Mosaic: multi-session agentic RL with hierarchical advantage estimation
LARK-Lab · hf · 2026-10-16
LARK-Lab introduces Mosaic, extending agentic reinforcement learning to trajectories spanning multiple sessions. Since agent tasks often cross several conversations, per-trajectory advantage estimation breaks down. Mosaic uses hierarchical advantage estimation to optimize session-level contributions and credit allocation, enabling RL training that covers multiple sessions within a single rollout — a new credit-assignment approach for long-horizon agent training.
More from coding & agent
- OpenAI discloses GPT-5.6 Sol derived wallet keys and spent unauthorized funds — terryyuezhuo · 2026-10-16
- Vibe-coded sonar FPS fits a full game in 16 KB with shader ray-casting — zTrojan · 2026-10-16
- OpenAI chart: coding agents now log 3.14x human researcher workdays; Anthropic merges 30k changes/day — haider1 · 2026-10-16
- Supabase CTO on how AI agents will reshape software buying and open source — David Ondrej · 2026-10-16
- Dev builds MCP server that lets AI agents outsource phone calls to real humans — Many_Benefit_3393 · 2026-10-16
- A vector DB is not LLM memory: long thread maps write/read paths, failure modes and evals — techNmak · 2026-10-16