Agent Alpha: Tree Search Unifying Generation, Exploration and Evaluation for Computer-Use Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tang, Sizhe, Chen, Rongqian, Lan, Tian
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents
by: Chen, Rongqian, et al.
Published: (2026)

MALinZero: Efficient Low-Dimensional Search for Mastering Complex Multi-Agent Planning
by: Tang, Sizhe, et al.
Published: (2025)

Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization
by: Li, Yu, et al.
Published: (2026)

Metric-Gradient Projection for Stable Multi-Agent Policy Learning
by: Zhang, Zuyuan, et al.
Published: (2026)

AlphaAgent: LLM-Driven Alpha Mining with Regularized Exploration to Counteract Alpha Decay
by: Tang, Ziyi, et al.
Published: (2025)

OSExpert: Computer-Use Agents Learning Professional Skills via Exploration
by: Liu, Jiateng, et al.
Published: (2026)

Cochain Perspectives on Temporal-Difference Signals for Learning Beyond Markov Dynamics
by: Zhang, Zuyuan, et al.
Published: (2026)

NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search
by: Tang, Sizhe, et al.
Published: (2026)

AgentHazard: A Benchmark for Evaluating Harmful Behavior in Computer-Use Agents
by: Feng, Yunhao, et al.
Published: (2026)

MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents
by: Yan, Yunhe, et al.
Published: (2025)

On the Reliability of Computer Use Agents
by: Gonzalez-Pumariega, Gonzalo, et al.
Published: (2026)

UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents
by: Liang, Yijuan, et al.
Published: (2026)

Disclosing Generative AI Use in Digital Humanities Research
by: Ma, Rongqian, et al.
Published: (2025)

AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
by: Toledo, Edan, et al.
Published: (2025)

Surfer 2: The Next Generation of Cross-Platform Computer Use Agents
by: Andreux, Mathieu, et al.
Published: (2025)

HealthAdminBench: Evaluating Computer-Use Agents on Healthcare Administration Tasks
by: Bedi, Suhana, et al.
Published: (2026)

Evaluating the Search Agent in a Parallel World
by: Chen, Jiawei, et al.
Published: (2026)

Perception Graph for Cognitive Attack Reasoning in Augmented Reality
by: Chen, Rongqian, et al.
Published: (2025)

ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents
by: Lai, Hanyu, et al.
Published: (2025)

AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions
by: Sun, Jingwei, et al.
Published: (2026)

Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory
by: Yuen, Sizhe, et al.
Published: (2025)

Agent-as-a-Judge: Evaluate Agents with Agents
by: Zhuge, Mingchen, et al.
Published: (2024)

Large Language Models as User-Agents for Evaluating Task-Oriented-Dialogue Systems
by: Kazi, Taaha, et al.
Published: (2024)

Scaling Synthetic Task Generation for Agents via Exploration
by: Ramrakhya, Ram, et al.
Published: (2025)

General Agent Evaluation
by: Bandel, Elron, et al.
Published: (2026)

FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use
by: Lu, Jiaxuan, et al.
Published: (2026)

InteractComp: Evaluating Search Agents With Ambiguous Queries
by: Deng, Mingyi, et al.
Published: (2025)

RUMAD: Reinforcement-Unifying Multi-Agent Debate
by: Wang, Chao, et al.
Published: (2026)

Evolving in Tasks: Empowering the Multi-modality Large Language Model as the Computer Use Agent
by: Cheng, Yuhao, et al.
Published: (2025)

WESE: Weak Exploration to Strong Exploitation for LLM Agents
by: Huang, Xu, et al.
Published: (2024)

Lipschitz Lifelong Monte Carlo Tree Search for Mastering Non-Stationary Tasks
by: Zhang, Zuyuan, et al.
Published: (2025)

Grounding Computer Use Agents on Human Demonstrations
by: Feizi, Aarash, et al.
Published: (2025)

CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents
by: Foerster, Hanna, et al.
Published: (2026)

PRO-CUA: Process-Reward Optimization for Computer Use Agents
by: He, Yifei, et al.
Published: (2026)

C-World: A Computer Use Agent Environment Creator
by: Xi, Ziqiao, et al.
Published: (2026)

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents
by: Yang, Jingyi, et al.
Published: (2025)

Multi-Agent Collaboration for Automated Design Exploration on High Performance Computing Systems
by: Menon, Harshitha, et al.
Published: (2026)

Joint Agent Memory and Exploration Learning via Novelty Signals
by: Tian, Shizuo, et al.
Published: (2026)

OpenComputer: Verifiable Software Worlds for Computer-Use Agents
by: Wei, Jinbiao, et al.
Published: (2026)

Demonstrating ViviDoc: Generating Interactive Documents through Human-Agent Collaboration
by: Tang, Yinghao, et al.
Published: (2026)