Accelerating Domain-Specific Code Development for Research
Boost research coding with real-time, context-aware AI agents accessing up-to-date domain knowledge for materials science, engineering, and bioengineering.
SAVOIR: Shapley-Based Social Intelligence for AI Agents
Discover SAVOIR, a Shapley-based framework enhancing social intelligence in AI agents through fair reward attribution and improved dialogue learning.
DW-Bench: Benchmarking LLMs on Data Warehouse Graphs
Discover DW-Bench, a benchmark evaluating LLMs on data warehouse graph topology with FK and data-lineage edges for advanced reasoning.
Enhancing Safety Alignment in Large Reasoning Models
Discover how modifying reasoning structures with AltTrain improves safety alignment in large reasoning models, reducing harmful AI outputs effectively.
Personalized Benchmarking for LLMs Based on User Preferences
Discover how personalized benchmarking improves LLM evaluation by aligning models with individual user preferences and diverse communication styles.