Reinforcement Learning with Verifiable Rewards (RLVR) has been central to the recent success of Large Reasoning Models. …

Data policies for reinforcement learning with verifiable rewards (RLVR) determine which rollouts are used, how strongly …

Reinforcement learning with verifiable rewards (RLVR) substantially improves single-sample accuracy (pass@1) but causes …

Agent 工程系统学习第 13 章（前沿专题）：三个高薪高门槛方向。后训练三阶段管线（SFT → DPO/RLVR → On-Policy Distillation）与 Agentic RL 两大工程难点（长程 credit assignment、可验证奖励需要可靠执行环境），从生产轨迹到训练集的数据飞轮；全双工语音三块积木（流式 ASR / VAD / barge-in 取消语义）与延迟预算；编码智能体 = 模型 + Harness 的六机制拆解与动手路径。

Multi-step agents are trained on flat action streams: SFT and RLVR weight every token uniformly and ignore the sub-proce…

Reinforcement learning with verifiable rewards (RLVR) improves the reasoning capabilities of large language models (LLMs…

Group relative policy optimization for reinforcement learning with verifiable rewards (RLVR) typically uses a fixed impo…

「Agent 工程系统学习」专题导读：一套教材型 AI Agent 工程学习资料的总览。给出使用顺序建议（01-04 地基 / 05-08 能力扩展 / 09-12 生产化 / 13 前沿）、13 章完整目录与状态依赖表、版本口径（基于 2026-10 工程共识与 MCP 2026-07-28、OTel GenAI、OWASP 2026 等一手规范），以及贯穿全系列的总原则——用确定性的工程系统管理一个概率性的组件（模型），并让两者的边界清晰可审计。

梦晨* 2026-10-03 10:38:19 来源：量子位 文婷 发自 凹非寺 量子位 | 公众号QbitAI 他来了他来了，TypeSafe AI的联合创始人兼CEO **Diogo Almeida**，顶着一头新染的红发闪亮登场了！…

On-policy learning has been argued to reduce catastrophic forgetting, produce sparser parameter updates, and improve gen…

TypeSafe AI 的 Jev 全面开放，注册即得 5 美元额度（约 1.2 亿输入 Token），输出 Token 永久免费。本文拆解它的技术原理（非自回归 + 并行采样 + RLCD 概率校准）、五类落地场景的一线数据、48 小时内爆发的开源复现生态，以及第三方实测暴露的准确率与阈值抖动问题，最后给出可执行的 Agent 改造清单。

Multi-turn agents trained with reinforcement learning (RL) receive a single scalar reward per trajectory, which motivate…

Agent trajectories record what an agent does and what happens next. Yet standard supervised fine-tuning (SFT) applies lo…

Training prompts in online reinforcement learning (RL) differ substantially in how informative they are for the current …

A core goal of efficient reasoning is to improve the accuracy-efficiency frontier. However, jointly improving reasoning …

Reinforcement learning (RL) has become central to post-training of large language models. Recent advances in RL for Mixt…

Reinforcement learning with verifiable rewards is typically performed on-policy, keeping training data close to the curr…

We demonstrate that training LLMs with RL does not improve performance equally across a dataset. RL shows large improvem…

On-policy distillation (OPD) provides dense, per-token supervision for language model post-training, but its effectivene…