works on

From the 1 of 10 linked papers with an AI index.

activity
20242026
collaborators

10 papers

cs.CL2026

Flout at Your Own Risk: LLMs Struggle with Pragmatic Cooperativity Under Epistemic Asymmetry

Hannah VanderHoeven, Abhijnan Nath, Nikhil Krishnaswamy

The paper investigates how large language models handle pragmatic cooperation when they have less information than their collaborators, evaluating their ability to follow Grice's m…

cs.MA2026

ECHO: Learning Epistemically Adaptive Language Agents with Turn-Level Credit

Abhijnan Nath, Nikhil Krishnaswamy

What does it mean for a language agent to be adaptive? Effective multi-turn agents must decide what information to seek, how to use new evidence, and when they are certain enough t…

cs.AI2026

Owen-Shapley Policy Optimization: A Principled RL Algorithm for Generative Search LLMs

Abhijnan Nath, Alireza Bagheri Garakani, Tianchen Zhou +3

Large language models are increasingly trained via reinforcement learning for personalized recommendation tasks, but standard methods like GRPO rely on sparse, sequence-level rewar…

cs.CL2026

CRAFT: Grounded Multi-Agent Coordination Under Partial Information

Abhijnan Nath, Hannah VanderHoeven, Nikhil Krishnaswamy

We introduce CRAFT, a multi-agent benchmark for evaluating pragmatic communication in large language models under strict partial information. In this setting, multiple agents with…

cs.CL2026

Collaborate, Deliberate, Evaluate: How LLM Alignment Affects Coordinated Multi-Agent Outcomes

Abhijnan Nath, Carine Graff, Nikhil Krishnaswamy

As Large Language Models (LLMs) get integrated into diverse workflows, they are increasingly being regarded as "collaborators" with humans, and required to work in coordination wit…

cs.AI2026

Learning "Partner-Aware" Collaborators in Multi-Party Collaboration

Abhijnan Nath, Nikhil Krishnaswamy

Large Language Models (LLMs) are increasingly being deployed in agentic settings where they act as collaborators with humans. Therefore, it is increasingly important to be able to…