Tag
该论文提出 VepAgent，一个将因果转移推理与工具增强强化学习结合的智能体框架，用于视频事件预测，并构建了 futurebench-4K 思维链数据集，在 FutureBench 和 NEPBench 上达到 SOTA 性能。
MolDesignBench is a new benchmark for evaluating LLM-based agents in scenario-grounded molecular design, comprising 2K instances with implicit and explicit constraints, revealing that current frontier LLMs achieve low success rates, especially in reasoning about implicit constraints and infeasibility detection.
This paper presents ContrAgent, a contract-based framework for symbolic temporal supervision of LLM agents that ensures deterministic safety checks both online and offline with low latency.
Presents NeSy-Spatial, a neuro-symbolic framework that self-evolves spatial reasoning skills by composing tool-use and geometry skills, improving accuracy on spatial reasoning benchmarks.