Publications

* denotes equal contribution (random order).

GROVE: Benchmarking and Training LLM Agents to Persuade

Sarim Hashmi*, Kshitij Mishra*, Tair Djanibekov, Dushyant Singh Chauhan, Nils Lukas

Under review

SIRA: Self-Improving Recommendation Agents under Demand Shifts

Kshitij Mishra, Sarim Hashmi, Dushyant Singh Chauhan, Martin Takáč, Salem Lahlou, Nils Lukas

Under review

PERSUADE: A Debate Arena for Benchmarking, Optimizing, and Auditing Persuasion in Language Models

Sarim Hashmi, Samuele Poppi, Salem Lahlou, Martin Takáč, Kshitij Mishra, Nils Lukas

Under review