weak-tier models gain little, traced to two failure modes: failing to activate relevant harness artifacts and failing to follow them faithfully once activated

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 modelsclaim0.871
  Diagnosis of second failure mode explaining low harness-benefit for weak-tier models
• 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 modelsclaim0.858
  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)hypothesis0.813
  Explanation offered for why high-base-capability models show lower Δbenefit
• 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-tierclaim0.803
  Second major claim of the paper, supported by Δbenefit measurements across six models on three benchmarks
• what explains why weak-tier models with the most performance headroom benefit least from harness evolution?question0.803
  In-depth diagnostic question addressed by the two failure mode analysis
• Weak-tier model deficits are not in task understanding but in protocol-level and procedural execution: they identify the right skill but cannot operate under itclaim0.794
  Diagnostic claim from case studies of activation and adherence failures in Qwen3-32B
• Harness invocation should be treated as a first-class learned skill and baked into agent training, as weak-tier models fail to load skills 75% of the timeclaim0.757
  Design recommendation derived from harness activation failure finding
• Overbid frequency, self-bidding rate, bankrupt-initiation patterns, and context-dependent offer calibration are failure modes invisible to both static evaluations and aggregate rankings like Eloclaim0.752
  key claim about the benchmark's unique diagnostic value