🧰 GRPO

The items that name it 43

• [AINews] Gemini 4 Carbon tops leaderboards, launches for cyber defenders
  articleas classification.technologies2026-10-29
• Introducing LFM3: Every Modality for Specialized Intelligence
  articleas classification.technologies2026-10-27
• Bayes-Adaptive MDPs for Rollout Allocation to Enhance GRPO Training
  paperas classification.technologies2026-10-27
• Intervention-Certified Amplification: A Validity Gate for $σ$-Weighted Post-Training
  paperas classification.technologies2026-10-24
• Building Reasoning Models from the Ground Up: A Video Course
  courseas classification.technologies2026-10-24
• Profile-Driven User Simulation via Reinforcement Learning with Hierarchical Rewards for Task-Oriented Dialogues
  paperas classification.technologies2026-10-23
• When to Stop Penalizing Actions? Martingale GRPO for VLA Reinforcement Learning
  paperas classification.technologies2026-10-23
• Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox
  writeupas classification.technologies2026-10-22
• InterWebCoder: Learning Interactive Webpage Generation from Executable Tests via Reinforcement Learning
  paperas classification.technologies2026-10-20
• Rethinking GRPO for Large Reasoning Model Safety Alignment
  paperas classification.technologies2026-10-16
• [AINews] Agents disprove Polysemanticity; greatly improve Interpretability & Alignment
  articleas classification.technologies2026-10-16
• Identify, Classify, Act: Per-Instruction Controlled Compliance for LLMs over External Data
  paperas classification.technologies2026-10-16
• Welcome Beam: a 501B open model you can own, customize, and scale
  articleas classification.technologies2026-10-16
• Learning to Steer LLM Agents and Multi-Agent Systems
  paperas classification.technologies2026-10-15
• EliteReplay: Preserving Diverse Solutions in RL Post-Training via Quality-Diversity Search
  paperas frameworks and tools2026-10-15

  Reinforcement learning post-training algorithm paired with the elite archive replay loss in EliteReplay

• PROBE: Learning to Audit Policy Compliance in Tool-Using LLM Agents
  paperas classification.technologies2026-10-15
• Multi-Reward Hacking: From Aggregation-Induced Drift to Trust-Anchored Defense
  paperas classification.technologies2026-10-15
• [AINews] AI Engineer NYC: Gemini 4 Argon, Vals AI Benchmarks
  articleas classification.technologies2026-10-14
• ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning
  paperas frameworks and tools2026-10-13

  Efficient critic-free group-based RL algorithm; mentioned as a baseline that broadcasts trajectory-level advantages uniformly to all actions

• [AINews] TypeSafe/Jev at >$100M ARR, $7.5B valuation 3 weeks after launch
  articleas classification.technologies2026-10-10
• Matched-Context Group Policy Optimization for LLM Agent Training
  paperas classification.technologies2026-10-09
• A Step Harder, Not a Step Too Far: The Benefits and Limits of Curriculum Difficulty Progression in GRPO
  paperas classification.technologies2026-10-09
• RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing
  paperas classification.technologies2026-10-07
• Better Call Reward: Reward Hacking as Strategic Abstention in Legal Reasoning Models
  paperas classification.technologies2026-10-05
• OpenAI Banned PewDiePie Twice While He Built Ajax, an Uncensored AI That Will Run on Your PC
  articleas classification.technologies2026-10-03
• [AINews] not much happened today
  articleas classification.technologies2026-10-03
• Semifactual Credit-Augmented Policy Optimization
  paperas classification.technologies2026-09-30
• [AINews] Opus 5.5 is good at explainer videos
  articleas classification.technologies2026-09-29
• How GLM5.3 Sparse Attention Affects HBM Memory Usage
  articleas classification.technologies2026-09-28
• Shockingly Simple Self-retrospection Improves Agentic Models Without RL
  paperas classification.technologies2026-09-28
• Reinforcing Agentic Creativity in Scientific Ideation with Night Science
  paperas classification.technologies2026-09-28
• [AINews] The Future of Latent Space
  articleas classification.technologies2026-09-25
• SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue
  paperas classification.technologies2026-09-22
• [AINews] Here are 6 Clones of Jev in 2 days
  articleas classification.technologies2026-09-19
• Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL
  writeupas classification.technologies2026-09-10
• Training a coding model to paint watercolours with TRL and OpenEnv
  articleas classification.technologies2026-09-03
• Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
  writeupas classification.technologies2026-09-03
• whitecircle/halo
  repoas classification.technologies2026-08-26
• Granite 4.2 LLMs: How They're Built
  articleas classification.technologies2026-08-25
• 5 useful things you'll learn in my new post-training textbook (shipping now!)
  articleas classification.technologies2026-08-10
• Introducing dfs-large1: A New Frontier for Cybersecurity | depthfirst
  writeupas classification.technologies2026-07-30
• Controlling Reasoning Effort in LLMs
  articleas classification.technologies2026-07-18
• MiMo-V2.6-Flash-RL (Xiaomi)
  repoas classification.technologies

In every workspace you can read 46