English
Related papers

Related papers: Self-Improving AI Agents through Self-Play

200 papers

Algorithmic collusion has emerged as a central question in AI: Will the interaction between different AI agents deployed in markets lead to collusion? More generally, understanding how emergent behavior, be it a cartel or market dominance…

Multiagent Systems · Computer Science 2025-10-31 Ziyi Wang , Carmine Ventre , Maria Polukarov

This paper presents a theoretical framework unifying AIXI -- a model of universal AI -- with variational empowerment as an intrinsic drive for exploration. We build on the existing framework of Self-AIXI -- a universal learning agent that…

Artificial Intelligence · Computer Science 2025-03-05 Yusuke Hayashi , Koichi Takahashi

The maintained artifact in an AI-enabled system is not code plus settings, but a versioned governed program space: domains, structural constraints, eligibility, evaluation assets, and a statistical release gate. AI-enabled systems operate…

Software Engineering · Computer Science 2026-04-23 Nimrod Busany

The nonlinear vector autoregressive (NVAR) model provides an appealing framework to analyze multivariate time series obtained from a nonlinear dynamical system. However, the innovation (or error), which plays a key role by driving the…

Machine Learning · Statistics 2021-03-01 Hiroshi Morioka , Hermanni Hälvä , Aapo Hyvärinen

This paper develops an autonomous framework for systematic factor investing via agentic AI. Rather than relying on sequential manual prompts, our approach operationalizes the model as a self-directed engine that endogenously formulates…

Portfolio Management · Quantitative Finance 2026-04-07 Allen Yikuan Huang , Zheqi Fan

Agentic Artificial Intelligence (AI) can autonomously pursue long-term goals, make decisions, and execute complex, multi-turn workflows. Unlike traditional generative AI, which responds reactively to prompts, agentic AI proactively…

Computers and Society · Computer Science 2025-02-18 Anirban Mukherjee , Hannah Hanwen Chang

Training models through self-play alone (without any human data) has been a longstanding goal in AI, but its effectiveness for training large language models remains unclear, particularly in code generation where rewards based on unit tests…

Artificial Intelligence · Computer Science 2025-12-23 Alex Wilf , Pranjal Aggarwal , Bryan Parno , Daniel Fried , Louis-Philippe Morency , Paul Pu Liang , Sean Welleck

Today's AI systems have human-designed, fixed architectures and cannot autonomously and continuously improve themselves. The advance of AI could itself be automated. If done safely, that would accelerate AI development and allow us to reap…

Artificial Intelligence · Computer Science 2026-03-16 Jenny Zhang , Shengran Hu , Cong Lu , Robert Lange , Jeff Clune

Small language models are attractive for production deployment due to their low cost, fast inference, and ease of specialization. However, adapting them to a specific task remains a challenging engineering loop, driven not by training…

Artificial Intelligence · Computer Science 2026-04-14 Dhruv Atreja , Julia White , Nikhil Nayak , Kelton Zhang , Henrijs Princis , George Hurn-Maloney , Ash Lewis , Urchade Zaratiana

AI coding assistants like GitHub Copilot are rapidly transforming software development, but their safety remains deeply uncertain-especially in high-stakes domains like cybersecurity. Current red-teaming tools often rely on fixed benchmarks…

Cryptography and Security · Computer Science 2025-08-07 Xiangzhe Xu , Guangyu Shen , Zian Su , Siyuan Cheng , Hanxi Guo , Lu Yan , Xuan Chen , Jiasheng Jiang , Xiaolong Jin , Chengpeng Wang , Zhuo Zhang , Xiangyu Zhang

Self-play has enabled large language models to autonomously improve through self-generated challenges. However, existing self-play methods for vision-language models rely on passive interaction with static image collections, resulting in…

Computer Vision and Pattern Recognition · Computer Science 2026-02-13 Jinghan He , Junfeng Fang , Feng Xiong , Zijun Yao , Fei Shen , Haiyun Guo , Jinqiao Wang , Tat-Seng Chua

This paper is an invited layperson summary for The Academic of the paper referenced on the last page. We summarize how the formal framework of autocatalytic networks offers a means of modeling the origins of self-organizing, self-sustaining…

Artificial Intelligence · Computer Science 2024-07-17 Liane Gabora , Joscha Bach

Despite rapid advances in text-to-image generation, faithfully realizing user intent remains challenging, often requiring manual multi-turn trial and error. To automate this process, existing systems rely on either simple prompt rewriting…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Jinming Liu , Ruoyu Feng , Yuqi Wang , Wenjun Zeng , Xin Jin

Providing timely and meaningful feedback remains a persistent challenge in higher education, especially in large courses where teachers must balance formative depth with scalability. Recent advances in Generative Artificial Intelligence…

Human-Computer Interaction · Computer Science 2026-01-26 Alvaro Becerra , Ruth Cobos

Self-learning paradigms in large-scale conversational AI agents tend to leverage user feedback in bridging between what they say and what they mean. However, such learning, particularly in Markov-based query rewriting systems have far from…

Computation and Language · Computer Science 2022-05-03 Pragaash Ponnusamy , Clint Solomon Mathialagan , Gustavo Aguilar , Chengyuan Ma , Chenlei Guo

In this paper, we present a new methodology that employs tester agents to automate video game testing. We introduce two types of agents -synthetic and human-like- and two distinct approaches to create them. Our agents are derived from…

Artificial Intelligence · Computer Science 2019-06-04 Sinan Ariyurek , Aysu Betin-Can , Elif Surer

Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, but this assumption has rarely been validated against human annotation. We introduce AgentProp-Bench, a 2,000-task benchmark with 2,300…

Artificial Intelligence · Computer Science 2026-04-21 Bhaskar Gurram

Reinforcement learning (RL) agent development traditionally requires substantial expertise and iterative effort, often leading to high failure rates and limited accessibility. This paper introduces Agent$^2$, an LLM-driven…

Artificial Intelligence · Computer Science 2025-10-01 Yuan Wei , Xiaohan Shan , Ran Miao , Jianmin Li

AI agents are increasingly deployed to execute important tasks. While rising accuracy scores on standard benchmarks suggest rapid progress, many agents still continue to fail in practice. This discrepancy highlights a fundamental limitation…

Artificial Intelligence · Computer Science 2026-02-24 Stephan Rabanser , Sayash Kapoor , Peter Kirgis , Kangheng Liu , Saiteja Utpala , Arvind Narayanan

We present AgentGA, a framework that evolves autonomous code-generation runs by optimizing the agent seed: the task prompt plus optional parent archives that initialize a fresh workspace. The outer loop searches over these reusable starting…

Artificial Intelligence · Computer Science 2026-05-12 David Y. Y. Tan , Kellie Chin , Jingxian Zhang