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
- AI is still not at a maturity plateau, the author argues — generativist · 2026-07-22
- Essay argues LLMs are externalized metacognition, not standalone intelligence — lnsip9reg · 2026-07-22
- A multipolar AI race will not automatically make AI go well, repost argues — JeffLadish · 2026-07-22
- Decentralized AI as the Antidote to Digital Feudalism in the Economic Singularity — srimisra · 2026-07-22
- Humanoid robot sorting packages in a warehouse sparks debate over job loss — MonaJalal_ · 2026-07-22
- You can outsource thinking, but not understanding, in the age of agents — Yuchenj_UW · 2026-07-22