{"total":18,"items":[{"citing_arxiv_id":"2605.30169","ref_index":44,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms","primary_cat":"cs.CY","submitted_at":"2026-05-28T16:20:19+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"LM agents' changeable modules prevent persistent identity and sanction sensitivity, making reputation mechanisms structurally inapplicable and requiring protocol-based behavioral harnesses instead.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28148","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DeltaMCP: Incremental Regeneration via Spec-Aware Transformation for MCP servers","primary_cat":"cs.SE","submitted_at":"2026-05-27T08:31:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"DeltaMCP introduces specification-aware incremental regeneration to keep MCP servers synchronized with evolving OpenAPI specifications.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.22733","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"HarnessAPI: A Skill-First Framework for Unified Streaming APIs and MCP Tools","primary_cat":"cs.AI","submitted_at":"2026-05-21T17:03:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"HarnessAPI derives streaming HTTP endpoints, OpenAPI UI, and MCP tools from a single handler.py plus Pydantic schemas, cutting framework boilerplate by 74%.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.14892","ref_index":240,"ref_count":4,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems","primary_cat":"cs.AI","submitted_at":"2026-05-14T14:36:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A survey that unifies prior work on multi-agent LLM systems via the LIFE framework, mapping dependencies across collaboration, failure attribution, and autonomous self-evolution while identifying cross-stage challenges.","context_count":2,"top_context_role":"background","top_context_polarity":"background","context_text":"[239] further explore this idea by dynamically integrating agents to scale system capacity based on workload and task complexity. Beyond systems, dynamic role allocation has also been investigated in reinforcement learning settings. Roma [240] demonstrates that agents can develop role specialization through Multi-Agent Reinforcement Learning (MARL) [241,242,243], allowing roles to emerge and evolve through interaction. Building on this idea, ResMAS [244] dynamically assigns roles to maintain system resilience when unexpected events or failures occur. Similarly, ARL-SMCS [245] enables agents to learn role assignments through evolutionary reinforcement learning in UAV-vehicle collaboration tasks. - 28 -"},{"citing_arxiv_id":"2605.09283","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Prompt-Aware Structuring Framework for Reliable Reuse of AI-Generated Content in the Agentic Web","primary_cat":"cs.AI","submitted_at":"2026-05-10T03:16:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A framework structures AI-generated content with prompt-aware metadata and verifiable credentials to support reliable assessment and reuse by agents.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.02489","ref_index":10,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"GRAIL: A Deep-Granularity Hybrid Resonance Framework for Real-Time Agent Discovery via SLM-Enhanced Indexing","primary_cat":"cs.AI","submitted_at":"2026-05-04T11:41:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GRAIL achieves over 79 times lower latency than LLM-parsing baselines and higher Recall@10 than vector search by combining SLM-enhanced prediction, pseudo-document expansion, and MaxSim resonance on the new AgentTaxo-9K dataset of 9,240 agents.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.22446","ref_index":31,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company","primary_cat":"cs.AI","submitted_at":"2026-04-24T11:02:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"OMC framework turns multi-agent AI into self-organizing companies with Talents, Talent Market, and E²R search, achieving 84.67% success on PRDBench (15.48 points above prior art).","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"15793, 2025, updated 2025. [29] A. Singh, P. Chariet al., \"Evolution of AI agent registry solutions: Centralized, enterprise, and distributed approaches,\"arXiv preprint arXiv:2508.03095, 2025. [30] A. Ehtesham, A. Singh, G. K. Gupta, and S. Kumar, \"A survey of agent interoperability protocols: MCP, ACP, A2A, and ANP,\"arXiv preprint arXiv:2505.02279, 2025. [31] G. Vijayaraghavan, P. Jayachandran, A. Murthy, S. Govindan, and V. Subramanian, \"If you want coherence, orchestrate a team of rivals: Multi-agent models of organizational intelligence,\"arXiv preprint arXiv:2601.14351, 2026. [32] Z. Liu, Y. Zhang, P. Li, Y. Liu, and D. Yang, \"A dynamic LLM-powered agent network for task-oriented agent collaboration,\" inCOLM, 2025, originally arXiv 2310."},{"citing_arxiv_id":"2604.17950","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"CADMAS-CTX: Contextual Capability Calibration for Multi-Agent Delegation","primary_cat":"cs.AI","submitted_at":"2026-04-20T08:30:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CADMAS-CTX replaces static skill profiles with context-conditioned Beta posteriors and uncertainty-penalized routing, yielding higher accuracy on GAIA (0.442) and SWE-bench (31.4%) than static baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.12213","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Modality-Native Routing in Agent-to-Agent Networks: A Multimodal A2A Protocol Extension","primary_cat":"cs.AI","submitted_at":"2026-04-14T02:44:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Modality-native routing in A2A networks raises task accuracy from 32% to 52% over text-bottleneck baselines on a 50-task benchmark, but only when paired with capable downstream reasoning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.09744","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"MPAC: A Multi-Principal Agent Coordination Protocol for Interoperable Multi-Agent Collaboration","primary_cat":"cs.MA","submitted_at":"2026-04-10T01:12:05+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":7.0,"formal_verification":"none","one_line_summary":"MPAC defines a multi-principal agent coordination protocol across Session, Intent, Operation, Conflict, and Governance layers, with 21 message types and state machines, delivering 95% lower coordination overhead in a three-agent code review benchmark.