New papers say scaffolds explain only 1.5% of agent performance variance
gerardsans · x · 2026-07-21
A thread about two papers argues that “agent” scaffolds may contribute far less than people assume.
- MORPHEUS (NeurIPS 2026) is cited as finding that scaffolds explain only 1.5% of performance variance, while the base next-token model explains 41.4%—about 28× more.
- The implication: multi-agent swarms, chain-of-thought wrappers, and similar orchestration layers often just reshape prompts around the same frozen weights.
- A reply cites CORRAL (arXiv:2604.18805), which reportedly ran 25k+ trajectories across 8 scientific domains and found that 68% ignored evidence, 71% never updated beliefs, and only 26% showed refutation-driven revision.
- The combined argument is that many “agentic” behaviors may be an illusion created by scaffolding plus narrative, not genuine adaptation or reasoning.
More from AGI Musings
- WSJ: for Anthropic investors, a 10% extinction chance may still be a 90% portfolio win — peterwildeford · 2026-10-27
- Simile, the AI human-simulation startup, raises $300M+ at $2B valuation with 85%+ behavior prediction — joon_s_pk · 2026-10-27
- AI images are moldy bread, AI text is spoiled milk: a researcher's ick analogy — _vaishnavh · 2026-10-27
- AI images are moldy bread, AI text is spoiled milk, researcher argues — _vaishnavh · 2026-10-27
- Peter Diamandis: revisit the projects you abandoned because you couldn't afford the team — PeterDiamandis · 2026-10-27
- Nat Lambert: don't trust any AI model until you've rigorously tested it — natolambert · 2026-10-27