{"paper":{"title":"LIDSA: Cognitive Arbitration for Signal-Free Autonomous Intersection Management","license":"http://creativecommons.org/licenses/by/4.0/","headline":"An LLM can manage autonomous intersections without traffic signals by arbitrating vehicle intents and priorities.","cross_cats":["cs.CY","cs.ET"],"primary_cat":"cs.AI","authors_text":"Abderrahmane Lakas, Merouane Debbah, Mohamed Amine Ferrag","submitted_at":"2026-05-12T16:04:50Z","abstract_excerpt":"Large language models (LLMs) show strong potential for Intelligent Transportation Systems (ITS), particularly in tasks requiring situational reasoning and multi-agent coordination. These capabilities make them well suited for cooperative driving, where rule-based approaches struggle in complex and dynamic traffic environments. Intersection management remains especially challenging due to conflicting right-of-way demands, heterogeneous vehicle priorities, and vehicle-specific kinematic constraints that must be resolved in real time. However, existing approaches typically use LLMs as auxiliary c"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Results show that LISA reduces mean control delay by up to 89.1% and maintains Level of Service C while all non-LLM baselines degrade to Level of Service F. Under near-saturated demand, LISA reduces mean waiting time by 93% and peak queue length by 60.6% relative to fixed-cycle control. It also lowers fuel consumption by up to 48.8% and achieves 86.2% intent satisfaction.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"LLM inference can be executed with low enough latency to support real-time sub-second speed advisory decisions despite the acknowledged limits of current LLM inference speeds for sub-second control.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LISA applies LLMs as primary decision-makers for signal-free intersection management, cutting mean control delay by up to 89.1% and maintaining better service levels than fixed-cycle, SCATS, AIM, or GLOSA baselines.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An LLM can manage autonomous intersections without traffic signals by arbitrating vehicle intents and priorities.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"95a7311bd85726a062e695e7eb7174aa2e44c90078bfb64f56eaa9df5399b5c7"},"source":{"id":"2605.12321","kind":"arxiv","version":2},"verdict":{"id":"836be406-f719-4276-8511-636ee636c721","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T04:30:21.562180Z","strongest_claim":"Results show that LISA reduces mean control delay by up to 89.1% and maintains Level of Service C while all non-LLM baselines degrade to Level of Service F. Under near-saturated demand, LISA reduces mean waiting time by 93% and peak queue length by 60.6% relative to fixed-cycle control. It also lowers fuel consumption by up to 48.8% and achieves 86.2% intent satisfaction.","one_line_summary":"LISA applies LLMs as primary decision-makers for signal-free intersection management, cutting mean control delay by up to 89.1% and maintaining better service levels than fixed-cycle, SCATS, AIM, or GLOSA baselines.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"LLM inference can be executed with low enough latency to support real-time sub-second speed advisory decisions despite the acknowledged limits of current LLM inference speeds for sub-second control.","pith_extraction_headline":"An LLM can manage autonomous intersections without traffic signals by arbitrating vehicle intents and priorities."},"integrity":{"clean":false,"summary":{"advisory":1,"critical":0,"by_detector":{"doi_compliance":{"total":1,"advisory":1,"critical":0,"informational":0}},"informational":0},"endpoint":"/pith/2605.12321/integrity.json","findings":[{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1162/tacla) was visible in the surrounding text but could not be confirmed against doi.org as printed.","detector":"doi_compliance","severity":"advisory","ref_index":42,"audited_at":"2026-05-19T07:40:33.419235Z","detected_doi":"10.1162/tacla","finding_type":"recoverable_identifier","verdict_class":"incontrovertible","detected_arxiv_id":null}],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-20T13:31:25.372125Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T09:57:56.022175Z","status":"completed","version":"1.0.0","findings_count":1},{"name":"claim_evidence","ran_at":"2026-05-19T22:41:58.275501Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T10:39:14.612109Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"f6c42f7cebb6d05571acb86e17c520d7170979d674e8f7556167f67801cd55cc"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"c0a803185bc41050b0fcc5a861a478660241d37e8c23976b5f9894d5009c78ef"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}