AI Model Benchmarking: Challenges and Insights 2025
Explore the fragmented AI benchmarking landscape in 2025, revealing inconsistencies and the need for standardized evaluation of AI models.
Boosting Weak Reasoning Models with Agentic Systems
Explore how agentic systems enhance weak reasoning models using verifier-backed committees for improved AI inference and decision-making.
Efficient Distribution-Aware Algorithm Design with LLM Agents
Discover how LLM agents optimize algorithm design by balancing solution quality and execution speed in combinatorial optimization tasks.
ClawForge: Benchmarking Command-Line AI Agents Effectively
Discover ClawForge, a cutting-edge framework for realistic, interactive benchmarks to evaluate command-line AI agents in dynamic workflows.
Attention-Guided Decision Models for Pharmacists in Drug Shortages
Explore how attention-guided dynamic decomposition aids pharmacists in managing drug shortages with bounded rationality and improved decision-making.