collaborators

7 papers

cs.MA2026

Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs

Elizabeth Mieczkowski, Alexander Ku, Tiwalayo Eisape +5

Large language models (LLMs) are increasingly deployed in teams, yet existing coordination approaches often occupy two extremes. Highly structured methods rely on fixed roles, pipe…

cs.AI2026

Cognitive Models and AI Algorithms Provide Templates for Designing Language Agents

Ryan Liu, Dilip Arumugam, Cedegao E. Zhang +3

While contemporary large language models (LLMs) are increasingly capable in isolation, there are still many difficult problems that lie beyond the abilities of a single LLM. For su…

cs.LG2026

Toward Efficient Exploration by Large Language Model Agents

Dilip Arumugam, Thomas L. Griffiths

A burgeoning area within reinforcement learning (RL) is the design of sequential decision-making agents centered around large language models (LLMs). While autonomous decision-maki…

cs.AI2026

Using Reinforcement Learning to Train Large Language Models to Explain Human Decisions

Jian-Qiao Zhu, Hanbo Xie, Dilip Arumugam +2

A central goal of cognitive modeling is to develop models that not only predict human behavior but also provide insight into the underlying cognitive mechanisms. While neural netwo…

cs.SI2025

Lossy communication constrains iterated learning

Ben Prystawski, Dilip Arumugam, Noah D. Goodman

Humans' distinctive role in the world can largely be attributed to our capacity for iterated learning, a process by which knowledge is expanded and refined over generations. A rang…

cs.LG2025

Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL

Mahsa Bastankhah, Grace Liu, Dilip Arumugam +2

In this work, we take a first step toward elucidating the mechanisms behind emergent exploration in unsupervised reinforcement learning. We study Single-Goal Contrastive Reinforcem…