5 papers
Predicting Performance of Symbolic and Prompt Programs with Examples
Chengqi Zheng, Keya Hu, Shuzhi Liu +3
LLM prompting is widely used for naturally stated tasks, yet it is unreliable it may succeed on a few test cases but fail at deployment time. We study performance prediction: given…
DSPO: Stable and Efficient Policy Optimization for Agentic Search and Reasoning
Chenyang Gu, Yewen Pu, Bruce Yang +2
Enhancing LLMs with the ability to actively search external knowledge is crucial for complex and real-world tasks. Current approaches either rely on prompting to elicit the model's…
Bongards at the Boundary of Perception and Reasoning: Programs or Language?
Cassidy Langenfeld, Claas Beger, Gloria Geng +4
Vision-Language Models (VLMs) have made great strides in everyday visual tasks, such as captioning a natural image, or answering commonsense questions about such images. But humans…
When Robots Should Say "I Don't Know": Benchmarking Abstention in Embodied Question Answering
Tao Wu, Chuhao Zhou, Guangyu Zhao +3
Embodied Question Answering (EQA) requires an agent to interpret language, perceive its environment, and navigate within 3D scenes to produce responses. Existing EQA benchmarks ass…
Code Driven Planning with Domain-Adaptive Critic
Zikang Tian, Shaohui Peng, Du Huang +11
Large Language Models (LLMs) have been widely adopted as task planners for AI agents in sequential decision-making problems, leveraging their extensive world knowledge. However, th…