Efficient Pruning of Long Chain-of-Thought in LRMs
Optimize Large Reasoning Models by pruning long chain-of-thought outputs to reduce computation without losing reasoning quality.
RL-PLUS: Enhancing LLMs in Reinforcement Learning
Discover RL-PLUS, a hybrid-policy optimization method that overcomes capability boundary collapse in LLMs, boosting reasoning and problem-solving skills.
Orak Benchmark: Train & Evaluate LLM Agents in Video Games
Discover Orak, a benchmark for training and evaluating LLM agents across diverse video games with fine-tuning datasets and versatile game coverage.
FieldWorkArena: Real-World Agentic AI Benchmark for Safety
Discover FieldWorkArena, a benchmark evaluating agentic AI in real fieldwork tasks to improve safety and efficiency in manufacturing and retail.
Agentic AI Optimisation: What It Is & Why It Matters
Discover Agentic AI Optimisation (AAIO), how it works, why it’s crucial for digital interactions, and its ethical and regulatory impact.