres
Publié: (2026)

Training Proactive and Personalized LLM Agents
par: Sun, Weiwei, et autres
Publié: (2025)

Solving NLP Problems through Human-System Collaboration: A Discussion-based Approach
par: Kaneko, Masahiro, et autres
Publié: (2023)

BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents
par: Wei, Jason, et autres
Publié: (2025)

Agent Workflow Memory
par: Wang, Zora Zhiruo, et autres
Publié: (2024)

BehaviorBox: Automated Discovery of Fine-Grained Performance Differences Between Language Models
par: Tjuatja, Lindia, et autres
Publié: (2025)

K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts
par: Lee, Nahyun, et autres
Publié: (2026)

Do LLMs exhibit human-like response biases? A case study in survey design
par: Tjuatja, Lindia, et autres
Publié: (2023)

Executable Code Actions Elicit Better LLM Agents
par: Wang, Xingyao, et autres
Publié: (2024)

PresentAgent-2: Towards Generalist Multimodal Presentation Agents
par: Wu, Wei, et autres
Publié: (2026)

Browse and Concentrate: Comprehending Multimodal Content via prior-LLM Context Fusion
par: Wang, Ziyue, et autres
Publié: (2024)

ZINA: Multimodal Fine-grained Hallucination Detection and Editing
par: Wada, Yuiga, et autres
Publié: (2025)

VisualPuzzles: Decoupling Multimodal Reasoning Evaluation from Domain Knowledge
par: Song, Yueqi, et autres
Publié: (2025)

Sandboxed Coding Agents are Competitive Omni-modal Task Solvers
par: Chen, Dongping, et autres
Publié: (2026)

Grounding Multilingual Multimodal LLMs With Cultural Knowledge
par: Nyandwi, Jean de Dieu, et autres
Publié: (2025)

BrowserAgent: Building Web Agents with Human-Inspired Web Browsing Actions
par: Yu, Tao, et autres
Publié: (2025)

On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models
par: Zhang, Charlie, et autres
Publié: (2025)

Midtraining Bridges Pretraining and Posttraining Distributions
par: Liu, Emmy, et autres
Publié: (2025)

An Incomplete Loop: Instruction Inference, Instruction Following, and In-context Learning in Language Models
par: Liu, Emmy, et autres
Publié: (2024)

What Is Missing in Multilingual Visual Reasoning and How to Fix It
par: Song, Yueqi, et autres
Publié: (2024)

Can Large Language Models be Trusted for Evaluation? Scalable Meta-Evaluation of LLMs as Evaluators via Agent Debate
par: Chern, Steffi, et autres
Publié: (2024)

A Rubric-Supervised Critic from Sparse Real-World Outcomes
par: Wang, Xingyao, et autres
Publié: (2026)

PhysicsSolutionAgent: Towards Multimodal Explanations for Numerical Physics Problem Solving
par: Thole, Aditya, et autres
Publié: (2026)

BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese
par: Zhou, Peilin, et autres
Publié: (2025)

AgentSkiller: Scaling Generalist Agent Intelligence through Semantically Integrated Cross-Domain Data Synthesis
par: Sun, Zexu, et autres
Publié: (2026)

InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection
par: Liu, Yuhang, et autres
Publié: (2025)

RAGGED: Towards Informed Design of Scalable and Stable RAG Systems
par: Hsia, Jennifer, et autres
Publié: (2024)

Recursive Agent Optimization
par: Gandhi, Apurva, et autres
Publié: (2026)

LocAgent: Graph-Guided LLM Agents for Code Localization
par: Chen, Zhaoling, et autres
Publié: (2025)

Cognitive Agent Compilation for Explicit Problem Solver Modeling
par: Moon, Hyeongdon, et autres
Publié: (2026)

CodeRAG-Bench: Can Retrieval Augment Code Generation?
par: Wang, Zora Zhiruo, et autres
Publié: (2024)

BrowseConf: Confidence-Guided Test-Time Scaling for Web Agents
par: Ou, Litu, et autres
Publié: (2025)