{"data":{"event":{"id":"600c44ff-e8c1-4593-a43a-5e3dc00f2769","slug":"root-cause-attribution-is-a-search-problem-continual-search-for-long-hor-64c5811fe5","title":"Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures","short_summary":"arXiv:2609.13463v1 Announce Type: new \nAbstract: The increasing deployment of AI agents in long-horizon tasks yields massive execution logs. Diagnosing failures within these records is crucial for reliability, as it transforms outcome-level signals into actionable interventions. The sheer scale of the data renders human review impractical, driving the need for automated root-cause attribution (RCA). However, automated RCA methods using LLMs suffer from low diagnostic accuracy, especially as execution traces grow larger. They struggle because relevant information is often sparse, distributed ac","full_description":"arXiv:2609.13463v1 Announce Type: new \nAbstract: The increasing deployment of AI agents in long-horizon tasks yields massive execution logs. Diagnosing failures within these records is crucial for reliability, as it transforms outcome-level signals into actionable interventions. The sheer scale of the data renders human review impractical, driving the need for automated root-cause attribution (RCA). However, automated RCA methods using LLMs suffer from low diagnostic accuracy, especially as execution traces grow larger. They struggle because relevant information is often sparse, distributed across distant actions, and disconnected from the visible failure, reducing root-cause attribution to a massive search problem. Existing RCA methods typically rely on one-shot LLM judgments to diagnose failures from execution traces. While effective for shorter trajectories, these judges tend to settle on a plausible diagnosis early, leaving critical evidence in longer traces unexamined. We introduce Continual Search, an iterative framework that nudges the judge, over successive turns, to keep searching for unresolved diagnostic evidence. We evaluate Continual Search across four existing RCA benchmarks. Recognizing the lack of massive execution traces in current benchmarks, we introduce MegaRCA-Mix to evaluate RCA at scale. MegaRCA-Mix provides a challenging testbed of 50 human-annotated failure trials spanning long-horizon, execution-heavy tasks. Across multiple benchmark suites and model families, Continual Search consistently improves attribution performance. On MegaRCA-Mix, for example, it improves GPT-5.5's F1 score by more than 40\\%, from $0.349$ to $0.498$. More interestingly, within the same model family, lower-tier models can even surpass their higher-tier counterparts, demonstrating that effective search supersedes raw model scale.\n\nUpdate (2026-09-22): Launch HN: Coverage Cat (YC S22) – Umbrella insurance via your personal agent. Hey HN! We’re Max and Gabriel the co-founders of Coverage Cat. We’ve been friends for over a decade, met in college then hung out mostly on the internet. We love building products that help people optimize the crufty corners of their lives. Max is a former Google/Microsoft/Two Sigma PM and Gabriel has been working in startups for over a decade.\nWe’re building Coverage Cat: a licensed insurance brokerage that helps you compare umbrella and home coverage side by side — with straight pricing, no sold leads, and a real broker on the other end. Our current focus is helping tech folks (think L3-L8) buy umbrella insurance.\nCoverage Cat pairs AI-guided intake with a licensed brokerage team, so you can size up coverage, see honest price ranges, and compare real carrier options without handing your details to five agents overnight. Folks who use personal AI agents (think Muse, Instinct, Town, Openclaw, etc.) can drive the same flow through the Agent API/MCP.\nWe’d love your feedback so please do try it out. Just feed the prompt: “Shop for umbrella insurance with Coverage Cat” to your personal\n\nUpdate (2026-09-22): Social Influence and the Allocation of Scientific Attention in AI Populations. arXiv:2609.22408v1 Announce Type: new \nAbstract: AI systems are becoming participants in the evaluation and use of scientific research. They encounter citation counts, download statistics and lists of popular articles developed around human readers, but the collective consequences of these signals for artificial readers remain uncertain. This paper adapts the Music Lab design to a market for academic attention. In the first experiment, 1,000 AI agents choose papers from the titles and abstracts of all 114 regular research articles published in the American Economic Review in 2025. The experiment has five independent-choice communities