4 papers
Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents
Wenjie Tang, Minne Li, Sijie Huang +2
Reinforcement learning from verifiable rewards (RLVR) is a promising paradigm for improving large language model (LLM) agents on long-horizon interactive tasks. However, in partial…
DSGBench: A Diverse Strategic Game Benchmark for Evaluating LLM-based Agents in Complex Decision-Making Environments
Wenjie Tang, Yuan Zhou, Erqiang Xu +3
Large language model (LLM)-based agents are increasingly applied to complex strategic environments that demand long-horizon reasoning, multi-agent interaction, and decision-making…
Human-Aligned Bench: Fine-Grained Assessment of Reasoning Ability in MLLMs vs. Humans
Yansheng Qiu, Li Xiao, Zhaopan Xu +3
The goal of achieving Artificial General Intelligence (AGI) is to imitate humans and surpass them. Models such as OpenAI's o1, o3, and DeepSeek's R1 have demonstrated that large la…
Advancing Fine-Grained Visual Understanding with Multi-Scale Alignment in Multi-Modal Models
Wei Wang, Zhaowei Li, Qi Xu +7
Multi-modal large language models (MLLMs) have achieved remarkable success in fine-grained visual understanding across a range of tasks. However, they often encounter significant c…