About
Research & Development
LLM Agents Automate Engineering Modeling for Critical Heat Flux Prediction
TLDR: A new study demonstrates how Large Language Model (LLM) agents can fully automate data-driven modeling and analysis for engineering applications. Using two frameworks—a...
Research & Development
Enhancing Multimodal AI Reasoning Through Visual Uncertainty
TLDR: VOGUE is a novel method that improves Multimodal Large Language Models (MLLMs) by guiding exploration with visual uncertainty. It treats images as stochastic...
Research & Development
Lateral Tree-of-Thoughts: A New Approach to Smarter Language Model Reasoning
TLDR: Lateral Tree-of-Thoughts (LToT) is a novel search-time controller for large language models that improves upon existing Tree-of-Thoughts (ToT) methods. It addresses limitations like...
Research & Development
Internalizing Safety in AI Teams with Adversarial Co-Evolution
TLDR: AdvEvo-MARL is a novel multi-agent reinforcement learning framework that enhances the safety and robustness of LLM-based multi-agent systems. It achieves this by co-evolving...
Research & Development
AgentRec: A New Multi-Agent AI Framework for Smarter Conversational Recommendations
TLDR: AgentRec is a novel LLM-powered multi-agent framework designed to enhance conversational recommender systems. It utilizes specialized AI agents for conversation understanding, preference modeling,...
Research & Development
Assessing AI’s Understanding of Psychology: Introducing PsychoBench
TLDR: PsychoBench is a new benchmark of 2,252 U.S. National Counselor Certification Exam questions designed to evaluate the psychological knowledge of Large Language Models...