Publications

A collection of my research work.

MARS-RA: Rank Aggregation for Credit Assignment via Multimodal Comparisons in Embodied Multi-Agent Cooperation

MARS-RA: Rank Aggregation for Credit Assignment via Multimodal Comparisons in Embodied Multi-Agent Cooperation

Dawei Wang, Di Zhao, Xinyuan Liu, Marci Chi Ma, Xiaoyang Liu, Chengming Zhou, Gary Ushaw, Richard Davison

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) 2026

MARS-RA improves credit assignment in cooperative MARL by using large multimodal models to rank agents through pairwise contribution comparisons, converting these rankings into robust reward-shaping signals for effective cooperation.

DOI
Tracing the Light of Thought: A Probabilistic Self- and Cross-Consistency Verification Mechanism Improving Mathematical Reasoning in LLMs

Tracing the Light of Thought: A Probabilistic Self- and Cross-Consistency Verification Mechanism Improving Mathematical Reasoning in LLMs

Xiaoyang Liu, Dawei Wang, Tian Li, Huizhi Liang, Gary Ushaw, Richard Davison

Findings of the Association for Computational Linguistics: ACL 2026 2026

We explored bridging ray tracing and LLM reasoning by proposing inference algorithms that sample reasoning trajectories directly based on LLM confidence at multiple granularities.

DOI
Towermind: A tower defence game learning environment and benchmark for llm as agents

Towermind: A tower defence game learning environment and benchmark for llm as agents

Dawei Wang, Chengming Zhou, Di Zhao, Xinyuan Liu, Marci Chi Ma, Gary Ushaw, Richard Davison

Proceedings of the AAAI Conference on Artificial Intelligence 2026

We introduce TowerMind, a tower defense game benchmark for evaluating long-term planning and decision-making in agentic LLMs, characterized by low evaluation costs, multimodal inputs, and reinforcement learning compatibility.