Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution
The article introduces Solvita, a new framework designed to enhance large language models for competitive programming. It addresses the limitations of existing multi-agent systems by enabling continuous learning through a closed-loop system. Solvita has demonstrated superior performance in various coding competitions, significantly improving accuracy over previous models.
- ▪Solvita reorganizes problem-solving into a closed-loop system involving four specialized agents: Planner, Solver, Oracle, and Hacker.
- ▪The framework allows for continuous learning without requiring weight updates to the underlying large language model.
- ▪Evaluated across multiple coding competitions, Solvita has established a new state-of-the-art among code-generation agents.
Opening excerpt (first ~120 words) tap to expand
Computer Science > Artificial Intelligence arXiv:2605.15301 (cs) [Submitted on 14 May 2026] Title:Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution Authors:Han Li, Jinyu Tian, Rili Feng, Yuqiao Du, Chong Zheng, Chenyu Wang, Chenchen Liu, Shihao Li, Xinping Lei, Yifan Yao, Weihao Xie, Letian Zhu, Jiaheng Liu View a PDF of the paper titled Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution, by Han Li and 12 other authors View PDF HTML (experimental) Abstract:Large language models (LLMs) still struggle with the rigorous reasoning demands of hard competitive programming.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at arXiv cs.AI.
Discussion
0 commentsMore from arXiv cs.AI
