CATArena: Evaluation of LLM Agents through Iterative Tournament Competitions

• URL: http://arxiv.org/abs/2510.26852v1
• Date: Thu, 30 Oct 2025 15:22:53 GMT
• Title: CATArena: Evaluation of LLM Agents through Iterative Tournament Competitions
• Abstract summary: Large Language Model (LLM) agents have evolved from basic text generation to autonomously completing complex tasks through interaction with external tools.<n>In this work, we emphasize the importance of learning ability, including both self-improvement and peer-learning, as a core driver for agent evolution toward human-level intelligence.<n>We propose an iterative, competitive peer-learning framework, which allows agents to refine and optimize their strategies through repeated interactions and feedback.
• Score: 49.02422075498554
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Model (LLM) agents have evolved from basic text generation to autonomously completing complex tasks through interaction with external tools. However, current benchmarks mainly assess end-to-end performance in fixed scenarios, restricting evaluation to specific skills and suffering from score saturation and growing dependence on expert annotation as agent capabilities improve. In this work, we emphasize the importance of learning ability, including both self-improvement and peer-learning, as a core driver for agent evolution toward human-level intelligence. We propose an iterative, competitive peer-learning framework, which allows agents to refine and optimize their strategies through repeated interactions and feedback, thereby systematically evaluating their learning capabilities. To address the score saturation issue in current benchmarks, we introduce CATArena, a tournament-style evaluation platform featuring four diverse board and card games with open-ended scoring. By providing tasks without explicit upper score limits, CATArena enables continuous and dynamic evaluation of rapidly advancing agent capabilities. Experimental results and analyses involving both minimal and commercial code agents demonstrate that CATArena provides reliable, stable, and scalable benchmarking for core agent abilities, particularly learning ability and strategy coding.

Related papers

• Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents [67.97365535829098]
  Learning from experience is critical for developing capable, self-improving large language model (LLM) agents.<n>We propose Evo-Harness, which distills noisy, single-shot executions into reusable skill harnesses for cross-domain and topic-level adaptation.<n>Our analysis demonstrates the effectiveness of Evo-Harness and provides a principled understanding of how LLM agents can effectively learn on the fly.
  arXiv  Detail & Related papers  (2026-08-15T06:43:56Z)
• Harnessing LLM Agents with Skill Programs [58.356514745548026]
  We introduce HASP, a new framework that upgrades skills into executable Program Functions (PFs)<n>PFs act as executable guardrails that activate on failure-prone states and modify the next action or inject corrective context.<n> HASP drives substantial gains compared to both training-free and training-based methods on web-search, math reasoning, and coding tasks.
  arXiv  Detail & Related papers  (2026-05-18T01:35:11Z)
• AI In Cybersecurity Education -- Scalable Agentic CTF Design Principles and Educational Outcomes [25.913186214869242]
  This paper presents a study of Capture-the-Flag competitions built on the Cyber Security Awareness Week competition system.<n>We formalize three autonomy levels: human-in-the-loop, autonomous agent frameworks, and hybrid.<n>Our results offer actionable guidance for designing LLM-assisted cybersecurity competitions as learning technologies.
  arXiv  Detail & Related papers  (2026-03-23T04:05:59Z)
• BotzoneBench: Scalable LLM Evaluation via Graded AI Anchors [9.224594551677374]
  Large Language Models (LLMs) are increasingly deployed in interactive environments requiring strategic decision-making.<n>Recent game-based evaluations employ LLM-vs-LLM tournaments that produce relative rankings dependent on transient model pools.<n>Here we show that anchoring LLM evaluation to fixed hierarchies of skill-calibrated game Artificial Intelligence (AI) enables linear-time absolute skill measurement.
  arXiv  Detail & Related papers  (2026-01-22T13:15:08Z)
• JudgeAgent: Knowledge-wise and Dynamic LLM Evaluation with Agent-as-Interviewer [19.09571232466437]
  We propose Agent-as-Interviewer, a dynamic evaluation paradigm for large language models (LLMs)<n>Unlike current benchmarking or dynamic interaction paradigms, Agent-as-Interviewer utilizes agents to invoke knowledge tools for wider and deeper knowledge in the dynamic multi-turn question generation.<n>We develop JudgeAgent, a knowledge-wise dynamic evaluation framework that employs knowledge-driven synthesis as the agent's tool and uses difficulty scoring as strategy guidance.
  arXiv  Detail & Related papers  (2025-09-02T08:52:16Z)
• QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search [89.97082652805904]
  We propose QLASS (Q-guided Language Agent Stepwise Search), to automatically generate annotations by estimating Q-values.<n>With the stepwise guidance, we propose a Q-guided generation strategy to enable language agents to better adapt to long-term value.<n>We empirically demonstrate that QLASS can lead to more effective decision making through qualitative analysis.
  arXiv  Detail & Related papers  (2025-02-04T18:58:31Z)
• From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning [62.54484062185869]
  We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process.<n>We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
  arXiv  Detail & Related papers  (2024-11-06T10:35:11Z)
• SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement [18.84439000902905]
  Current large language model (LLM)-based software agents often follow linear, sequential processes.<n>We propose SWE-Search, a multi-agent framework that integrates Monte Carlo Tree Search (MCTS) with a self-improvement mechanism.<n>This highlights the potential of self-evaluation driven search techniques in complex software engineering environments.
  arXiv  Detail & Related papers  (2024-10-26T22:45:56Z)
• Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement [50.481380478458945]
  Iterative step-level Process Refinement (IPR) framework provides detailed step-by-step guidance to enhance agent training. Our experiments on three complex agent tasks demonstrate that our framework outperforms a variety of strong baselines.
  arXiv  Detail & Related papers  (2024-06-17T03:29:13Z)
• AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents [74.16170899755281]
  We introduce AgentBoard, a pioneering comprehensive benchmark and accompanied open-source evaluation framework tailored to analytical evaluation of LLM agents.<n>AgentBoard offers a fine-grained progress rate metric that captures incremental advancements as well as a comprehensive evaluation toolkit.<n>This not only sheds light on the capabilities and limitations of LLM agents but also propels the interpretability of their performance to the forefront.
  arXiv  Detail & Related papers  (2024-01-24T01:51:00Z)
• MERMAIDE: Learning to Align Learners using Model-Based Meta-Learning [62.065503126104126]
  We study how a principal can efficiently and effectively intervene on the rewards of a previously unseen learning agent in order to induce desirable outcomes. This is relevant to many real-world settings like auctions or taxation, where the principal may not know the learning behavior nor the rewards of real people. We introduce MERMAIDE, a model-based meta-learning framework to train a principal that can quickly adapt to out-of-distribution agents.
  arXiv  Detail & Related papers  (2023-04-10T15:44:50Z)
• Credit-cognisant reinforcement learning for multi-agent cooperation [0.0]
  We introduce the concept of credit-cognisant rewards, which allows an agent to perceive the effect its actions had on the environment as well as on its co-agents. We show that by manipulating these experiences and constructing the reward contained within them to include the rewards received by all the agents within the same action sequence, we are able to improve significantly on the performance of independent deep Q-learning.
  arXiv  Detail & Related papers  (2022-11-18T09:00:25Z)
• Modelling Assessment Rubrics through Bayesian Networks: a Pragmatic Approach [40.06500618820166]
  This paper presents an approach to deriving a learner model directly from an assessment rubric. We illustrate how the approach can be applied to automatize the human assessment of an activity developed for testing computational thinking skills.
  arXiv  Detail & Related papers  (2022-09-07T10:09:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.