SOURCE-LINKED INTELLIGENCE

Zero-Shot Self-Orchestration with Ledger-Based Control for Improved LLM Coding Performance

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

Multi-agent large language model systems are widely reported to beat single-model baselines, but the evidence is mixed, and comparisons are usually confounded: pipelines change token budgets, tool calls, and prompts simultaneously, so an aggregate gain rarely reveals what actually helped. We investigate the effect of introducing the manager-worker scaffold over a shared filesystem workspace, with no training and no per-benchmark tuning, measured against the same model answering in a single pass. Across nine models -- five open-weight, spanning 9B to ~2.8T parameters, and four frontier closed m

Read original source ↗ Open in workspace

recordType

paper

region

Global