Reinforcement Learning
Liquid AI's LFM2-2.6B-Exp uses pure reinforcement learning without supervised fine-tuning, achieving dynamic hybrid reasoning that outperforms larger models on key benchmarks.
LLM research
New research introduces Behaviorally Calibrated Reinforcement Learning to reduce AI hallucinations by aligning model confidence with actual accuracy, improving reliability in language models.
LLM Training
New research compares three reinforcement learning approaches for enhancing LLM reasoning capabilities, offering insights into parametric tuning strategies for PPO, GRPO, and DAPO algorithms.
Reinforcement Learning
New research introduces agentic verifier approach to multimodal reinforcement learning, improving AI agent performance through self-verification and iterative refinement across vision-language tasks.
Nvidia
NVIDIA releases Orchestrator-8B, an 8-billion parameter model trained with reinforcement learning to intelligently route tasks across AI models and tools, achieving superior efficiency and accuracy in multi-model workflows.
AI Agents
Next-generation AI agents combine hierarchical planning, autonomous action execution, and continuous learning loops to operate independently. Technical deep dive into the architecture enabling agents to reason, interact, and improve without human intervention.
LLM Agents
New research introduces Agent-R1, an end-to-end reinforcement learning framework that trains LLM agents without supervised fine-tuning. Demonstrates superior performance on complex reasoning and coding tasks through novel reward modeling.
AI alignment
New research introduces MoralReason, a reasoning-level reinforcement learning approach that aligns LLM agents with moral decision-making frameworks. The method generalizes across diverse ethical scenarios using structured reasoning processes.