{"total":17,"items":[{"citing_arxiv_id":"2605.19240","ref_index":8,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"CASPIAN: Online Detection and Attribution of Cascade Attacks in LLM Multi-Agent Systems via Cross-Channel Causal Monitoring","primary_cat":"cs.MA","submitted_at":"2026-05-19T01:16:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"CASPIAN introduces unified cross-channel causal monitoring via late-interaction conditional transfer entropy to detect cascade onset and attribute origin, bridge, and amplifier agents in LLM multi-agent systems.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18535","ref_index":22,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Beyond Scaling: Agents Are Heading to the Edge","primary_cat":"cs.LG","submitted_at":"2026-05-18T15:18:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Personal agents require edge deployment to preserve high-fidelity local context and zero-latency loops, as claimed through three structural shifts away from cloud-centric designs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17361","ref_index":16,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"\\textsc{MasFACT}: Continual Multi-Agent Topology Learning via Geometry-Aware Posterior Transfer","primary_cat":"cs.LG","submitted_at":"2026-05-17T09:58:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"MasFACT transfers historical topology priors across tasks via Fused Gromov-Wasserstein optimal transport and PAC-Bayes conservative adaptation to reduce topology forgetting in continual multi-agent settings.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17169","ref_index":25,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Responsible Agentic AI Requires Explicit Provenance","primary_cat":"cs.AI","submitted_at":"2026-05-16T21:56:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Explicit provenance across the full agentic AI lifecycle is the necessary condition for making responsibility computable and actionable.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14563","ref_index":29,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation","primary_cat":"cs.SE","submitted_at":"2026-05-14T08:35:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"MemDocAgent generates consistent hierarchical repository-level code documentation by combining dependency-aware traversal with memory-guided agent interactions that accumulate work traces.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Advances in neural information processing systems, 36:8634-8652, 2023. [28] Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, et al. Metagpt: Meta programming for a multi-agent collaborative framework. InThe twelfth international conference on learning representations, 2023. [29] Chen Qian, Wei Liu, Hongzhang Liu, Nuo Chen, Yufan Dang, Jiahao Li, Cheng Yang, Weize Chen, Yusheng Su, Xin Cong, et al. Chatdev: Communicative agents for software development. InProceedings of the 62nd annual meeting of the association for computational linguistics (volume 1: Long papers), pages 15174-15186, 2024. [30] Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun"},{"citing_arxiv_id":"2605.14483","ref_index":3,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"LEMON: Learning Executable Multi-Agent Orchestration via Counterfactual Reinforcement Learning","primary_cat":"cs.AI","submitted_at":"2026-05-14T07:24:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LEMON trains an LLM orchestrator with counterfactual-augmented GRPO to produce deployable multi-agent specifications that reach state-of-the-art results on six reasoning and coding benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11514","ref_index":20,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems","primary_cat":"cs.CR","submitted_at":"2026-05-12T04:35:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"FlowSteer is a prompt-only attack that biases multi-agent LLM workflow planning to propagate malicious signals, raising success rates by up to 55%, with FlowGuard as an input-side defense reducing it by up to 34%.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"enables their flexibility, making workflow formation a necessary target for future MAS safeguards. 2 2 Related Work We focus on the most relevant literature here and defer a broader discussion toAppendix C. Planner-executor MAS and social influence.LLM-based multi-agent systems have evolved from static collaboration frameworks with predefined roles and communication protocols [20, 32, 55, 45] to planner-executor architectures, where task decomposition, role assignment, and dependencies are generated dynamically from user input [ 13, 14, 47, 62]. This flexibility makes workflows safety-critical. In parallel, studies of social influence show that agents can shape one another's reasoning to support coordination [ 4, 24], while also amplifying conformity, peer pressure, and"},{"citing_arxiv_id":"2605.10057","ref_index":8,"ref_count":3,"confidence":0.55,"is_internal_anchor":false,"paper_title":"STAR: Failure-Aware Markovian Routing for Multi-Agent Spatiotemporal Reasoning","primary_cat":"cs.AI","submitted_at":"2026-05-11T06:34:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"STAR presents a failure-aware routing framework using a state-conditioned transition policy and an agent routing matrix combining expert routes with learned recoveries from execution traces to improve multi-agent spatiotemporal reasoning.