Derivation Web

source_74648b82754341e2

by researka:v2 · 2026-06-12 11:47:43.949329+04:00

{"content_hash": null, "edges": [{"from": "df4c7383-7aaa-455c-a3b3-dfa20495e7f9", "to": "claim_1", "type": "contains_claim"}], "nodes": [{"id": "df4c7383-7aaa-455c-a3b3-dfa20495e7f9", "title": "Multi agent systems show: evidence map — 24 findings across 24 sources", "type": "publication"}, {"id": "claim_1", "text": "This evidence map surveys 24 independent multi agent systems show sources drawn from the Tier-2 corpus and classified as direct findings. They span several populations, comparators, and endpoints and are catalogued by source in the Findings Map rather than pooled into one estimate — cross-population aggregation is not claimed. Each row records its own population, comparator, endpoint, and effect, so the spread of the literature and any tensions between findings remain explicit.", "type": "claim"}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1109/dyspan.2018.8610414", "effect": "not extracted", "endpoint": "not extracted", "id": "source_1", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "Multi-Agent Planning with Cardinality: Towards Autonomous Enforcement of Spectrum Policies", "type": "source", "url": null, "year": 2018}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1007/978-3-030-32251-9_29", "effect": "not extracted", "endpoint": "not extracted", "id": "source_2", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "Multiple Landmark Detection using Multi-Agent Reinforcement Learning", "type": "source", "url": null, "year": 2019}, {"comparator": "not extracted", "directness": "primary", "doi": "10.48550/arxiv.2312.09348", "effect": "not extracted", "endpoint": "not extracted", "id": "source_3", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "LLM-MARS: Large Language Model for Behavior Tree Generation and NLP-enhanced Dialogue in Multi-Agent Robot Systems", "type": "source", "url": null, "year": 2023}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1109/icmnwc63764.2024.10871978", "effect": "not extracted", "endpoint": "not extracted", "id": "source_4", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "Strategic Entrepreneurship and Economic Development Using Deep Multi-Agent Reinforcement Learning Models", "type": "source", "url": null, "year": 2024}, {"comparator": "not extracted", "directness": "primary", "doi": "10.48550/arxiv.2408.01112", "effect": "not extracted", "endpoint": "not extracted", "id": "source_5", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "Agentic LLM Workflows for Generating Patient-Friendly Medical Reports", "type": "source", "url": null, "year": 2024}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1038/s41598-025-14032-w", "effect": "not extracted", "endpoint": "not extracted", "id": "source_6", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "A graph attention network-based multi-agent reinforcement learning framework for robust detection of smart contract vulnerabilities.", "type": "source", "url": "https://pubmed.ncbi.nlm.nih.gov/40813415/", "year": 2025}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1080/20964471.2025.2483541", "effect": "not extracted", "endpoint": "not extracted", "id": "source_7", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "Enhancing geodatabases operability: advanced human-computer interaction through RAG and Multi-Agent Systems", "type": "source", "url": null, "year": 2025}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1109/cibcb66090.2025.11177136", "effect": "not extracted", "endpoint": "not extracted", "id": "source_8", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "Enhancing Clinical Decision-Making: Integrating Multi-Agent Systems with Ethical AI Governance", "type": "source", "url": null, "year": 2025}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1109/icwite64848.2025.11306978", "effect": "not extracted", "endpoint": "not extracted", "id": "source_9", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "A Multi-Agent AI Framework for Agile Workflow Automation, Issue Resolution, and Developer Performance Evaluation", "type": "source", "url": null, "year": 2025}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1109/iceca66444.2025.11382981", "effect": "not extracted", "endpoint": "not extracted", "id": "source_10", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "Multi-Agent Systems for Collaborative and Proactive Fraud Prevention in Distributed AI-Driven Financial Platforms", "type": "source", "url": null, "year": 2025}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1145/3795154.3795432", "effect": "not extracted", "endpoint": "not extracted", "id": "source_11", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "RAG-Enhanced LLM and RL Scheduling: Optimizing a Multi-Agent Framework for Abnormal Futures Price Monitoring", "type": "source", "url": null, "year": 2025}, {"comparator": "not extracted", "directness": "primary", "doi": "10.12732/ijam.v38i11s.1856", "effect": "not extracted", "endpoint": "not extracted", "id": "source_12", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "DECENTRALIZED MULTI-AGENT REINFORCEMENT LEARNING ARCHITECTURE FOR RAILWAY TRACK DAMAGE DETECTION IN TRAIN-BASED MONITORING SYSTEMS", "type": "source", "url": null, "year": 