Related papers: Optimizing Life Sciences Agents in Real-Time using…
With recent and rapid advancements in artificial intelligence (AI), understanding the foundation of purposeful behaviour in autonomous agents is crucial for developing safe and efficient systems. While artificial neural networks have…
Developing robotic agents that can perform well in diverse environments while showing a variety of behaviors is a key challenge in AI and robotics. Traditional reinforcement learning (RL) methods often create agents that specialize in…
AI agents -- systems that combine foundation models with reasoning, planning, memory, and tool use -- are rapidly becoming a practical interface between natural-language intent and real-world computation. This survey synthesizes the…
Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning, yet their application in agentic, multi-step reasoning within interactive environments remains a difficult challenge.…
Learning continually and online from a continuous stream of data is challenging, especially for a reinforcement learning agent with sequential data. When the environment only provides observations giving partial information about the state…
Active learning for regression reduces labeling costs by selecting the most informative samples. Improved Greedy Sampling is a prominent method that balances feature-space diversity and output-space uncertainty using a static,…
Adapting production-level computer vision tools to bespoke scientific datasets is a critical "last mile" bottleneck. Current solutions are impractical: fine-tuning requires large annotated datasets scientists often lack, while manual code…
In order perform a large variety of tasks and to achieve human-level performance in complex real-world environments, Artificial Intelligence (AI) Agents must be able to learn from their past experiences and gain both knowledge and an…
Critical sectors of human society are progressing toward the adoption of powerful artificial intelligence (AI) agents, which are trained individually on behalf of self-interested principals but deployed in a shared environment. Short of…
Large Language Models (LLMs) have advanced artificial intelligence by enabling human-like text generation and natural language understanding. However, their reliance on static training data limits their ability to respond to dynamic,…
Reinforcement Learning (RL) has made significant strides in enabling artificial agents to learn diverse behaviors. However, learning an effective policy often requires a large number of environment interactions. To mitigate sample…
Current context augmentation methods, such as retrieval-augmented generation, are essential for solving knowledge-intensive reasoning tasks. However, they typically adhere to a rigid, brute-force strategy that executes retrieval at every…
A default assumption in the design of reinforcement-learning algorithms is that a decision-making agent always explores to learn optimal behavior. In sufficiently complex environments that approach the vastness and scale of the real world,…
Large language models (LLMs) based Agents are increasingly pivotal in simulating and understanding complex human systems and interactions. We propose the AI-Agent School (AAS) system, built around a self-evolving mechanism that leverages…
The learning from practice paradigm is crucial for developing capable Agentic AI systems, yet it is severely hampered by inefficient experience generation, a bottleneck especially pronounced in complex benchmarks like GAIA. To address this,…
We describe AI agents as stochastic dynamical systems and frame the problem of learning to reason as in transductive inference: Rather than approximating the distribution of past data as in classical induction, the objective is to capture…
The last few years have witnessed substantial progress in the field of embodied AI where artificial agents, mirroring biological counterparts, are now able to learn from interaction to accomplish complex tasks. Despite this success,…
Recent advances in large language model (LLM) have empowered autonomous agents to perform multi-turn interactions with tools and environments. However, scaling such agent training is limited by the lack of diverse and reliable environments.…
Recent advances in large language models (LLMs) have enabled a new class of AI agents that automate multiple stages of the data science workflow by integrating planning, tool use, and multimodal reasoning across text, code, tables, and…
Dynamic Data selection aims to accelerate training by prioritizing informative samples during online training. However, existing methods typically rely on task-specific handcrafted metrics or static/snapshot-based criteria to estimate…