Posts

All the articles I've posted.

• Do Verifier Errors Grow Superlinearly with Horizon? A Six-Stage Experiment

  Updated: 17 Aug, 2026 · 17 min read

  A preregistered 224-artifact study confirms a 66% hybrid-verifier improvement, does not support the universal superlinear headline, and finds that task structure can reverse the apparent horizon effect.

• From Tool Calls to Policy Updates: A Reproducible Agent RL Stack

  14 Aug, 2026 · 45 min read

  A reproducible blueprint for Agent RL: environment snapshots, verifier contracts, credit assignment, three-policy semantics, asynchronous generation and training, partial rollouts, and runnable smoke tests.

• A Repair Can Save a Trajectory Without Teaching the Agent

  14 Aug, 2026 · 18 min read

  An eight-seed counterfactual-replay experiment found that high-value one-action repairs reliably rescue failed agent trajectories—but a repair-value-dominant SFT selector did not beat simpler rules and recovered only 25% of matched-RL improvement.

• Beyond 49 ms: Where VM Resume Latency Actually Goes in Agentic RL

  14 Aug, 2026 · 21 min read

  A measurement-first look at fast sandbox resume, speculative tool execution, and action-observation co-speculation—and why time-to-useful-work matters more than boot time.

• Reproducing CompactRL: What Worked, What Failed, and Why We Did Not Scale

  Updated: 24 Jul, 2026 · 16 min read

  An auditable CompactRL reproduction spanning the public algorithm, a 96-step long-horizon simulation, integration with slime, real Qwen actor-critic training, value-function fixes, 17 experimental phases, and the evidence that stopped us from scaling.

• From Long CoT to Agent Swarms: The Documented Evolution of Kimi's Reinforcement Learning

  18 Jul, 2026 · 15 min read

  A source-grounded history of Kimi's reinforcement-learning stack, from Kimi k1.5's long-context outcome RL and partial rollouts to K2's general RL and K2.5's multimodal GRMs and Parallel-Agent RL.