Tagged “reinforcement-learning”

4 posts.

All Model Architecture13 Training & Alignment8 Inference & Serving11 Agents & Orchestration10 Reasoning & Evaluation7 Safety, Security & Governance3 Platforms & Practice11

Agents & Orchestration 24 min

Agentic Reinforcement Learning: Training Models to Act, Not Just Answer

RLHF taught a model to answer one question well. Agentic RL asks a harder thing: take fifty actions in a live environment, most of them invisible in the final reward, and still learn which ones mattered. That single change, from …

agentic-ai reinforcement-learning rlvr tool-use ∑ ◫

Training & Alignment 21 min

RL from Verifiable Rewards: Training Models on Answers That Can Be Checked

Replace the reward model with a function that simply checks the answer, and a frontier reasoning model falls out of pure reinforcement learning. The catch is what 'checkable' quietly assumes, and what the model learns to exploit.

rlvr reinforcement-learning reasoning grpo ∑ ◫

Reasoning & Evaluation 18 min

Test-Time Compute: How Reasoning Models Buy Intelligence by the Token

A 7B model that thinks for thirty seconds can outscore a 70B model that answers instantly. Test-time compute is the lever that makes this possible, and it is quietly rewriting the economics of model design.

reasoning test-time-compute inference reinforcement-learning ∑ ◫

Training & Alignment 21 min

Why Token-Level RL Collapses: GSPO and Sequence-Level Importance Sampling

GRPO weights every token by its own importance ratio, and on long responses that single-sample estimator quietly poisons the gradient until the model collapses. GSPO moves the ratio up to the whole sequence, and Qwen3's largest m…

reinforcement-learning rlhf gspo grpo ∑ ◫