Related papers: Self-Improving AI Agents through Self-Play
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,…
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…
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…
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…
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…
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…
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,…
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…
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…
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…
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…
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…
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),…
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…
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…
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…
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…
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…
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…