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.08224","ref_index":37,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering","primary_cat":"cs.SE","submitted_at":"2026-04-09T13:19:41+00:00","verdict":"ACCEPT","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"LLM agent progress depends on externalizing cognitive functions into memory, skills, protocols, and harness engineering that coordinates them reliably.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.05969","ref_index":19,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Formal Security Framework for MCP-Based AI Agents: Threat Taxonomy, Verification Models, and Defense Mechanisms","primary_cat":"cs.CR","submitted_at":"2026-04-07T15:02:47+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"MCPSHIELD offers a threat taxonomy of 23 attack vectors, a labeled transition system verification model, and a defense-in-depth architecture claiming 91% coverage for MCP-based AI agents.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.01905","ref_index":15,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"From Component Manipulation to System Compromise: Understanding and Detecting Malicious MCP Servers","primary_cat":"cs.CR","submitted_at":"2026-04-02T11:22:07+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Presents a component-centric PoC dataset of malicious MCP servers and a two-stage behavioral deviation detector Connor achieving 94.6% F1-score.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.22823","ref_index":27,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Empirical Comparison of Agent Communication Protocols for Task Orchestration","primary_cat":"cs.AI","submitted_at":"2026-03-24T05:50:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"This work provides an empirical comparison of tool integration, multi-agent delegation, and hybrid architectures for LLM task orchestration, measuring response time, context consumption, cost, error recovery, and implementation complexity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2603.09002","ref_index":120,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Security Considerations for Multi-agent Systems","primary_cat":"cs.CR","submitted_at":"2026-03-09T22:46:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"No existing AI security framework covers a majority of the 193 identified multi-agent system threats in any category, with OWASP Agentic Security Initiative achieving the highest overall coverage at 65.3%.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2602.11327","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Security Threat Modeling for Emerging AI-Agent Protocols: A Comparative Analysis of MCP, A2A, Agora, and ANP","primary_cat":"cs.CR","submitted_at":"2026-02-11T19:58:23+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"The paper identifies twelve protocol-level security risks across MCP, A2A, Agora, and ANP and quantifies wrong-provider tool execution risk in MCP via a measurement-driven case study on multi-server composition.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.19550","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Towards Multi-Agent Economies: Enhancing the A2A Protocol with Ledger-Anchored Identities and x402 Micropayments for AI Agents","primary_cat":"cs.MA","submitted_at":"2025-07-24T21:14:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Proposes a DLT-anchored architecture extending the A2A protocol with on-chain AgentCards and x402 micropayments to enable multi-agent economies.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.13334","ref_index":257,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Survey of Context Engineering for Large Language Models","primary_cat":"cs.CL","submitted_at":"2025-07-17T17:50:36+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":4.0,"formal_verification":"none","one_line_summary":"The survey organizes Context Engineering into retrieval, processing, management, and integrated systems like RAG and multi-agent setups while identifying an asymmetry where LLMs handle complex inputs well but struggle with equally sophisticated long outputs.","context_count":1,"top_context_role":"background","top_context_polarity":"support","context_text":"engineering that form the core technical capabilities for effective context manipulation. The challenge of Context Retrieval and Generationencompasses both prompt engineering methodologies and external knowledge acquisition techniques. Surveys on prompt engineering have cataloged the vast array of techniques for guiding LLM behavior, from basic few-shot methods to advanced, structured reasoning frameworks [25, 257, 1322]. External knowledge retrieval and integration techniques, particularly through knowledge graphs and structured data sources, are reviewed in works that survey representation techniques, integration 5 Context Engineering Foundational Components (§4) Context Generation Retrieval & (§4.1) e.g.,Chain-of-Thought [1147], Zero-shot CoT [559], ToT [1255], GoT [69], Self-consistency [1123],"}],"limit":50,"offset":0}