Harness Engineering: The Hidden Key to Recursive Self-Improvement
Harness Engineering for Self-Improvement
Recursive self-improvement (RSI) in AI isn't just about models rewriting their own weights—it's increasingly about the 'harness' surrounding them. This post explores how harness engineering, from workflow automation to context management, is becoming the critical driver of AI progress. Drawing on recent frameworks like Agentic Context Engineering and Meta-Harness, it argues that optimizing the harness—the system that orchestrates the model's actions—may be the most practical near-term path to RSI, potentially surpassing raw model intelligence in importance.
A harness should encapsulate complicated logic while keeping the interface simple.
- bisonbear
I’ve been thinking about how we practically implement this at an organizational layer for large codebases. There’s clearly alpha to be had in optimizing AGENTS.md / skills / tools / … to improve performance, quality, and cost efficiency of an agent. The problem is defining what quality means, and providing a way for agents to optimize the harness using that lever.
The first step I see towards this is building a generic, reliable, and accurate *fitness function* for codebases - turning PRs into gradeable tasks that an agent can solve, and improve on.
I’m pretty curious how others are optimizing the coding agent harness now, as this has been a huge pain point for my company (we’re pretty much relying solely on vibes).
- zby
IMHO training weights has peaked and now it is time for a training paradigm for prompts and code. We don't have the gradient descent here - but I think it can be more sample efficient because causal theories can be better than just correlations.
I am working on a unified theory in https://zby.github.io/commonplace/ - it is all agent edited so it might be hard to read, but hopefully we are catching most logical errors. Some day the llm prose will improve.
I have even a preliminary theory on what is needed for the positive feedback loop: https://zby.github.io/commonplace/articles/reflective-self-i... - (this is not stable yet - but I think you can give it to your agent to read :).
- erwincoumans
Thanks for the really nice in-depth post! Hoping for a future one about:
"Much recent work on auto-research, self-improving agents, and evolutionary program search can be organized around this question. Other work on model self-play, synthetic data, test-time training and a broader theme of continual learning also matches the RSI vision (e.g. Yuan et al. 2024, Chen et al. 2024), Zhao et al. 2025, Choi et al. 2026)) but they will not be the focus of this post."
- cahaya
Thanks for the post. For https://Document.bot (Kinda Cursor IDE for knowledge workers), im already trying to improve the harness (besides spotting bugs) using hillclimb experiments. More and more i'm using a AI harness engineering skill in Codex to further improve the app. This blog post helped me to improve the skill a bit.
- Kinrany
The quest for Torment Nexus continues