Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution
arXiv cs.AI·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
2d agoQuick Take
Solvita enhances LLMs for competitive programming through a continuous learning framework with specialized agents.
Key Points
- Introduces a closed-loop problem-solving system.
- Utilizes four specialized agents for dynamic learning.
- Achieves state-of-the-art performance in code generation.
📖 Reader Mode
~2 min readAuthors: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
Abstract:Large language models (LLMs) still struggle with the rigorous reasoning demands of hard competitive programming. While recent multi-agent frameworks attempt to bridge this reliability gap, they remain fundamentally stateless: they rely on static retrieval and discard the valuable problem-solving and debugging experience gained from previous tasks. To address this, we present Solvita, an agentic evolution framework that enables continuous learning without requiring weight updates to the underlying LLM. Solvita reorganizes problem-solving into a closed-loop system of strategy selection, program synthesis, certified supervision, and targeted hacking, executed by four specialized agents: Planner, Solver, Oracle, and Hacker. Crucially, each agent is paired with a trainable, graph-structured knowledge network. As the system operates, outcome signals, such as pass/fail verdicts, test certification quality, and adversarial vulnerabilities discovered by the Hacker, are recast as reinforcement learning updates to these network weights. This allows the agents to dynamically route future queries based on past successes and failures, effectively accumulating transferable reasoning experience over time. Evaluated across CodeContests, APPS, AetherCode, and live Codeforces rounds, Solvita establishes a new state-of-the-art among code-generation agents, outperforming existing multi-agent pipelines and nearly doubling the accuracy of single-pass baselines.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.15301 [cs.AI] |
| (or arXiv:2605.15301v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.15301 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Han Li [view email]
[v1]
Thu, 14 May 2026 18:15:09 UTC (824 KB)
— Originally published at arxiv.org
More from arXiv cs.AI
See more →1d ago
FeaturedOriginal
From Prompts to Protocols: An AI Agent for Laboratory Automation
AI Summary
An AI agent integrates large language models for automating laboratory protocols, enhancing efficiency and accuracy.