AI RESEARCH
Textual Equilibrium Propagation for Deep Compound AI Systems
arXiv CS.AI
•
ArXi:2601.21064v3 Announce Type: replace-cross Large language models (LLMs) are increasingly deployed as part of compound AI systems that coordinate multiple modules (e.g., retrievers, tools, verifiers) over long-horizon workflows. Recent approaches that propagate textual feedback globally (e.g., TextGrad) make it feasible to optimize such pipelines, but we find that performance degrades as system depth grows.