3 papers
cs.LG2026
MetaEvo: A Meta-Optimization Framework for Experience-Driven Agent Evolution
Bowen Ren, Heyan Huang, Yinghao Li +1
Large language models (LLMs) exhibit strong reasoning capabilities, yet most LLM-based agents are statically deployed and unable to improve through task interactions. Existing expe…
cs.CL2025
SRA-MCTS: Self-driven Reasoning Augmentation with Monte Carlo Tree Search for Code Generation
Bin Xu, Yiguan Lin, Yinghao Li +1
Large language models demonstrate exceptional performance in simple code generation tasks but still face challenges in tackling complex problems. These challenges may stem from ins…
cs.CL2025
Extrapolation Merging: Keep Improving With Extrapolation and Merging
Yiguan Lin, Bin Xu, Yinghao Li +1
Large Language Models (LLMs) require instruction fine-tuning to perform different downstream tasks. However, the instruction fine-tuning phase still demands significant computation…