相关论文: Agentic Design of Compositional Machines

Reinforcement Learning (RL) is essential for evolving Large Language Models (LLMs) into autonomous agents capable of long-horizon planning, yet a practical recipe for scaling RL in complex, multi-turn environments remains elusive. This…

Game environments provide rich, controllable settings that stimulate many aspects of real-world complexity. As such, game agents offer a valuable testbed for exploring capabilities relevant to Artificial General Intelligence. Recently, the…

Recent engineering developments in specialised computational hardware, data-acquisition and storage technology have seen the emergence of Machine Learning (ML) as a powerful form of data analysis with widespread applicability beyond its…

There is growing interest in using machine learning (ML) to support clinical diagnosis, but most approaches rely on static, fully observed datasets and fail to reflect the sequential, resource-aware reasoning clinicians use in practice.…

Small language models (SLMs) offer compelling advantages in cost, latency, and adaptability, but have so far lagged behind larger models on long-horizon software engineering tasks such as SWE-bench, where they suffer from pervasive action…

We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data. CompILE uses a novel unsupervised,…

Large language models (LLMs) have proven to be highly effective for solving complex reasoning tasks. Surprisingly, their capabilities can often be improved by iterating on previously generated solutions. In this context, a reasoning plan…

Large Language Models (LLMs) have the potential to accelerate small molecule drug design due to their ability to reason about information from diverse sources and formats. However, their practical utility remains unclear due to the lack of…

Modelica is a widely adopted language for simulating complex physical systems, yet effective model creation and optimization require substantial domain expertise. Although large language models (LLMs) have demonstrated promising…

Large Language Models (LLMs) and Vision Language Models (VLMs) possess extensive knowledge and exhibit promising reasoning abilities, however, they still struggle to perform well in complex, dynamic environments. Real-world tasks require…

Background: There is great interest in agentic LLMs, large language models that act as agents. Objectives: We review the growing body of work in this area and provide a research agenda. Methods: Agentic LLMs are LLMs that (1) reason, (2)…

The burgeoning field of generative artificial intelligence has fundamentally reshaped our approach to content creation, with Large Vision-Language Models (LVLMs) standing at its forefront. While current LVLMs have demonstrated impressive…

Autoresearch offers a flexible paradigm for automating scientific tasks, in which an AI agent proposes, implements, evaluates, and refines candidate solutions against a quantitative objective. Here, we use composition-based…

Finite element (FE) analysis guides the design and verification of nearly all manufactured objects. It is at the core of computational engineering, enabling simulation of complex physical systems, from fluids and solids to multiphysics…

Compositionality is considered central to language abilities. As performant language systems, how do large language models (LLMs) do on compositional tasks? We evaluate adjective-noun compositionality in LLMs using two complementary setups:…

Humans can reason compositionally when presented with new tasks. Previous research shows that appropriate prompting techniques enable large language models (LLMs) to solve artificial compositional generalization tasks such as SCAN. In this…

Recent trends are emerging in the use of Large Language Models (LLMs) as autonomous agents that take actions based on the content of the user text prompts. We intend to apply these concepts to the field of Guidance, Navigation, and Control…

Agent-based models (ABMs) are ubiquitous in research and industry. Currently, simulating ABMs involves at least some imperative (step-by-step) computer instructions. An alternative approach is declarative programming, in which a set of…

We propose a set of compositional design patterns to describe a large variety of systems that combine statistical techniques from machine learning with symbolic techniques from knowledge representation. As in other areas of computer science…

Reinforcement learning (RL) is increasingly used to improve the reasoning, coding, and tool-use capabilities of large language models, but agentic RL remains prohibitively expensive. Scaling RL to agentic LLMs requires supporting complex…