Milad Kazemi — accepted AI-conference papers

2025

Abstract Counterfactuals for Language Model Agents

Edoardo Pona, Milad Kazemi, Yali Du, David Watson, Nicola Paoletti

NeurIPS 2025poster

Counterfactual inference is a powerful tool for analysing and evaluating autonomous agents, but its application to language model (LM) agents remains challenging. Existing work on counterfactuals in LMs has primarily focused on token-level counterfactuals, which are often inadequate for LM agents du…

Cited by 0 Source ↗Scholar ↗

2024

Assume-Guarantee Reinforcement Learning

Milad Kazemi, Mateo Perez, Fabio Somenzi, Sadegh Soudjani, Ashutosh Trivedi, Alvaro Velasquez

AAAI 2024technical

We present a modular approach to reinforcement learning (RL) in environments consisting of simpler components evolving in parallel. A monolithic view of such modular environments may be prohibitively large to learn, or may require unrealizable communication between the components in the form of a ce…

Cited by 1 Source ↗PDF ↗Scholar ↗