9 papers
ToolSciVer: Multimodal Scientific Claim Verification with Visual Tool Augmented Reinforcement Learning
Binglin Zhou, Peng Shi, Ryo Kamoi +2
Multimodal Scientific Claim Verification (MSCV) requires models to verify scientific claims using visually grounded evidence from papers, including figures, tables, charts, and tex…
Efficient PRM Training Data Synthesis via Formal Verification
Ryo Kamoi, Yusen Zhang, Nan Zhang +4
Process Reward Models (PRMs) have emerged as a promising approach for improving LLM reasoning capabilities by providing process supervision over reasoning traces. However, existing…
Bridging the Know-Act Gap via Task-Level Autoregressive Reasoning
Jihyun Janice Ahn, Ryo Kamoi, Berk Atil +34
LLMs often generate seemingly valid answers to flawed or ill-posed inputs. This is not due to missing knowledge: under discriminative prompting, the same models can mostly identify…
Evaluating LLM-Simulated Conversations in Modeling Inconsistent and Uncollaborative Behaviors in Human Social Interaction
Ryo Kamoi, Ameya Godbole, Longqi Yang +3
Simulating human conversations using large language models (LLMs) has emerged as a scalable methodology for modeling human social interaction. However, simulating human conversatio…
One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence
Bowen Jiang, Taiwei Shi, Ryo Kamoi +5
This paper introduces OMAR: One Model, All Roles, a reinforcement learning framework that enables AI to develop social intelligence through multi-turn, multi-agent conversational s…
VisOnlyQA: Large Vision Language Models Still Struggle with Visual Perception of Geometric Information
Ryo Kamoi, Yusen Zhang, Sarkar Snigdha Sarathi Das +2
Large Vision Language Models (LVLMs) have achieved remarkable performance in various vision-language tasks. However, it is still unclear how accurately LVLMs can perceive visual in…