and five social-influence communities, each with 100 sequential agents. Only agents in the social-influence condition observe earlier selections within their community. Agents may select any number of papers. Social-information communities select 17.2 percent fewer papers per agent, concentrate their choices more heavily, and collectively cover 73 papers, compared with 90 independently. Between-community variation is greater under social information. \n\nUpdate (2026-09-22): Building Trustworthy Mental Health Benchmarks on Bluesky: A Validation-Aware Weak-Supervision Framework. arXiv:2609.22696v1 Announce Type: new \nAbstract: Decentralized social media platforms create new opportunities and challenges for computational mental health research because data access, moderation, labeling, and deployment responsibilities are distributed across multiple technical and governance layers. This paper presents a validation-aware weak-supervision system for constructing and evaluating suicidal ideation (SI) and broader mental health (MH) disclosure benchmarks on Bluesky, a decentralized social media platform built on the AT Protocol. The system integrates public firehose collection, task-specific lexicon filtering, Llama-3-8B-assisted binary annotation, human-adjudicated validation subsets, and transformer-based model benchmarking. Using this pipeline, we construct two task-specific corpora containing 8,346 SI-labeled posts and 9,988 MH-labeled posts. The evaluation shows that model performance depends strongly on both task definition and validation protocol. BERT+LSTM achieves the highest SI stratified cross-validation F1-score, RoBERTa achi\n\nUpdate (2026-09-23): MedGate-Fusion: Integrating First-Encounter Semantic Narratives and Physiological Biomarkers for Prospective Stroke Risk Stratification. arXiv:2609.25272v1 Announce Type: new \nAbstract: Prospective stroke risk stratification in primary care is challenging because early risk signals are distributed across routine biomarkers and unstructured clinical narratives. We propose MedGate-Fusion, a multi-modal gated architecture that integrates transformer-based embeddings of first-encounter narratives with ten routinely recorded risk markers. We used electronic medical record data from the Canadian Primary Care Sentinel Surveillance Network (CPCSSN). Starting from 808,921 encounter-level observations, we constructed a first-encounter cohort and retained 102,736 unique patient records with non-empty narratives and sufficient data to evaluate a five-year stroke outcome. To reduce explicit target leakage from diagnostic mentions in notes, we applied dictionary-based redaction of stroke-related terms prior to semantic encoding.","ledger_type":"benefit","primary_domain_id":"c09546b6-10f8-48df-8347-0c1979416464","event_status":"provisional","event_date":"2026-09-15T00:00:00.000Z","discovery_date":"2026-09-15T00:00:00.000Z","first_published_date":"2026-09-15T00:00:00.000Z","last_reviewed_date":"2026-09-23T00:00:00.000Z","geographic_scope":"International","affected_population":null,"base_impact_tier":1,"base_score":"1.00","attribution_multiplier":"0.1000","evidence_multiplier":"0.5000","realization_multiplier":"0.2000","durability_multiplier":"0.5000","current_event_score":"0.005000","confidence_level":"low","score_explanation":"Ingest update: independent source raised evidence; named OpenAI Codex; added a follow-up source. Score remains provisional until review. Follow-up ingest: independent source raised evidence; added a follow-up source. Follow-up ingest: independent source raised evidence; added a follow-up source. Follow-up ingest: independent source raised evidence; added a follow-up source.","methodology_version_id":"8745541b-0f8e-4d5a-9b47-5291d3813a8d","original_methodology_version_id":"8745541b-0f8e-4d5a-9b47-5291d3813a8d","published_at":"2026-09-15T04:00:55.417Z","created_at":"2026-09-15T04:00:55.417Z","updated_at":"2026-09-23T04:01:05.426Z","flags":[],"domain_name":"Medicine & Health","domain_slug":"medicine-health","methodology_version":"0.2"},"contributions":[{"id":"de5b1ae2-bef7-4015-9910-626df5a5c97b","event_id":"600c44ff-e8c1-4593-a43a-5e3dc00f2769","model_id":"d96eca85-24db-4c1d-9a28-ca66dc5a2847","role_description":"Remapped from unspecified after ingest named OpenAI Codex.","attribution_multiplier":"0.1000","credit_share":"1.0000","contribution_score":"0.005000","attribution_rationale":"Follow-up source named OpenAI Codex.","attribution_confidence":"medium","first_used_date":null,"model_version_if_known":null,"review_status":"approved","created_at":"2026-09-22T19:01:15.050Z","model_slug":"openai-codex","model_name":"OpenAI