llm-pipelines

Tag

Cards List
#llm-pipelines

QUIVER: A Formal Framework for Quantifying Perturbation Propagation and Bifurcation in Compound AI Systems

arXiv cs.AI · 2026-05-26 Cached

QUIVER introduces a formal framework for quantifying how perturbations propagate through compound AI systems structured as computation graphs, defining sensitivity matrices, trajectory divergence, bifurcation thresholds, and distribution faithfulness, with validation on production and public pipelines.

0 favorites 0 likes
#llm-pipelines

Learning to Hand Off: Provably Convergent Workflow Learning under Interface Constraints

arXiv cs.AI · 2026-05-20 Cached

This paper formalizes workflow learning in multi-agent LLM pipelines as an interface-constrained semi-Markov decision process (IC-SMDP) and proposes IC-ICQQ, an asynchronous decentralized Q-learning algorithm with a finite-sample bound that decomposes error sources, providing the first finite-sample guarantee for neural Q-learning under decentralized partial observability.

0 favorites 0 likes
#llm-pipelines

Operationalizing Document AI: A Microservice Architecture for OCR and LLM Pipelines in Production

arXiv cs.AI · 2026-05-20 Cached

This paper presents a microservice architecture for production document AI pipelines that combine classification, OCR, and LLM extraction, sharing design decisions and batch profiling insights that reveal OCR, not LLM parsing, dominates latency.

0 favorites 0 likes
← Back to home

Submit Feedback