4 papers
JevGPT: Thinking Fast and Slow in Autonomous Research
Yasheng Sun, Yanning Dai, Yimeng Chen +9
Autonomous research agents must acquire and reason over evidence within a limited budget. Yet relevant sources can remain uninspected or unused, leaving a gap between retrieval cov…
STEVE: Stabilizing Textual Gradient-Based Prompt Optimization via Error-Driven Refinement and Regularized Verification
Yifan Xu, Yixuan Li, Xinzhuo Li +4
Textual-gradient methods automate prompt optimization through natural-language feedback, but their iterative updates can be unstable. We identify two sources of this instability: n…
Planning to Explore: Curiosity-Driven Planning for LLM Test Generation
Alfonso Amayuelas, Firas Laakom, Piotr Piękos +5
The use of LLMs for code generation has naturally extended to code testing and evaluation. As codebases grow in size and complexity, so does the need for automated test generation.…
Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making
Xiaopeng Yuan, Xingjian Zhang, Ke Xu +5
Large language models (LLMs) are increasingly used for tasks that require complex reasoning. Most benchmarks focus on final outcomes but overlook the intermediate reasoning steps -…