StateFuse: Deterministic Conflict-Preserving Memory for Multi-Agent Systems
Quick Answer
StateFuse introduces a conflict-aware replicated memory contract for multi-agent systems, preserving contradictions while maintaining accuracy.
Quick Take
Evaluated against 282 questions in MemoryAgentBench, it ties on accuracy but excels in surfacing conflicts and enabling safer corrections.
Key Points
- StateFuse uses OpSet/CRDT merge without introducing new join algebra.
- It features immutable history and explicit conflict objects for better inspection.
- In tests, it preserves contradictions while collapsed methods do not.
- Semantic correction handles improve safety when exact identifiers are missing.
- Best suited as a public memory contract for contradiction surfacing.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Agent systems accumulate conflicting observations across branches, retries, and replicas, yet many practical memory layers still collapse disagreement behind overwrite rules that are difficult to inspect or correct. We present StateFuse, a conflict-aware replicated memory contract built on standard OpSet/CRDT merge. StateFuse does not introduce a new join algebra; it defines an agent-facing semantics layer with immutable history, explicit conflict objects, exact and semantic correction handles (claim_id / claim_ref), deterministic predicate contracts, and projection-time resolution that cannot rewrite replicated state.
We evaluate StateFuse against flat multi-value, raw-log, provenance-style, and collapsed baselines under matched resolver and verification policies. On a 282-question official conflict-bearing MemoryAgentBench slice, the compared methods tie on answer accuracy, but conflict-preserving surfaces keep contradictions visible while collapsed surfaces do not. In a controlled agent loop with uniform verification, preserving ambiguity enables safer abstention and correction than early collapse. A correction-handle ablation further shows that semantic handles matter when exact prior identifiers are unavailable.
The resulting claim is narrow: StateFuse is best supported as a safer public memory contract for contradiction surfacing, abstention, and auditable correction, not as a universal accuracy gain.
| Comments: | Code and supplementary materials available at: this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2607.05844 [cs.AI] |
| (or arXiv:2607.05844v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.05844 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sergey Volkov [view email]
[v1]
Tue, 7 Jul 2026 05:06:33 UTC (21 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.