Loading the harness is not sufficient for benefiting from it: a model with near-ceiling SLR can still have low HFR and LPR

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

• 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 modelsclaim0.774
  Diagnosis of second failure mode explaining low harness-benefit for weak-tier models
• Harness-benefit is non-monotonic in base capability: weak-tier models benefit little, mid-tier models benefit most, and strong-tier models benefit less than mid-tierclaim0.772
  Second major claim of the paper, supported by Δbenefit measurements across six models on three benchmarks
• which models actually benefit from updated harnesses?question0.761
  Second open question the paper sets out to answer through agent-side 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 modelsclaim0.753
  Diagnosis of first failure mode explaining low harness-benefit for weak-tier models
• 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)hypothesis0.753
  Explanation offered for why high-base-capability models show lower Δbenefit
• weak-tier models gain little, traced to two failure modes: failing to activate relevant harness artifacts and failing to follow them faithfully once activatedquote0.747
  Verbatim summary of weak-tier harness-benefit failure diagnosis from conclusion
• what explains why weak-tier models with the most performance headroom benefit least from harness evolution?question0.743
  In-depth diagnostic question addressed by the two failure mode analysis
• Harness-updating capability is flat in base capability: models from different capability tiers produce harness updates that lead to surprisingly similar gainsclaim0.737
  First major claim of the paper, supported by narrow spread across evolvers and case study