Arman Cohan

MRMR: A Realistic and Expert-Level Multidisciplinary Benchmark for Reasoning-Intensive Multimodal Retrieval

Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning

Medical thinking with multiple images

CellForge: Agentic Design of Virtual Cell Models

COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferences

References Improve LLM Alignment in Non-Verifiable Domains

AlphaResearch: Accelerating New Algorithm Discovery with Language Models

DyFlow: Dynamic Workflow Framework for Agentic Reasoning

MSRS: Evaluating Multi-Source Retrieval-Augmented Generation

TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models

One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs

On Evaluating LLM Alignment by Evaluating LLMs as Judges

ChemAgent: Self-updating Memories in Large Language Models Improves Chemical Reasoning

ML-Bench: Evaluating Large Language Models for Code Generation in Repository-Level Machine Learning Tasks

PuzzlePlex: A Benchmark to Evaluate the Reasoning and Planning of Large Language Models on Puzzles

COMAL: A Convergent Meta-Algorithm for Aligning LLMs with General Preferences