… The following papers were recommended by the Semantic Scholar API STARS: Skill-Triggered Audit for Request-Conditioned Invocation Safety in Agent Systems 2026 PolicyBank: Evolving Policy Understanding for LLM Agents 2026 On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment… …
… AI-generated summary On-policy distillation OPD is widely used for LLM post-training. When pushed with a reward-extrapolation coefficient lambda 1, the student can lift past the teacher in domain, but past a threshold lambda the same step violates the output contract on structured-output tasks . …
… I found the explanation of Hugging Face’s “Skills Training” initiative — how it lets you use a coding‑agent like Claude Code or other supported agents to fine‑tune large language models, submit GPU jobs, monitor progress and push trained models to the Hub — particularly eye‑opening. …
… Leveraging the observation that driving VLAs often emit structured JSON-like outputs, Fast-dDrive freezes structural tokens into a section scaffold and employs a section-aware training recipe that prioritizes safety-critical planning. …