Strong-tier models benefit less from harness evolution because they already solve many tasks under the initial harness, leaving less room for improvement (ceiling effect)

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• what explains why weak-tier models with the most performance headroom benefit least from harness evolution?question0.871
  In-depth diagnostic question addressed by the two failure mode analysis
• Weak-tier models often fail to invoke relevant harness artifacts during task-solving, with Qwen3-32B showing a 25% load rate against ~96% for strong modelsclaim0.823
  Diagnosis of first failure mode explaining low harness-benefit for weak-tier models
• Even when the harness is loaded, weak-tier models fail to adhere to it due to weak instruction-following over long-horizon tasks, drifting more than four times more steeply than strong modelsclaim0.821
  Diagnosis of second failure mode explaining low harness-benefit for weak-tier models
• weak-tier models gain little, traced to two failure modes: failing to activate relevant harness artifacts and failing to follow them faithfully once activatedquote0.813
  Verbatim summary of weak-tier harness-benefit failure diagnosis from conclusion
• harness-updating is flat in base capability: models across capability tiers produce updates that yield similar gains, and even the Qwen3.5-9B evolver induces gains comparable to Claude Opus 4.6quote0.795
  Verbatim summary of first major finding from conclusion
• which models actually benefit from updated harnesses?question0.781
  Second open question the paper sets out to answer through agent-side analysis
• Harness-updating capability is flat in base capability: models from different capability tiers produce harness updates that lead to surprisingly similar gainsclaim0.771
  First major claim of the paper, supported by narrow spread across evolvers and case study
• End-to-end evaluation scores conflate three sources of improvement: base capability, harness-updating quality, and harness-benefit, leaving it unclear which models produce useful updates or benefit most from themclaim0.760
  Motivating claim for the paper's controlled analysis approach