Tag: AI research agent
Browse our exclusive articles!
Evaluating Agentic LLMs with Semantics-Preserving CTF Challenges
Explore a novel family-based method to evaluate agentic LLMs using semantics-preserving transformations for enhanced robustness in cybersecurity tasks.
CoMeT: Efficient Long-Context Transformer for LLMs
Discover CoMeT, the Collaborative Memory Transformer that enables efficient long-context modeling with constant memory and linear time complexity.
Disco-RAG: Advanced Discourse-Aware Retrieval Generation
Discover Disco-RAG, a discourse-aware retrieval-augmented generation framework that boosts AI performance in knowledge-intensive tasks and long-document su...
Unified Entropy Control Boosts Reinforcement Learning
Discover how Unified Entropy Control enhances reinforcement learning with targeted exploration and stable optimization for better model performance.
ARC-AGI-3 Benchmark: Advancing Agentic AI Intelligence
Discover ARC-AGI-3, the new benchmark pushing AI limits in adaptive agentic intelligence with turn-based, interactive challenges and strategic planning.