S-Bus: Automatic Read-Set Reconstruction for Multi-Agent LLM State Coordination
Sajjad Khan

TL;DR
S-Bus introduces an HTTP middleware with a DeliveryLog mechanism that reconstructs read sets for multi-agent LLM collaboration, preventing structural race conditions through observable-read isolation.
Contribution
It presents a novel DeliveryLog system for automatic read-set reconstruction and formal proofs of its safety properties, enhancing multi-agent LLM state coordination.
Findings
Zero structural conflicts in empirical tests against PostgreSQL and Redis.
Formal proofs confirm soundness and safety of the DeliveryLog mechanism.
Operating conditions for ORI are topology-dependent, neutral in dedicated-shard workloads.
Abstract
Concurrent LLM agents sharing mutable natural-language state produce Structural Race Conditions (SRCs): write-write and cross-shard stale-read conflicts that silently corrupt agent output. Existing multi-agent frameworks (LangGraph, CrewAI, AutoGen) provide no write-ownership semantics over shared state. We present S-Bus, an HTTP middleware whose central mechanism is a server-side DeliveryLog: a per-agent log of HTTP GET operations that automatically reconstructs each agent's read set at commit time without agent SDK changes under HTTP/1.1. The consistency property the DeliveryLog provides -- Observable-Read Isolation (ORI), a partial causal consistency over the HTTP-observable projection of the read set -- prevents structural race conditions when agents collaborate via shared shards. Three contributions: (C1) The DeliveryLog mechanism for automatic HTTP-traffic-based read-set…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