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Llm-based intent processing and network optimization using attention-based hierarchical reinforcement learning. In2025 IEEE Wireless Communications and Networking Conference (WCNC), pages 1-6. IEEE, 2025. [7] Bochen Han and Songmao Zhang. Exploring advanced llm multi-agent systems based on blackboard architecture.arXiv preprint arXiv:2507.01701, 2025. [8] Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, et al. Metagpt: Meta programming for a multi-agent collaborative framework. InThe twelfth international conference on learning representations, 2023. [9] Wenbin Li, Di Yao, Ruibo Zhao, Wenjie Chen, Zijie Xu, Chengxue Luo, Chang Gong, Quanliang"},{"citing_arxiv_id":"2605.09423","ref_index":33,"ref_count":4,"confidence":0.55,"is_internal_anchor":false,"paper_title":"SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning","primary_cat":"cs.AI","submitted_at":"2026-05-10T08:51:50+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":8.0,"formal_verification":"none","one_line_summary":"SimWorld Studio deploys an evolving coding agent to create adaptive 3D environments that co-evolve with embodied learners, delivering 18-point success-rate gains over fixed environments in navigation benchmarks.","context_count":2,"top_context_role":"background","top_context_polarity":"background","context_text":"International Conference on Computer Vision, pages 7909-7920, 2023. [32] Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, et al. Metagpt: Meta programming for a multi-agent collaborative framework. InThe twelfth international conference on learning representations, 2023. [33] Yicong Hong, Yiqun Mei, Chongjian Ge, Yiran Xu, Yang Zhou, Sai Bi, Yannick Hold- Geoffroy, Mike Roberts, Matthew Fisher, Eli Shechtman, et al. Relic: Interactive video world model with long-horizon memory.arXiv preprint arXiv:2512.04040, 2025. URL https://arxiv.org/abs/2512.04040. [34] Shengran Hu, Cong Lu, and Jeff Clune. Automated design of agentic systems."},{"citing_arxiv_id":"2605.09278","ref_index":23,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium","primary_cat":"cs.AI","submitted_at":"2026-05-10T03:04:12+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"EquiMem calibrates shared memory in multi-agent debate by computing a game-theoretic equilibrium from agent queries and paths, outperforming heuristics and LLM validators across benchmarks while remaining robust to adversarial agents.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"include role-conditioned debate [9, 77], dynamic participant selection [10, 37], and tournament-style aggregation [28, 95]. Theoretical work studies the consensus properties of debate [ 58, 91] and its vulnerability to adversarial participants [2, 34]. To enable cross-task learning, recent systems pair debate with a shared memory that persists across rounds [23, 49, 89]. Memory design for LLM agents.Agent memory has evolved from fixed context windows to struc- tured persistent stores [45, 46, 94]. Common designs include embedding-based retrieval [56, 69, 94], graph-structured memory [12, 51], and hierarchical or multi-tier storage [ 45, 75, 84]. These sys- tems are typically optimised for retrieval quality, with veracity and provenance treated as sec-"},{"citing_arxiv_id":"2605.08715","ref_index":18,"ref_count":4,"confidence":0.55,"is_internal_anchor":false,"paper_title":"AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems","primary_cat":"cs.CL","submitted_at":"2026-05-09T05:55:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"AgentForesight introduces an online auditor model that predicts decisive errors in multi-agent trajectories at the earliest step using a coarse-to-fine reinforcement learning recipe on a new curated dataset AFTraj-2K.","context_count":2,"top_context_role":"background","top_context_polarity":"background","context_text":"Measuring mathematical problem solving with the math dataset. arXiv preprint arXiv:2103.03874, 2021. [17] Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, et al. Metagpt: Meta programming for a multi-agent collaborative framework. InThe twelfth international conference on learning representations, 2023. [18] Jie Huang, Xinyun Chen, Swaroop Mishra, Huaixiu Steven Zheng, Adams Wei Yu, Xinying Song, and Denny Zhou. Large language models cannot self-correct reasoning yet.arXiv preprint arXiv:2310.01798, 2023. [19] Zhenlan Ji, Daoyuan Wu, Pingchuan Ma, Zongjie Li, and Shuai Wang. Testing and under- standing erroneous planning in llm agents through synthesized user inputs."},{"citing_arxiv_id":"2605.08686","ref_index":9,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs","primary_cat":"cs.AI","submitted_at":"2026-05-09T04:51:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A critique-and-routing controller cast as a finite-horizon MDP with policy-gradient optimization outperforms one-shot routing baselines on reasoning benchmarks while using the strongest agent for under 25% of calls.