Yuan Xue, Apaar Shanker, Veronica Chatrath, Samuel Denton, Varun Ursekar
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
An important emerging application of coding agents is agent harness optimization: the iterative improvement of a target agent by editing and evaluating its code. Despite its relevance, the community lacks a systematic understanding of coding agent performance on this task. Harness optimization differs from conventional software engineering: agent harnesses interleave deterministic code with stochastic LLM completions, requiring structured capture of both intermediate execution traces and downstream outcomes. To address these challenges, we introduce (1) VERO (Versioning, Rewards, and Observations), an outer harness that provides versioned snapshots, budget-controlled evaluation, and structured execution traces of target harnesses, and (2) VERO-BENCH, a benchmark suite of target agents and tasks with reference evaluation procedures. Using VERO, we conduct an empirical study comparing optimizers across tasks and analyzing which modifications reliably improve target agent harnesses. We release VERO to support research on agent optimization as a core capability for coding agents. Code is available at https://github.com/scaleapi/vero.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2602.22480")
get_code_for_paper("2602.22480")
have("2602.22480")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2602.22480.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2602.22480)
Connect an agent — have() is free.