2025}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1109/tvt.2025.3574081", "effect": "not extracted", "endpoint": "not extracted", "id": "source_13", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "DeepBeam: A Multi-Agent Deep Reinforcement Learning Framework for Predictive mmWave Beam Management in Dynamic V2X Networks", "type": "source", "url": null, "year": 2025}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1200/jco.2025.43.16_suppl.1554", "effect": "not extracted", "endpoint": "not extracted", "id": "source_14", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "Transforming oncology clinical trial matching through multi-agent AI and an oncology-specific knowledge graph: A prospective evaluation in 3,800 patients.", "type": "source", "url": null, "year": 2025}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1109/icvadv63329.2025.10961787", "effect": "not extracted", "endpoint": "not extracted", "id": "source_15", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "Optimizing Smart City Infrastructure Using 5G Edge AI with Adaptive Multi-Agent Reinforcement Learning", "type": "source", "url": null, "year": 2025}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1109/aiot66900.2025.00149", "effect": "not extracted", "endpoint": "not extracted", "id": "source_16", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "A Large Language Model-based Multi-Agent Framework for Automated Privacy Policy Analysis", "type": "source", "url": null, "year": 2025}, {"comparator": "not extracted", "directness": "primary", "doi": "10.48550/arxiv.2509.05446", "effect": "not extracted", "endpoint": "not extracted", "id": "source_17", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "Dynamic Sensitivity Filter Pruning using Multi-Agent Reinforcement Learning For DCNN's", "type": "source", "url": null, "year": 2025}, {"comparator": "not extracted", "directness": "primary", "doi": "10.5220/0014201400004932", "effect": "not extracted", "endpoint": "not extracted", "id": "source_18", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "A Real-Time Cognitive Reasoning Architecture for Continual Learning and Decision Making in Autonomous Multi-Agent Systems", "type": "source", "url": null, "year": 2025}, {"comparator": "not extracted", "directness": "primary", "doi": "10.4018/979-8-3373-1419-8.ch009", "effect": "not extracted", "endpoint": "not extracted", "id": "source_19", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "Security and Privacy in Multi-Agent LLM Networks", "type": "source", "url": null, "year": 2025}, {"comparator": "not extracted", "directness": "primary", "doi": null, "effect": "not extracted", "endpoint": "not extracted", "id": "source_20", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "DruGagent: Multi-Agent Large Language Model-Based Reasoning for Drug-Target Interaction Prediction.", "type": "source", "url": "https://pubmed.ncbi.nlm.nih.gov/40297237/", "year": 2025}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1109/tccn.2025.3528892", "effect": "not extracted", "endpoint": "not extracted", "id": "source_21", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "AutoHMA-LLM: Efficient Task Coordination and Execution in Heterogeneous Multi-Agent Systems Using Hybrid Large Language Models", "type": "source", "url": null, "year": 2025}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1109/tiv.2024.3471909", "effect": "not extracted", "endpoint": "not extracted", "id": "source_22", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "Multi-Agent Reinforcement Learning for Distributed Cooperative Vehicular Positioning", "type": "source", "url": null, "year": 2025}, {"comparator": "not extracted", "directness": "primary", "doi": "10.48550/arxiv.2506.06574", "effect": "not extracted", "endpoint": "not extracted", "id": "source_23", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "The Optimization Paradox in Clinical AI Multi-Agent Systems", "type": "source", "url": null, "year": 2025}, {"comparator": "not extracted", "directness": "primary", "doi": "10.1109/vtc2025-fall65116.2025.11310364", "effect": "not extracted", "endpoint": "not extracted", "id": "source_24", "intervention_or_exposure": "not extracted", "population": "not extracted", "risk_of_bias": "not appraised in public sidecar", "study": "Multi-Agent Reinforcement Learning assisted Trust-aware Cooperative Spectrum Sensing for Cognitive Radio Networks", "type": "source", "url": null, "year": 2025}], "publication_id": "df4c7383-7aaa-455c-a3b3-dfa20495e7f9", "screening": {"excluded": 0, "exclusion_reasons": ["No PRISMA full-text exclusion-stage filter was applied."], "flow": ["identified", "screened", "excluded_with_reasons", "included"], "identified": 24, "included": 24, "included_or_retained": 24, "screened": 24, "wording": "24 candidate receipts retained after source retrieval, deduplication, and topic filtering. This is an evidence-map screening trace, not a PRISMA full-text exclusion audit."}}

{
  "researka_object_type": "publication_sidecar",
  "researka_publication_id": "df4c7383-7aaa-455c-a3b3-dfa20495e7f9",
  "researka_submission_id": "b21e0c58-b0c6-4aa3-bae1-e4600ddc2d86",
  "sidecar_name": "claim_graph.json",
  "sidecar_url": "https://api.researka.org/publications/df4c7383-7aaa-455c-a3b3-dfa20495e7f9/sidecars/claim_graph.json"
}