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"llms via reinforcement learning.arXiv preprint arXiv:2501.12948, 2025. [8] Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. Measuring mathematical problem solving with the math dataset. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2021. [9] Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, et al. Metagpt: Meta programming for a multi-agent collaborative framework. InThe twelfth international conference on learning representations, 2023. [10] Binyuan Hui, Jian Yang, Zeyu Cui, Jiaxi Yang, Dayiheng Liu, Lei Zhang, Tianyu Liu, Jia-"},{"citing_arxiv_id":"2605.07069","ref_index":44,"ref_count":3,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Social Theory Should Be a Structural Prior for Agentic AI: A Formal Framework for Multi-Agent Social Systems","primary_cat":"cs.MA","submitted_at":"2026-05-08T00:30:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Agentic AI needs social theory as structural priors in the MASS framework to model emergent dynamics from multi-agent interactions.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"[43] Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. Measuring massive multitask language understanding.arXiv preprint arXiv:2009.03300, 2020. [44] Brian Hirshman, Michael K Martin, and Kathleen M Carley. Modeling information access in construct. Technical report, Technical report, Carnegie Mellon University School of Computer Science, 2008. [45] Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, et al. Metagpt: Meta programming for a multi-agent collaborative framework. InThe twelfth international conference on learning representations, 2023. [46] Ilya Horiguchi, Takahide Yoshida, and Takashi Ikegami."},{"citing_arxiv_id":"2604.27488","ref_index":4,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO","primary_cat":"cs.CL","submitted_at":"2026-04-30T06:39:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"Skills-Coach optimizes LLM agent skills via task generation, prompt/code tuning, comparative execution, and traceable evaluation, reporting gains on a 48-skill benchmark called Skill-X.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.12144","ref_index":48,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"VERITAS: A Multi-Agent Co-Scientist for Verifiable Image-Derived Hypothesis Testing","primary_cat":"cs.MA","submitted_at":"2026-04-13T23:48:35+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Multi-agent systems structure complex scientific workflows by decomposing tasks across specialized roles. In the scientific domain, Virtual Lab [41], Virtual Biotech [42], Agent Laboratory [43], VirSci [44], ResearchAgent [45], and SciAgents [46] organize teams of agents that collaboratively plan, code, and execute experiments. General-purpose multi-agent frameworks such as AutoGen [47] and MetaGPT [ 48] provide infrastructure for such agent orchestration, with MetaGPT's insight that structured intermediate artifacts reduce cascading hallucinations being directly relevant to our design. Nevertheless, a recent independent evaluation of several such AI research frameworks, including AgentLaboratory [43], AutoGen [47], MOOSE-Chem2 [49], SciAgents [46], SciMON [50], and Virtual Lab [41],"},{"citing_arxiv_id":"2604.08206","ref_index":11,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"\"Theater of Mind\" for LLMs: A Cognitive Architecture Based on Global Workspace Theory","primary_cat":"cs.MA","submitted_at":"2026-04-09T13:06:43+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Global Workspace Agents (GWA) is proposed as an active, event-driven cognitive architecture for LLMs featuring an entropy-based intrinsic drive and dual-layer memory to enable sustained self-directed agency.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.02674","ref_index":25,"ref_count":1,"confidence":0.55,"is_internal_anchor":false,"paper_title":"Do Agent Societies Develop Intellectual Elites? The Hidden Power Laws of Collective Cognition in LLM Multi-Agent Systems","primary_cat":"cs.MA","submitted_at":"2026-04-03T03:08:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LLM agent societies develop power-law coordination cascades and intellectual elites through an integration bottleneck that grows with system size.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Large language model based multi-agents: A survey of progress and challenges.arXiv preprint arXiv:2402.01680, 2024. [24] Aaron Halfaker, R Stuart Geiger, Jonathan T Morgan, and John Riedl. The rise and decline of an open collaboration system: How wikipedia's reaction to popularity is causing its decline. American behavioral scientist, 57(5):664-688, 2013. [25] Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, et al. Metagpt: Meta programming for a multi-agent collaborative framework. InThe twelfth international conference on learning representations, 2023. [26] Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik"}],"limit":50,"offset":0}