SEED is a self-evolving on-policy distillation framework for long-horizon LLM agents that uses a single policy checkpoint to collect trajectories, analyze them into hindsight skills, and distill skill-induced action probability shifts back into itself during RL.
198
No data
7
1
MIT
2026-07-17
It introduces a novel paradigm where the policy and its hindsight supervision co-evolve, achieving dense token-level supervision from sparse trajectory rewards without external skill banks or retrieval at inference.
Similar projects matched by category, topics, and programming language.
Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.