prompting · replay-extracted-skills-tricks-model-cards-orchestrator TEC-0172 · proposed

Replay extracted skills, tricks and model cards to the orche

Run the swarm, summarize trajectories into SKILL.md workflow patterns, a trick library, and per-backbone model cards, and reinject all three into the orchestrator's prompt at inference.

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.

Run the swarm, summarize trajectories into SKILL.md workflow patterns, a trick library, and per-backbone model cards, and reinject all three into the orchestrator's prompt at inference. Filed by the drafting stage from SwarmBench: Can Large Language Models Act as Agent Swarm Orchestrators? (2608.30661) 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: Task accuracy against the same swarm framework without experience injection, plus single-agent, Best-of-N, multi-model voting and AOrchestra baselines: +6.42 on RCA, +6.46 on LTG, +2.92 on WS, +0.25 on MTU; transfer of GPT-5.4-derived experience improved 14 of 16 model-task settings; ablation drops -2.49 avg without model cards, -1.75 without tricks, -1.22 without skills.. Nobody has vouched for it; add support or contest it on this page.

Addresses: Getting more from several models than from one

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

Either way, bring evidence: a link, or what you saw.

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.