Airbnb

Follow this topic Ask about this topic

Momentum

1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 14

All topics

When Are Aggregate Agent Traces Diagnosable? Traffic-Governed Interpretation and Calibrated Abstention
Sep 22, 2026Peiying Zhu, Sidi ChangTraces Fault Diagnosis
Blossom AI San Francisco, CA, USA
ViHoRec: A Quality-Controlled Vietnamese Hotel Recommendation Dataset and Cold-Start Benchmark
Jul 14, 2026Minh Hoang NguyenAirbnb Recommendation Quality
Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam · Vietnam National University, Ho Chi Minh City, Vietnam
Proximity Features: Privacy-Compliant Cold-Start Personalization at Airbnb
Jul 14, 2026Wei Jiang, Bin Xu, Hui Gao +6Airbnb Privacy
Airbnb Inc. San Francisco, USA
Understanding Guest Preferences and Optimizing Two-sided Marketplaces: Airbnb as an Example
Jul 1, 2026Yufei Wu, Daniel SchmiererAirbnb Preference Alignment Learning
Airbnb, Inc. San Francisco, California, USA
JourneyFormer: Encoding Airbnb Guest Journey with Sequence Modeling
Jun 17, 2026Daochen Zha, Chun How Tan, Xin Liu +9Airbnb Sequence Modeling
Airbnb, San Francisco, USA
Optimising Temporary Accommodation Placement Across London with AI-Powered SaaS in E-Governance Systems
Jun 15, 2026Hankun He, Jordan Richards, Gopalakrishnan Netuveli +5Artificial Intelligence Deployment Airbnb
UK Centre for AI in the Public Sector, London, United Kingdom · Institute for Connected Communities, University of East London, London E15 4LZ, United Kingdom · University of East London, London E15 4LZ, United Kingdom +1
Whose hotel does the AI recommend? An algorithm audit of reputation signals in LLM-assisted hotel selection
Jun 15, 2026Mirza Samad Ahmed Baig, Syeda Anshrah Gillani, Asher AliAirbnb Recommendation
Fandaqah, Al Khobar, Saudi Arabia. · Hamdard University, Karachi, Pakistan.
Less Context, Better Agents: Efficient Context Engineering for Long-Horizon Tool-Using LLM Agents
Jun 8, 2026Abhilasha Lodha, Mahsa Pahlavikhah Varnosfaderani, Abir Chakraborty +1Large Language Model Tool Use Model Context Protocol
Microsoft
Accommodation Goes Both Ways: Studying Linguistic Convergence Between Humans and Language Models
May 28, 2026Terra BlevinsLinguistics Convergence
Khoury College of Computer Sciences Northeastern University, Boston, MA
SentimentLens: Reconciling Sentiment and Ratings via Dual-Modality in the Hospitality Sector
May 22, 2026Dineth Jayakody, Pasindu Thenahandi, Sampath JayarathnaAirbnb Sentiment
Department of Computer Science Old Dominion University Norfolk, Virginia, USA
When Outcome Looks Right But Discipline Fails: Trace-Based Evaluation Under Hidden Competitor State
May 18, 2026Peiying Zhu, Sidi ChangReward-Only Policy Optimization Variants Airbnb
Blossom AI San Francisco, USA · Blossom AI Labs Tokyo, Japan
Reservation Based Smart Parking Management
May 17, 2026Giacomo Cabri, Manuela Montangero, Filippo Muzzini +1Airbnb Reputation
dept. Physics, Informatics and Mathematics University of Modena and Reggio Emilia Modena, Italy
Barriers and Enablers of Online Instruction in Hospitality Education in the Philippines: An Exploratory Study
Apr 27, 2026Maria Anna D. Cruz, Jeaneth D. Serna, Lloyd D. Feliciano +5Pedagogical Frameworks Airbnb
Pampanga State University, Pampanga, Philippines
Room Scene Discovery and Grouping in Unstructured Vacation Rental Image Collections
Jun 30, 2025Vignesh Ram Nithin Kappagantula, Shayan HassantabarAirbnb Query Image
Expedia Group Seattle, Washington, USA

Sep 22, 2026, cs.AIJ/K move · Enter open · S save

When Are Aggregate Agent Traces Diagnosable? Traffic-Governed Interpretation and Calibrated Abstention

Peiying Zhu, Sidi Chang

Blossom AI San Francisco, CA, USA

Traces Fault Diagnosis Admissibility Diagnosis Airbnb Interpretation

Open paper AskPDF arXiv

Runtime traces can appear transparent, but a closed-loop policy determines which states are visited and which failures become visible. We study a simulated hotel-pricing agent mapping time, inventory, and market state to discrete price actions under varying demand regimes. A fault may leave no aggregate trace when the policy rarely visits affected cells. We treat entry into aggregate-only fault interpretation as a diagnosability decision preceding scoring or localization. A reference-map gate requires repeated clean-policy support; a matched runtime gate then requires joint support in clean and current streams. Signal analysis occurs only after both pass. We calibrate false admission on a disjoint clean stream at the physical-component level and model detection by affected clean traffic rather than nominal cell coverage. In a frozen one-shot heldout, 55/72 (76.4%) regime-component units were reference-admitted, representing 20 physical components; 54/55 passed matched runtime admission, while the rejected unit abstained. Stable false admission was 0/20, with a one-sided exact 95% upper bound of 0.1391, meeting the frozen 0.20 criterion. Across 540 repeated unit-arm rows nested in those 20 clusters, affected clean traffic reduced negative log likelihood by 29.3% relative to cell coverage, a gain of 0.1264 nats per row (cluster-bootstrap 95% interval [0.0593, 0.1918]). Adding mask family and its interaction improved log loss by 0.0015 nats per row (one-sided upper bound 0.0066), below the frozen 0.01 practical-sufficiency margin. A development audit found that exact minimum hitting set and greedy selection chose identical supports in 12/12 scenarios because singleton evidence had resolved the conflicts. The result is a bounded rule for interpreting aggregate agent behavior: first establish exposure, then score change, and abstain when the trace cannot support the claim.

Momentum

Related topics

Latest papers 14