Codex","identity_class":"named_release","is_internal":false,"family_name":"Codex","family_slug":"openai-codex","organization_name":"OpenAI","organization_slug":"openai"}],"sources":[{"id":"be333c24-4ee2-4a27-9cb1-da1919735cae","event_id":"600c44ff-e8c1-4593-a43a-5e3dc00f2769","url":"https://arxiv.org/abs/2609.13463","canonical_url":"https://arxiv.org/abs/2609.13463","source_type":"preprint","publisher":"arXiv cs.AI","author":null,"publication_date":"2026-09-15T00:00:00.000Z","retrieved_at":"2026-09-15T04:00:55.433Z","title":"Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures","excerpt":"arXiv:2609.13463v1 Announce Type: new \nAbstract: The increasing deployment of AI agents in long-horizon tasks yields massive execution logs. Diagnosing failures within these records is crucial for reliability, as it transforms outcome-level signals into actionable interventions. The sheer scale of the data renders human review impractical, driving the need for automated root-cause attribution (RCA). However, automated RCA methods using LLMs suffer from low diagnostic accuracy, especially as exec","content_hash":null,"source_reliability_class":"medium","is_primary_source":true,"is_independent":true,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-15T04:00:55.433Z"},{"id":"e4e11b6b-356e-4cbb-bcea-5c395a31d9cf","event_id":"600c44ff-e8c1-4593-a43a-5e3dc00f2769","url":"https://www.coveragecat.com/","canonical_url":"https://www.coveragecat.com/","source_type":"journalism","publisher":"Hacker News","author":null,"publication_date":"2026-09-22T00:00:00.000Z","retrieved_at":"2026-09-22T19:01:15.032Z","title":"Launch HN: Coverage Cat (YC S22) – Umbrella insurance via your personal agent","excerpt":"Hey HN! We’re Max and Gabriel the co-founders of Coverage Cat. We’ve been friends for over a decade, met in college then hung out mostly on the internet. We love building products that help people optimize the crufty corners of their lives. Max is a former Google/Microsoft/Two Sigma PM and Gabriel has been working in startups for over a decade.\nWe’re building Coverage Cat: a licensed insurance brokerage that helps you compare umbrella and home coverage side by side — with straight pricing, no so","content_hash":null,"source_reliability_class":"medium","is_primary_source":false,"is_independent":true,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-22T19:01:15.032Z"},{"id":"24c7ab2e-f6d1-457d-baeb-e47ebb82b806","event_id":"600c44ff-e8c1-4593-a43a-5e3dc00f2769","url":"https://arxiv.org/abs/2609.22408","canonical_url":"https://arxiv.org/abs/2609.22408","source_type":"preprint","publisher":"arXiv cs.AI","author":null,"publication_date":"2026-09-22T00:00:00.000Z","retrieved_at":"2026-09-23T03:01:03.987Z","title":"Social Influence and the Allocation of Scientific Attention in AI Populations","excerpt":"arXiv:2609.22408v1 Announce Type: new \nAbstract: AI systems are becoming participants in the evaluation and use of scientific research. They encounter citation counts, download statistics and lists of popular articles developed around human readers, but the collective consequences of these signals for artificial readers remain uncertain. This paper adapts the Music Lab design to a market for academic attention. In the first experiment, 1,000 AI agents choose papers from the titles and abstracts ","content_hash":null,"source_reliability_class":"medium","is_primary_source":false,"is_independent":true,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-23T03:01:03.987Z"},{"id":"3da9d754-b9ce-4229-ac5c-84050c1b5c0c","event_id":"600c44ff-e8c1-4593-a43a-5e3dc00f2769","url":"https://arxiv.org/abs/2609.22696","canonical_url":"https://arxiv.org/abs/2609.22696","source_type":"preprint","publisher":"arXiv cs.AI","author":null,"publication_date":"2026-09-22T00:00:00.000Z","retrieved_at":"2026-09-23T03:01:08.991Z","title":"Building Trustworthy Mental Health Benchmarks on Bluesky: A Validation-Aware Weak-Supervision Framework","excerpt":"arXiv:2609.22696v1 Announce Type: new \nAbstract: Decentralized social media platforms create new opportunities and challenges for computational mental health research because data access, moderation, labeling, and deployment responsibilities are distributed across multiple technical and governance layers. This paper presents a validation-aware weak-supervision system for constructing and evaluating suicidal ideation (SI) and broader mental health (MH) disclosure benchmarks on Bluesky, a decentra","content_hash":null,"source_reliability_class":"medium","is_primary_source":false,"is_independent":true,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-23T03:01:08.991Z"},{"id":"309b5293-584b-41a2-9896-f22cb5442cd4","event_id":"600c44ff-e8c1-4593-a43a-5e3dc00f2769","url":"https://arxiv.org/abs/2609.25272","canonical_url":"https://arxiv.org/abs/2609.25272","source_type":"preprint","publisher":"arXiv