Evaluating LLMs for Accurate Chemical Cost Estimation
Discover how LLMs perform on chemical cost reasoning with the ChemCost benchmark, revealing strengths and challenges in pricing chemical reactions.
EnvSimBench: Benchmarking LLM Environment Simulation Accuracy
Discover EnvSimBench, a benchmark to evaluate and improve LLM-based environment simulation, enhancing AI agent training and reducing errors.
MemoRepair: Fixing Cascade Updates in Agentic Memory AI
Discover MemoRepair, a breakthrough method that solves cascade update issues in agentic memory, boosting AI reliability and reducing invalid memory exposur...
HMACE: Multi-Agent Evolution for Combinatorial Optimization
Discover HMACE, a multi-agent framework boosting efficiency in solving complex combinatorial optimization problems using collaborative AI evolution.
AIDA: Autonomous Business Intelligence for Data Insights
Discover AIDA, the autonomous agent transforming complex data into actionable business insights with advanced AI and reinforcement learning.