Related papers: APPA : Agentic Preformulation Pathway Assistant
We present $\textbf{Research Math Agents (RMA)}$, an agentic framework for automated reasoning on research-level mathematical problems. Unlike prior studies centered on competition mathematics or formal theorem proving, RMA targets…
The development of complex functional materials poses a multi-objective optimization problem in a large multidimensional parameter space. Solving it requires reproducible, user independent laboratory work and intelligent preselection of…
Large Language Models (LLMs) can be fine-tuned on domain-specific data to enhance their performance in specialized fields. However, such data often contains numerous low-quality samples, necessitating effective data processing (DP). In…
Clinical trials are critical for advancing medical treatments but remain prohibitively expensive and time-consuming. Accurate prediction of clinical trial outcomes can significantly reduce research and development costs and accelerate drug…
We introduce TAPAS (Task-based Adaptation and Planning using AgentS), a multi-agent framework that integrates Large Language Models (LLMs) with symbolic planning to solve complex tasks without the need for manually defined environment…
Prompt engineering is an iterative procedure often requiring extensive manual effort to formulate suitable instructions for effectively directing large language models (LLMs) in specific tasks. Incorporating few-shot examples is a vital and…
Physics-based motion planning is a challenging task, since it requires the computation of the robot motions while allowing possible interactions with (some of) the obstacles in the environment. Kinodynamic motion planners equipped with a…
RA is a software package that couples machine learning with formal reasoning in an attempt to find the laws that generate the empirical data that it has been given access to. A brief outline of RA in its initial stage of development is…
In our pursuit of advancing multi-modal AI assistants capable of guiding users to achieve complex multi-step goals, we propose the task of "Visual Planning for Assistance (VPA)". Given a succinct natural language goal, e.g., "make a shelf",…
Autonomous agents based on large language models (LLMs) have demonstrated impressive capabilities in a wide range of applications, including web navigation, software development, and embodied control. While most LLMs are limited in several…
Traditional drug discovery programs are being transformed by the advent of machine learning methods. Among these, Generative AI methods (GM) have gained attention due to their ability to design new molecules and enhance specific properties…
Healthcare professionals need effective ways to use, understand, and validate AI-driven clinical decision support systems. Existing systems face two key limitations: complex visualizations and a lack of grounding in scientific evidence. We…
Attention-based Transformers have revolutionized natural language processing (NLP) and shown strong performance in computer vision (CV) tasks. However, as the input sequence varies, the computational bottlenecks in Transformer models…
Keeping pace with the rapid growth of academia literature presents a significant challenge for researchers, funding bodies, and academic societies. To address the time-consuming manual effort required for scholarly discovery, we present a…
Multi-agent path finding (MAPF) attracts considerable attention in artificial intelligence community as well as in robotics, and other fields such as warehouse logistics. The task in the standard MAPF is to find paths through which agents…
Predicting material properties has always been a challenging task in materials science. With the emergence of machine learning methodologies, new avenues have opened up. In this study, we build upon our recently developed Graph Neural…
Large foundation models enable powerful reasoning for autonomous systems, but mapping semantic intent to reliable real-time control remains challenging. Existing approaches either (i) let Large Language Models (LLMs) generate trajectories…
The rapid evolution of Large Language Model (LLM) agents has necessitated robust memory systems to support cohesive long-term interaction and complex reasoning. Benefiting from the strong capabilities of LLMs, recent research focus has…
In recent decades, traditional drug research and development have been facing challenges such as high cost, long timelines, and high risks. To address these issues, many computational approaches have been suggested for predicting the…
Prevailing alignment methods target a fixed set of preferences and therefore risk forcing value lock-in as societal norms evolve over time. We introduce Adaptive Pluralistic Alignment (APA), a modular pipeline for updating pluralistically…