Fetching from the wire…
01
02
03
04
05
06
07
08
Research2026-08-09 · source-backed
HarnessOpt-Bench (arXiv 2608.06301) has a frontier LLM act as an optimizer receiving a target agent's seed harness (prompts, tools, control flow, memory, orchestration code) plus graded eval feedback and a fixed evaluation budget, then edits and nominates a candidate scored on a held-out partition. Across 5 frontier models, 4 downstream tasks, 111 scored runs, optimizer models separated more than the coding harnesses they acted through, and native harnesses didn't consistently beat shared ones. Practical read: when you hand your agent scaffold to a model to improve, spend on the strongest optimizer rather than standardizing tooling around it. And always hold out a test partition, because self-graded harness edits overfit the feedback set.
Each link below shares sources, entities, or timing with this story.
LLM uses OpenAI / Shared entity: LLM / Shared topic / Earlier coverage
Linked by a graph relationship (LLM uses OpenAI); both cover LLM; overlapping topics (agent, model).
LLM uses OpenAI / Same source domain / Shared topic / Tension
Linked by a graph relationship (LLM uses OpenAI); reported by the same outlet (arxiv.org); overlapping topics (agent, model).
Simon Willison released LLM / Shared entity: LLM / Shared topic / Earlier coverage
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; overlapping topics (agent, model).
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; overlapping topics (agent, alway).
Simon Willison released LLM / Shared entity: Bench / Shared topic / Earlier coverage
Linked by a graph relationship (Simon Willison released LLM); both cover Bench; overlapping topics (agent, model).
LLM uses OpenAI / Shared entity: LLM / Earlier coverage / Tension
Linked by a graph relationship (LLM uses OpenAI); both cover LLM; earlier LLM coverage from 2026-07-27.
LLM uses OpenAI / Shared entity: Bench / Earlier coverage / Tension
Linked by a graph relationship (LLM uses OpenAI); both cover Bench; earlier Bench coverage from 2026-04-25.
Simon Willison released LLM / Shared entity: LLM / Earlier coverage / Tension
Linked by a graph relationship (Simon Willison released LLM); both cover LLM; earlier LLM coverage from 2026-06-19.