Saaket Agashe

I am a second-year Ph.D. student in the ERIC Lab at UC Santa Cruz, under the guidance of Professor Xin Eric Wang. Prior to this, I earned my Master's degree in Computer Science at UC Santa Cruz and completed my Bachelor's in Electronics Engineering from VJTI, Mumbai.

I am interested in developing AI agents that can plan effectively, adapt to novel environments and collaborate with others. Specifically I work on:

Long-horizon Planning: Developing strategies that enable Agents to plan effectively in long-horizon, partially observable environments [1, 2]
Multi-agent Cooperation and Alignment: Analyzing and Enhancing cooperative behaviour in Agents and their alignment to humans [1, 2, 3, 6]
Language Grounding: Enabling agents to effectively localize and connect linguistic descriptions to visual scenes [1, 2, 5]

For more details, check my CV or drop me an email.

[Apr 2025] Our paper "Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents" is now available as a preprint!
[Mar 2024] Our paper "Agent S: An Open Agentic Framework that Uses Computers Like a Human" is accepted to ICLR 2025!
[Mar 2024] Our paper "LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models" is accepted to Findings of NAACL 2025!

[1] Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents
Saaket Agashe, Kyle Wong, Vincent Tu, Jiachen Yang, Ang Li, Xin Eric Wang
Preprint
Description: Enhanced version of Agent S with a compositional generalist-specialist framework that improves computer use capabilities through specialized components working together.
Website Paper Code

[2] Agent S: An Open Agentic Framework that Uses Computers Like a Human
Saaket Agashe, Jiuzhou Han, Shuyu Gan, Jiachen Yang, Ang Li, Xin Eric Wang
ICLR 2025
Description: Developed Agent S, an advanced OS-level GUI automation system that integrates experience-based learning, web retrieval, and hierarchical planning for efficient task execution, achieving state-of-the-art performance in the OSWorld benchmark..
Website Paper Code

[3] LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models
Saaket Agashe, Yue Fan, Anthony Reyna, Xin Eric Wang
Findings of NAACL 2025
Description: Introduced the LLM-Coordination Benchmark and conducted a comprehensive analysis of LLMs in Pure Coordination Games.
Website Paper Code

[4] Athena 3.0: Personalized multimodal chatbot with neuro-symbolic dialogue generators
UCSC Team Athena
Alexa Prize SGC5
Description: Entry to Alexa Prize Social Bot Grand Challenge that earned second place in scientific innovation category
Website Paper

[5] Localization using Spatial Descriptions
Saaket Agashe, Xin Eric Wang
Description: Visually grounding Spatial Descriptions to a single point in an image based on descriptions of objects in the neighborhood of the point.
Code

[6] Interacting with Next-Phrase Suggestions: How Suggestion Systems Aid and Influence the Cognitive Processes of Writing
Advait Bhat, Saaket Agashe, Niharika Mohile, Parth Oberoi, Ravi Jangir, Anirudha Joshi
IUI 2023
Best Paper Honourable Mention
Description: Exploratory qualitative study to understand how writers interact with next-phrase suggestions.
Code Paper

[7] How do people interact with biased text prediction models while writing?
Advait Bhat, Saaket Agashe, Anirudha Joshi
HCI+NLP Workshop, EACL 2021
Description: Pilot study to understand how people interact with next phrase suggestion system.
Code Paper

[8] Perception and Motion Planning for Autonomous mobile manipulator
Saaket Agashe, Akshay Paralikar, Shweta Kumaran, Shambhavi Kuthe, Aditya Gawali, Hiten Kothari, Shashank Deshmukh, Faruk Kazi
Description: Develop a functional autonomous mobile manipulator for testing algorithms developed in simulation in the real world.
Code