English
Related papers

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

200 papers

Autonomous GUI agents based on vision-language models (VLMs) often assume deterministic environment responses, generating actions without verifying whether previous operations succeeded. In real-world settings with network latency,…

Computation and Language · Computer Science 2026-04-08 Yuzhe Zhang , Xianwei Xue , Xingyong Wu , Mengke Chen , Chen Liu , Xinran He , Run Shao , Feiran Liu , Huanmin Xu , Qiutong Pan , Haiwei Wang

AI agents are increasingly used to solve complex, multi-step tasks, but existing multi-agent frameworks remain brittle as workflows grow in scale and depth. Small errors at intermediate stages can propagate through agent interactions, while…

Artificial Intelligence · Computer Science 2026-05-26 Andy Xu , Yu-Wing Tai

We introduce Gaia2, a benchmark for evaluating large language model agents in realistic, asynchronous environments. Unlike prior static or synchronous evaluations, Gaia2 introduces scenarios where environments evolve independently of agent…

Autonomous AI agents can remain fully authorized and still become unsafe as behavior drifts, adversaries adapt, and decision patterns shift without any code change. We propose the \textbf{Informational Viability Principle}: governing an…

Artificial Intelligence · Computer Science 2026-04-28 German Marin , Jatin Chaudhary

Reinforcement learning with verifiable rewards (RLVR) is pivotal for the continuous evolution of GUI agents, yet existing evaluation paradigms face significant limitations. Rule-based methods suffer from poor scalability and cannot handle…

Robotics · Computer Science 2026-02-03 Chaoqun Cui , Jing Huang , Shijing Wang , Liming Zheng , Qingchao Kong , Zhixiong Zeng

Data annotation is essential for supervised learning, yet producing accurate, unbiased, and scalable labels remains challenging as datasets grow in size and modality. Traditional human-centric pipelines are costly, slow, and prone to…

Machine Learning · Computer Science 2026-02-04 Subhodeep Ghosh , Bayan Divaaniaazar , Md Ishat-E-Rabban , Spencer Clarke , Senjuti Basu Roy

Reinforcement learning with verifiable rewards (RLVR) has advanced the reasoning capabilities of large language models. However, existing methods rely solely on outcome rewards, without explicitly optimizing verification or leveraging…

Software Engineering · Computer Science 2025-10-22 Yiyang Jin , Kunzhao Xu , Hang Li , Xueting Han , Yanmin Zhou , Cheng Li , Jing Bai

Recent advances have shown the effectiveness of self-evolving LLM agents on tasks such as program repair and scientific discovery. In this paradigm, a planner LLM synthesizes an agent program that invokes parametric models, including LLMs,…

Machine Learning · Computer Science 2026-04-28 Debangshu Banerjee , Changming Xu , Eugene Ie , Ming Zhang , Daiyi Peng , Chu-Cheng Lin , Gagandeep Singh

Conventional agent systems often struggle in open-ended environments where task distributions continuously drift and external supervision is scarce. Their reliance on static toolsets or offline training lags behind these dynamics, leaving…

Artificial Intelligence · Computer Science 2026-02-09 Haotian Li , Shijun Yang , Weizhen Qi , Silei Zhao , Rui Hua , Mingzhu Song , Xiaojian Yang , Chao Peng

Developing AI agents to autonomously manipulate graphical user interfaces is a long challenging task. Recent advances in data scaling law inspire us to train computer-use agents with a scaled instruction set, yet using behavior cloning to…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Fanbin Lu , Zhisheng Zhong , Ziqin Wei , Shu Liu , Chi-Wing Fu , Jiaya Jia

Given a black-box AI system and a task, at what confidence level can a practitioner trust the system's output? We answer with a reliability level -- a single number per system-task pair, derived from self-consistency sampling and conformal…

Machine Learning · Computer Science 2026-02-26 Charafeddine Mouzouni

Agentic frameworks are the software layer through which AI agents act in the world. Existing safety methods intervene on the model and therefore remain conditional on unverifiable properties of learned behavior. We introduce containment…

Artificial Intelligence · Computer Science 2026-05-12 Royce Moon , Lav R. Varshney

The rapid evolution to autonomous, agentic AI systems introduces significant risks due to their inherent unpredictability and emergent behaviors; this also renders traditional verification methods inadequate and necessitates a shift towards…

Artificial Intelligence · Computer Science 2025-09-30 Roham Koohestani

Modern Artificial Intelligence (AI) systems lack human-like consciousness or culpability, yet they exhibit fluid agency: behavior that is (i) stochastic (probabilistic and path-dependent), (ii) dynamic (co-evolving with user interaction),…

Computers and Society · Computer Science 2026-02-23 Anirban Mukherjee , Hannah Hanwen Chang

Modern AI agents optimize programs by refactoring source code to trigger trusted compiler transformations. This preserves program semantics and reduces source code pollution, making the program easier to maintain and portable across…

Programming Languages · Computer Science 2026-04-16 Akash Deo , Simone Campanoni , Tommy McMichen

Large Language Model agents have rapidly evolved from static text generators into dynamic systems capable of executing complex autonomous workflows. To enhance reliability, multi-agent frameworks assigning specialized roles are increasingly…

Computation and Language · Computer Science 2026-04-22 Bobo Li , Rui Wu , Zibo Ji , Meishan Zhang , Hao Fei , Min Zhang , Mong-Li Lee , Wynne Hsu

Self-evolving agentic artificial intelligence (AI) offers a new paradigm for future wireless systems by enabling autonomous agents to continually adapt and improve without human intervention. Unlike static AI models, self-evolving agents…

Artificial Intelligence · Computer Science 2025-10-08 Changyuan Zhao , Ruichen Zhang , Jiacheng Wang , Dusit Niyato , Geng Sun , Xianbin Wang , Shiwen Mao , Abbas Jamalipour

AI systems improve by drawing on more compute, data, energy, and better training methods. This paper asks a precise, testable version of the "runaway growth" question: under what measurable conditions could capability escalate without bound…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Akbar Anbar Jafari , Cagri Ozcinar , Gholamreza Anbarjafari

We propose a Kardashev-inspired yet operational Autonomous AI (AAI) Scale that measures the progression from fixed robotic process automation (AAI-0) to full artificial general intelligence (AAI-4) and beyond. Unlike narrative ladders, our…

Artificial Intelligence · Computer Science 2025-11-18 Przemyslaw Chojecki

Self-evolving agents should not train on examples they cannot justify. Data-free self-evolving search agents offer a scalable route to systems that generate their own questions, answer them, and improve from their own feedback without human…

Artificial Intelligence · Computer Science 2026-05-25 Yamato Arai , Yuma Ichikawa