S-Bus</p>\n","updatedAt":"2026-05-21T00:31:16.460Z","author":{"_id":"648622c80e6657a2a9400677","avatarUrl":"/avatars/0b56f575f0556366b34f0157a6a613bf.svg","fullname":"Sajjad Khan","name":"sajjadanwar0","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.40492111444473267},"editors":["sajjadanwar0"],"editorAvatarUrls":["/avatars/0b56f575f0556366b34f0157a6a613bf.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.17076","authors":[{"_id":"6a0c3a0b65eb30f20d9627ed","user":{"_id":"648622c80e6657a2a9400677","avatarUrl":"/avatars/0b56f575f0556366b34f0157a6a613bf.svg","isPro":false,"fullname":"Sajjad Khan","user":"sajjadanwar0","type":"user","name":"sajjadanwar0"},"name":"Sajjad Khan","status":"claimed_verified","statusLastChangedAt":"2026-05-20T17:13:06.172Z","hidden":false}],"publishedAt":"2026-05-16T00:00:00.000Z","submittedOnDailyAt":"2026-05-20T00:00:00.000Z","title":"S-Bus: Automatic Read-Set Reconstruction for Multi-Agent LLM State Coordination","submittedOnDailyBy":{"_id":"648622c80e6657a2a9400677","avatarUrl":"/avatars/0b56f575f0556366b34f0157a6a613bf.svg","isPro":false,"fullname":"Sajjad Khan","user":"sajjadanwar0","type":"user","name":"sajjadanwar0"},"summary":"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.\n 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.\n Three contributions: (C1) The DeliveryLog mechanism for automatic HTTP-traffic-based read-set reconstruction, with three-tier mechanised evidence: ReadSetSoundness and ORICommitSafety machine-checked in TLAPS (modulo one retained typing axiom); exhaustive TLC at N=3 (20,763,484 distinct states, zero violations); Dafny discharges 9 inductive soundness lemmas. (C2) Empirical structural-conflict prevention parity against PostgreSQL 17 SERIALIZABLE and Redis 7 WATCH/MULTI on shared-shard contention sweeps with 427,308 active HTTP-409 conflicts: zero Type-I corruptions across all three backends. (C3) ORI's operating envelope is topology-conditional: semantically neutral in dedicated-shard workloads; harmful in single-shard collaborative writing because preservation propagates concurrent contradictions.\n Source code: https://github.com/sajjadanwar0/sbus","upvotes":0,"discussionId":"6a0c3a0b65eb30f20d9627ee","githubRepo":"https://github.com/sajjadanwar0/sbus","githubRepoAddedBy":"user","ai_summary":"Structural race conditions in concurrent LLM agents are prevented through S-Bus middleware that uses a DeliveryLog mechanism to reconstruct read sets and enforce Observable-Read Isolation consistency.","ai_keywords":["Structural Race Conditions","write-write conflicts","stale-read conflicts","concurrent LLM agents","HTTP middleware","DeliveryLog","Observable-Read Isolation","ORI","read-set reconstruction","TLAPS","TLC","Dafny","machine-checked proofs","causal consistency","shared shards","dedicated shards"],"githubStars":0},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[],"acceptLanguages":["en"],"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.17076.md"}">
S-Bus: Automatic Read-Set Reconstruction for Multi-Agent LLM State Coordination
Abstract
Structural race conditions in concurrent LLM agents are prevented through S-Bus middleware that uses a DeliveryLog mechanism to reconstruct read sets and enforce Observable-Read Isolation consistency.
AI-generated summary
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 reconstruction, with three-tier mechanised evidence: ReadSetSoundness and ORICommitSafety machine-checked in TLAPS (modulo one retained typing axiom); exhaustive TLC at N=3 (20,763,484 distinct states, zero violations); Dafny discharges 9 inductive soundness lemmas. (C2) Empirical structural-conflict prevention parity against PostgreSQL 17 SERIALIZABLE and Redis 7 WATCH/MULTI on shared-shard contention sweeps with 427,308 active HTTP-409 conflicts: zero Type-I corruptions across all three backends. (C3) ORI's operating envelope is topology-conditional: semantically neutral in dedicated-shard workloads; harmful in single-shard collaborative writing because preservation propagates concurrent contradictions.
Source code: https://github.com/sajjadanwar0/sbus
Community
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2605.17076 in a model README.md to link it from this page.
Cite arxiv.org/abs/2605.17076 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2605.17076 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.