Diagnosing Failure Modes of Shared-State Collaboration in Resource-Constrained Visual Agents

Computer Science > Artificial Intelligence [Submitted on 29 May 2026] Diagnosing Failure Modes of Shared-State Collaboration in Resource-Constrained Visual Agents Yunpeng Zhou Modular visual reasoning systems increasingly rely on shared working memory for multi-step collaboration, yet the failure dynamics of intermediate state evolution in low-capacity regimes remain underexplored. We study failure modes of collaborative reasoning with weak learners (4B--8B models) through the lens of noise accumulation. We introduce CoSee, an auditing framework that formalizes the read-write-verify loop to trace information flow in document visual question answering. Across multi-page, chart, and web-based benchmarks, we find a counter-intuitive degradation: naive shared workspaces often amplify hallucinations rather than resolve them. We identify two dominant failure modes: Noise Reinforcement, where ungrounded notes are reused as evidence, and Policy Collapse, where added context shifts the model toward under-specified, short-form answers. Using cost-accuracy Pareto frontiers, we show that increased compute can correlate negatively with performance without explicit verification. Our findings suggest that for resource-constrained agents, the bottleneck lies not in reasoning depth but in communication fidelity, providing trace-level diagnostics and a mechanistic baseline for reliable modular design. Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2605.31354 [cs.AI]   (or arXiv:2605.31354v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2605.31354 Focus to learn more Submission history From: Yunpeng Zhou [view email] [v1] Fri, 29 May 2026 14:29:56 UTC (6,726 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)