Related papers: Continual Harness: Online Adaptation for Self-Impr…
Equipping LLM agents with reusable skills derived from past experience has become a popular and successful approach for tackling complex and long-horizon tasks. However, such lessons are often encoded as textual guidance that remains…
Recent advances in large language models have sparked growing interest in AI agents capable of solving complex, real-world tasks. However, most existing agent systems rely on manually crafted configurations that remain static after…
Humans are the bottleneck in building and improving AI. Both the models and the agents that wrap them are written, tuned, and corrected by people. The long-horizon goal of an AI that can figure out how to improve itself remains open. Two…
Recently there has been a rising interest in training agents, embodied in virtual environments, to perform language-directed tasks by deep reinforcement learning. In this paper, we propose a simple but effective neural language grounding…
Due to the scarcity of agent-oriented pre-training data, LLM-based autonomous agents typically rely on complex prompting or extensive fine-tuning, which often fails to introduce new capabilities while preserving strong generalizability. We…
Open-ended AI agents need to be able to learn efficiently goals of increasing complexity, abstraction and heterogeneity over their lifetime. Beyond sampling efficiently their own goals, autotelic agents specifically need to be able to keep…
LLM-powered embodied agents have shown success on conventional object-rearrangement tasks, but providing personalized assistance that leverages user-specific knowledge from past interactions presents new challenges. We investigate these…
Foundation models trained on web-scale data have revolutionized robotics, but their application to low-level control remains largely limited to behavioral cloning. Drawing inspiration from the success of the reinforcement learning stage in…
Competitive Pok\'emon Singles (CPS) is a popular strategy game where players learn to exploit their opponent based on imperfect information in battles that can last more than one hundred stochastic turns. AI research in CPS has been led by…
Deep reinforcement learning has enabled robots to learn motor skills from environmental interactions with minimal to no prior knowledge. However, existing reinforcement learning algorithms assume an episodic setting, in which the agent…
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…
Recent autonomous research systems -- AI-Scientist, PaperOrchestra, AutoSOTA, DeepResearch, InternAgent, ResearchAgent and others -- show LLM agents can ideate, run experiments and write papers, but each fixes a particular control-flow…
We present AlphaLab, an autonomous research harness that leverages frontier LLM agentic capabilities to automate the full experimental cycle in quantitative, computation-intensive domains. Given only a dataset and a natural-language…
Agent harnesses -- the stateful programs that wrap a language model and decide what it sees at each step -- are now known to change end-to-end performance on a fixed model by as much as six times. That raises a question asked less often…
We introduce Pok\'eAI, the first text-based, multi-agent large language model (LLM) framework designed to autonomously play and progress through Pok\'emon Red. Our system consists of three specialized agents-Planning, Execution, and…
Embodied planning requires agents to make coherent multi-step decisions based on dynamic visual observations and natural language goals. While recent vision-language models (VLMs) excel at static perception tasks, they struggle with the…
Agent performance is strongly shaped by the surrounding harness: the external execution system around a model that organizes a task run. Yet this logic is usually buried in tightly coupled controller code, which makes harnesses hard to…
LLM agents have shown strong performance across a wide range of complex tasks, including interactive environments that require long-horizon decision making. But these agents cannot learn on the fly at test time. Self-evolving agents address…
Living organisms exhibit persistent autonomy through internally generated goals and self-sustaining behavioral organization, yet current embodied agents remain driven by externally scripted objectives. This dependence on predefined task…
We study building embodied agents for open-ended creative tasks. While existing methods build instruction-following agents that can perform diverse open-ended tasks, none of them demonstrates creativity -- the ability to give novel and…