DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning — Changelog https://aaas.blog/paper/deepseek-r1-incentivizing-reasoning-capability-in-llms-via-rl Change history for DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning on the AaaS Knowledge Index. en-us Mon, 01 Jun 2026 12:08:03 GMT 1 field changed [Modified] brokenLinks: [] -> ["https://platform.deepseek.com/api-docs"] https://aaas.blog/paper/deepseek-r1-incentivizing-reasoning-capability-in-llms-via-rl gCGYd6qNljDJ3jIb6ZmF Mon, 01 Jun 2026 12:08:03 GMT 1 field changed [Added] brokenLinks: [] https://aaas.blog/paper/deepseek-r1-incentivizing-reasoning-capability-in-llms-via-rl auf8rWz0R3VfHmSbPUug Mon, 25 May 2026 10:37:13 GMT 2 fields changed [Modified] scores.citations: 82 -> 0 [Modified] scores.composite: 74.5 -> 54 https://aaas.blog/paper/deepseek-r1-incentivizing-reasoning-capability-in-llms-via-rl 9nHLNdMtCiPpnfB6Vrmr Fri, 15 May 2026 06:52:58 GMT