Tag: reinforcement-learning

Showing 1-3 of 3

Feb 06, 20267 min readAgent PlaybookIntermediate5 min build

Agent-Omit: A training framework for adaptive omission of thoughts and observations in LLM agents

Agent-Omit trains LLM agents to omit redundant internal thoughts and observations using cold-start omission data plus omit-aware RL; includes a KL-divergence bound and Agent-Omit-8B results.

agents LLM reinforcement-learning efficiency omission

+3 more

Model BreakdownsUnited States

Open

Feb 06, 20266 min readFounder NotesAdvanced5 min build

ORBIT: Cross‑Episode Meta‑RL for In‑Context Online Adaptation of LLMs

ORBIT trains LLMs via cross-episode meta-RL so models learn from interaction traces at inference; authors report Qwen3-14B matches GPT-5.2 on unseen environments after meta-training.

LLM in-context learning meta-RL ORBIT Qwen3-14B

+3 more

GPT-5.2 reinforcement-learning online learning

TutorialsUnited States

Open

Feb 06, 20268 min readTooling Deep DiveIntermediate240 min build

Scalable Interactive Oversight: building a decision-tree prototype to collect node-level feedback and steer LLMs

Guide to building Scalable Interactive Oversight: decompose intent into a decision tree, collect low‑burden node feedback, aggregate signals, and gain 54% better alignment.

scalable-interactive-oversight LLM human-in-the-loop reinforcement-learning alignment

+3 more

tooling supervision decomposition