Cover Image

Step-level Optimization for Efficient Computer-use Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wei, Jinbiao, Ni, Kangqi, Zhao, Yilun, Gan, Guo, Cohan, Arman
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

ANCHOR: Branch-Point Data Generation for GUI Agents
by: Wei, Jinbiao, et al.
Published: (2026)

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

SUCEA: Reasoning-Intensive Retrieval for Adversarial Fact-checking through Claim Decomposition and Editing
by: Liu, Hongjun, et al.
Published: (2025)

One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs
by: Dunefsky, Jacob, et al.
Published: (2025)

Investigating Data Contamination in Modern Benchmarks for Large Language Models
by: Deng, Chunyuan, et al.
Published: (2023)

ResearchGym: Evaluating Language Model Agents on Real-World AI Research
by: Garikaparthi, Aniketh, et al.
Published: (2026)

Step-Back Profiling: Distilling User History for Personalized Scientific Writing
by: Tang, Xiangru, et al.
Published: (2024)

PHYSICS: Benchmarking Foundation Models on University-Level Physics Problem Solving
by: Feng, Kaiyue, et al.
Published: (2025)

MIMIR: A Streamlined Platform for Personalized Agent Tuning in Domain Expertise
by: Deng, Chunyuan, et al.
Published: (2024)

MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning
by: Tang, Xiangru, et al.
Published: (2023)

M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Models
by: Li, Chuhan, et al.
Published: (2024)

Survey on Evaluation of LLM-based Agents
by: Yehudai, Asaf, et al.
Published: (2025)

Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplifications and Resistance in Multi-Agent Based LLM-as-Judge
by: Ma, Chiyu, et al.
Published: (2025)

RbtAct: Rebuttal as Supervision for Actionable Review Feedback Generation
by: Wu, Sihong, et al.
Published: (2026)

SciMDR: Advancing Scientific Multimodal Document Reasoning
by: Chen, Ziyu, et al.
Published: (2026)

A Survey of Multimodal Mathematical Reasoning: From Perception, Alignment to Reasoning
by: Yang, Tianyu, et al.
Published: (2026)

On the Benefits of Fine-Grained Loss Truncation: A Case Study on Factuality in Summarization
by: Flores, Lorenzo Jaime Yu, et al.
Published: (2024)

MedAgentsBench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning
by: Tang, Xiangru, et al.
Published: (2025)

Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future
by: Wu, Sihong, et al.
Published: (2026)

AbGen: Evaluating Large Language Models in Ablation Study Design and Evaluation for Scientific Research
by: Zhao, Yilun, et al.
Published: (2025)

On Evaluating LLM Alignment by Evaluating LLMs as Judges
by: Liu, Yixin, et al.
Published: (2025)

TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models
by: Shangguan, Ziyao, et al.
Published: (2024)

PuzzlePlex: Benchmarking Foundation Models on Reasoning and Planning with Puzzles
by: Long, Yitao, et al.
Published: (2025)

ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoning
by: Tang, Xiangru, et al.
Published: (2025)

Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems
by: Zhao, Yilun, et al.
Published: (2026)

Bayesian Calibration of Win Rate Estimation with LLM Evaluators
by: Gao, Yicheng, et al.
Published: (2024)

SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents
by: Lin, Jiaye, et al.
Published: (2025)

Preference-Driven Multi-Objective Combinatorial Optimization with Conditional Computation
by: Fan, Mingfeng, et al.
Published: (2025)

From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculations
by: Wang, Benlu, et al.
Published: (2025)

REVERE: Reflective Evolving Research Engineer for Scientific Workflows
by: Gangireddi, Balaji Dinesh, et al.
Published: (2026)

ReIFE: Re-evaluating Instruction-Following Evaluation
by: Liu, Yixin, et al.
Published: (2024)

STEVE: A Step Verification Pipeline for Computer-use Agent Training
by: Lu, Fanbin, et al.
Published: (2025)

Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers
by: Lifshitz, Shalev, et al.
Published: (2025)

IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery
by: Garikaparthi, Aniketh, et al.
Published: (2025)

Evaluating Legal Reasoning Traces with Legal Issue Tree Rubrics
by: Lee, Jinu, et al.
Published: (2025)

RouterRetriever: Routing over a Mixture of Expert Embedding Models
by: Lee, Hyunji, et al.
Published: (2024)

VF-Eval: Evaluating Multimodal LLMs for Generating Feedback on AIGC Videos
by: Song, Tingyu, et al.
Published: (2025)

LocAgent: Graph-Guided LLM Agents for Code Localization
by: Chen, Zhaoling, et al.
Published: (2025)

Local Occupancy-Enhanced Object Grasping with Multiple Triplanar Projection
by: Ma, Kangqi, et al.
Published: (2024)

ChemSafetyBench: Benchmarking LLM Safety on Chemistry Domain
by: Zhao, Haochen, et al.
Published: (2024)