SA

Saaket Agashe

0000-0002-8082-8830

cs.AIcs.CLcs.MAcs.CVcs.LGcs.HC

On Valency

published · living versions

W_acmvjsea·v1 · currentpublished

Evolving Agent Interfaces

with Yuzhe Yang, Gonzalo Gonzalez-Pumariega, Bhuvan Chandra Koduru, Chih-Lun Li +3

1 version

Preprints & journals

10 papers in the corpus · 2022–2026

Evolving Agent Interfaces2610.28601v1 · Saaket Agashe, Yuzhe Yang, Gonzalo Gonzalez-Pumariega et al.2026 · 0 citationsarXivon Valency

OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks2606.29537v2 · Mengqi Yuan, Zilong Zhou, Xinzhuang Xiong et al.2026 · 0 citationsarXiv

EnactToM: An Evolving Benchmark for Functional Theory of Mind in Embodied Agents2605.09826v2 · Gurusha Juneja, Dylan Lu, Saaket Agashe et al.2026 · 0 citationsarXiv

On the Reliability of Computer Use Agents2604.17849v1 · Gonzalo Gonzalez-Pumariega, Saaket Agashe, Jiachen Yang et al.2026 · 0 citationsarXiv

Context Bootstrapped Reinforcement Learning2603.18953v1 · Saaket Agashe, Jayanth Srinivasa, Gaowen Liu et al.2026 · 0 citationsarXiv

Self-Resource Allocation in Multi-Agent LLM Systems2504.02051v2 · Alfonso Amayuelas, Jingbo Yang, Saaket Agashe et al.2025 · 2 citationsarXiv

Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents2504.00906v1 · Saaket Agashe, Kyle Wong, Vincent Tu et al.2025 · 0 citationsarXiv

Agent S: An Open Agentic Framework that Uses Computers Like a Human2410.08164v1 · Saaket Agashe, Jiuzhou Han, Shuyu Gan et al.2024 · 2 citationsarXiv

LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models2310.03903v3 · Saaket Agashe, Yue Fan, Anthony Reyna et al.2023 · 32 citationsarXiv

Interacting with next-phrase suggestions: How suggestion systems aid and influence the cognitive processes of writing2208.00636v2 · Advait Bhat, Saaket Agashe, Niharika Mohile et al.2022 · 47 citationsarXiv

Career total: 14 works. 10 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.