[Pitch]: Signal Conditioned Agents for Lightweight Perception: An end-to-end pipeline for brain signal augmented computer use agents

[Thomson-Lam]

Title

Signal Conditioned Agents for Lightweight Perception

Description

Computer use agents are expensive and unreliable across long context windows due to the vision + language + agentic complexity, and the cost and unreliability of VLM agents compounds across long running steps. This project aims to build on top of Microsoft's OmniParser architecture and explore integration of implicit brain signals as a new source of data to augment and validate computer use agents' actions, and to make computer use agents more reliable and safe across long multi-step scenarios.

Project url

https://github.com/Thomson-Lam/brainhacks-26-proposal/tree/main

Project Leads

Thomson Lam (@Thomson-Lam)

[github-actions]

Thank you for pitching a project to Brainhack! We'll review your proposal shortly.
If you haven't already, be sure to register for the event

[github-actions]

✅ Project has been added to config.yaml!