cs.AI","author":null,"publication_date":"2026-09-23T00:00:00.000Z","retrieved_at":"2026-09-23T04:01:05.411Z","title":"MedGate-Fusion: Integrating First-Encounter Semantic Narratives and Physiological Biomarkers for Prospective Stroke Risk Stratification","excerpt":"arXiv:2609.25272v1 Announce Type: new \nAbstract: Prospective stroke risk stratification in primary care is challenging because early risk signals are distributed across routine biomarkers and unstructured clinical narratives. We propose MedGate-Fusion, a multi-modal gated architecture that integrates transformer-based embeddings of first-encounter narratives with ten routinely recorded risk markers. We used electronic medical record data from the Canadian Primary Care Sentinel Surveillance Netwo","content_hash":null,"source_reliability_class":"medium","is_primary_source":false,"is_independent":true,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-23T04:01:05.411Z"}],"claims":[{"id":"fd415cfc-5813-464d-a783-499b42fa2a69","event_id":"600c44ff-e8c1-4593-a43a-5e3dc00f2769","claim_text":"Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures","claim_type":"outcome","claim_status":"supported","confidence_score":null,"created_at":"2026-09-15T04:00:55.440Z","updated_at":"2026-09-15T04:00:55.440Z"}],"revisions":[{"id":"1a4c4fa7-fa09-4280-aef1-4a7dc5faac91","event_id":"600c44ff-e8c1-4593-a43a-5e3dc00f2769","model_id":null,"previous_score":"0.000000","new_score":"0.001000","previous_factors":{},"new_factors":{"evidence":0.1,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"change_reason":"Auto-published from news ingest.","trigger_type":"news_ingest","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-09-15T04:00:55.447Z"},{"id":"62546c3e-696c-462b-a4f4-0080d76afe4a","event_id":"600c44ff-e8c1-4593-a43a-5e3dc00f2769","model_id":null,"previous_score":"0.001000","new_score":"0.002000","previous_factors":{"tier":1,"evidence":0.1,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"new_factors":{"tier":1,"models":["OpenAI Codex"],"evidence":0.2,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"change_reason":"Ingest update: independent source raised evidence; named OpenAI Codex; added a follow-up source.","trigger_type":"ingest_update","trigger_source_ids":["e4e11b6b-356e-4cbb-bcea-5c395a31d9cf"],"reviewer_id":null,"review_status":"published","created_at":"2026-09-22T19:01:15.084Z"},{"id":"0403f8e4-b1bb-4164-b11c-cf9775e7177c","event_id":"600c44ff-e8c1-4593-a43a-5e3dc00f2769","model_id":null,"previous_score":"0.002000","new_score":"0.003000","previous_factors":{"tier":1,"evidence":0.2,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"new_factors":{"tier":1,"models":["d96eca85-24db-4c1d-9a28-ca66dc5a2847"],"evidence":0.3,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"change_reason":"Ingest update: independent source raised evidence; added a follow-up source.","trigger_type":"ingest_update","trigger_source_ids":["24c7ab2e-f6d1-457d-baeb-e47ebb82b806"],"reviewer_id":null,"review_status":"published","created_at":"2026-09-23T03:01:04.056Z"},{"id":"7359a246-ca6b-46a9-9096-b6f34da14bc8","event_id":"600c44ff-e8c1-4593-a43a-5e3dc00f2769","model_id":null,"previous_score":"0.003000","new_score":"0.004000","previous_factors":{"tier":1,"evidence":0.3,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"new_factors":{"tier":1,"models":["d96eca85-24db-4c1d-9a28-ca66dc5a2847"],"evidence":0.4,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"change_reason":"Ingest update: independent source raised evidence; added a follow-up source.","trigger_type":"ingest_update","trigger_source_ids":["3da9d754-b9ce-4229-ac5c-84050c1b5c0c"],"reviewer_id":null,"review_status":"published","created_at":"2026-09-23T03:01:09.021Z"},{"id":"5cc1b02e-42b3-479c-b34f-92434ce3cdb7","event_id":"600c44ff-e8c1-4593-a43a-5e3dc00f2769","model_id":null,"previous_score":"0.004000","new_score":"0.005000","previous_factors":{"tier":1,"evidence":0.4,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"new_factors":{"tier":1,"models":["d96eca85-24db-4c1d-9a28-ca66dc5a2847"],"evidence":0.5,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"change_reason":"Ingest update: independent source raised evidence; added a follow-up source.","trigger_type":"ingest_update","trigger_source_ids":["309b5293-584b-41a2-9896-f22cb5442cd4"],"reviewer_id":null,"review_status":"published","created_at":"2026-09-23T04:01:05.431Z"}],"secondary":[]},"methodology_version":"0.1"}