Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity
Summary
Zhening Li et al. introduce JAZ, whose invoke primitive is a minimal agent loop that treats LLM-written code and recursive subagents as the harness.
invoke is a language primitive, not a toolkit stack.
The LLM writes the body of each call; recursive invoke is the default subagent path, generalizing CodeAct and recursive language models.
Everything the model sees is a REPL variable.
Named inputs, the user prompt, and interaction history are programmable objects, so agents can search prior history instead of only reading a message list.
everything visible to the model is also a variable in the code environment
StuLife far-recall favors prompt-only invoke over specialized memory.
With GPT-5.4 nano, invoke averages about 70% pass on far-recall tasks versus Letta at about 62% and roughly half Letta's dollar cost.
With GPT-5.4 nano, it achieves 70% on the recall-heavy subset of StuLife
AppWorld self-improvement also stays inside the loop.
A top-level GPT-5.4 invoke with nano sub-invokes averages about 74% TGC, ahead of ACE on CodeAct at about 70%, while editing prompts and skills from test feedback.
it achieves 74%, outperforming CodeAct (68%), CodeAct+subagents (71%), and a specialized self-improvement harness, ACE
Hooks and dynamic scope keep the core thin.
Observability, budgets, validation, and ConfigOverride attach locally or via scope without replacing the invoke loop.
We study whether a minimal harness that is little more than the agent loop itself can exhibit these capabilities.
Read the original ↗Save to your Sponge
Summarized with Sponge. Quotes are the author’s own words.