report-per-family-spread-aggregate-agent-score TEC-0175 · proposedReport per-family spread, not an aggregate agent score
Split an agent benchmark into skill-isolated families with verifier-computed gold (canonical SQL, exact DAG schedule, closed-form lambda) and report per-family accuracy plus token cost from one instrumented run instead of a blended score.
Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.
Split an agent benchmark into skill-isolated families with verifier-computed gold (canonical SQL, exact DAG schedule, closed-form lambda) and report per-family accuracy plus token cost from one instrumented run instead of a blended score. Filed by the drafting stage from BekchiAI: Measuring, Observing, and Controlling LLM Agents in One Click (2608.26867) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: Four models scored on 13 families; overall scores 0.88/0.86/0.82/0.71 while gpt-oss-120b led ug_fetch (0.78) and ug_imposter (0.89) yet scored 0.24 on sql_analytics and 0.25 on tool_error_recovery. No human validation of the families' construct validity.. Nobody has vouched for it; add support or contest it on this page.
Does it work?
nothing measured0 supporting · 0 contesting sources
Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.
No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.
No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.
Code
No repository linked yet. Contribute one.
Sources
Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.