# CATArena: Evaluating Evolutionary Capabilities of Code Agents via Iterative Tournaments

arXiv: https://arxiv.org/abs/2510.26852 · HTML: https://mlsanity.com/paper/2510.26852/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 24 of its 37 references that are in the map.
- First posted on arXiv 30 Oct 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 24 of 24)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate](https://mlsanity.com/paper/2305.19118/) (2023)
- [CodeBLEU: a Method for Automatic Evaluation of Code Synthesis](https://mlsanity.com/paper/2009.10297/) (2020)
- [Language Models can Solve Computer Tasks](https://mlsanity.com/paper/2303.17491/) (2023)
- [DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents](https://mlsanity.com/paper/2506.11763/) (2025)
- [SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents](https://mlsanity.com/paper/2406.12952/) (2024)
- [A Survey on Code Generation with LLM-based Agents](https://mlsanity.com/paper/2508.00083/) (2025)
- [RedCode: Risky Code Execution and Generation Benchmark for Code Agents](https://mlsanity.com/paper/2411.07781/) (2024)
- [SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents](https://mlsanity.com/paper/2504.08703/) (2025)
- [SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks](https://mlsanity.com/paper/2506.11791/) (2025)
- [DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models](https://mlsanity.com/paper/2410.07331/) (2024)
- [Web-Bench: A LLM Code Benchmark Based on Web Standards and Frameworks](https://mlsanity.com/paper/2505.07473/) (2025)
- [TextArena](https://mlsanity.com/paper/2504.11442/) (2025)
- [GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging](https://mlsanity.com/paper/2508.18993/) (2025)
- [PeerGPT: Probing the Roles of LLM-based Peer Agents as Team Moderators and Participants in Children's Collaborative Learning](https://mlsanity.com/paper/2403.14227/) (2024)
- [Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios](https://mlsanity.com/paper/2410.12468/) (2024)
- [Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey](https://mlsanity.com/paper/2506.11102/) (2025)
- [Hallucination to Consensus: Multi-Agent LLMs for End-to-End JUnit Test Generation](https://mlsanity.com/paper/2506.02943/) (2025)
- [OIBench: Benchmarking Strong Reasoning Models with Olympiad in Informatics](https://mlsanity.com/paper/2506.10481/) (2025)
- [Leveraging LLMs to Automate Energy-Aware Refactoring of Parallel Scientific Codes](https://mlsanity.com/paper/2505.02184/) (2025)
- [LLM-based Multi-Agent System for Intelligent Refactoring of Haskell Code](https://mlsanity.com/paper/2506.19481/) (2025)

## Built on by (most cited first, 5 of 5)

- [DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations](https://mlsanity.com/paper/2605.24539/) (2026)
- [MonoScale: Scaling Multi-Agent System with Monotonic Improvement](https://mlsanity.com/paper/2601.23219/) (2026)
- [SAGE: A Quantitative Evaluation of Socialized Evolution in Agent Ecosystems](https://mlsanity.com/paper/2606.03544/) (2026)
- [Frontier Coding Agents Can Now Implement an AlphaZero Self-Play Machine Learning Pipeline For Connect Four That Performs Comparably to an External Solver](https://mlsanity.com/paper/2604.25067/) (2026)
- [Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition](https://mlsanity.com/paper/2610.12341/) (2026)

## Abstract (arXiv)

Current evaluation for Large Language Model (LLM) code agents predominantly focus on generating functional code in single-turn scenarios, which fails to evaluate the agent's capability for continuous code optimization and multi-turn iterative development. To bridge this gap, we introduce CATArena, a framework designed to evaluate the evolutionary capabilities of code agents via iterative tournaments. Agents engage in multi-turn tournaments and continuously refine their code through self-reflection and peer-learning based on comprehensive execution feedback. For evaluation, we propose a dual-metric system to decouple static generation proficiency from evolutionary potential. Extensive experiments reveal that an agent's evolutionary potential is not strictly correlated with its initial proficiency. Our analysis further reveals that current agents struggle to concurrently leverage both peer-learning and self-reflection for effective performance gains. Furthermore, the results validate CATArena's high extensibility and resistance to variance tasks, establishing it as a continuous and reliable standard for assessing the evolutionary capability of LLM code agents.