Dolly Sah

dsah17

dollysah

AI & ML interests

AI agents, LLM reasoning, verifiers, AI/ML, agentic AI, reliable AI, model evaluation/validation, NLP, data analytics, responsible AI, AI safety, and trustworthy ML

Recent Activity

upvoted a paper 1 day ago

UndoBench: Separating Task Competence from Recovery Capability in Tool-Using AI Agents

liked a Space 8 days ago

TanmaySah/InvariantOne-Demo

liked a model 12 days ago

TanmaySah/InvariantOne-v1

View all activity

Organizations

None yet

upvoted a paper 1 day ago

UndoBench: Separating Task Competence from Recovery Capability in Tool-Using AI Agents

Paper • 2610.05622 • Published 4 days ago • 12

liked a Space 8 days ago

InvariantOne Demo

⚖

Order-Equivariant Probabilistic Decision Model

liked a model 12 days ago

TanmaySah/InvariantOne-v1

Text Classification • Updated 9 days ago • 25 • 2

authored 2 papers about 1 month ago

EvoUndo: Recoverability-Constrained Self-Evolution for LLM Agent Harnesses

Paper • 2608.28363 • Published Aug 28 • 11

The Verifier Tax: Horizon Dependent Safety Success Tradeoffs in Tool Using LLM Agents

Paper • 2603.19328 • Published Mar 18 • 1

upvoted a paper about 1 month ago