{"total":14,"rows":[{"id":"2602.12315","title":"AgenticShop: Benchmarking Agentic Product Curation for Personalized Web Shopping","created":"2026-02-12","cited_by_count":7,"area":"agents"},{"id":"2511.23281","title":"MCP vs RAG vs NLWeb vs HTML: A Comparison of the Effectiveness and Efficiency of Different Agent Interfaces to the Web (Technical Report)","created":"2025-11-28","cited_by_count":6,"area":"agents"},{"id":"2510.19631","title":"HSCodeComp: A Realistic and Expert-level Benchmark for Deep Search Agents in Hierarchical Rule Application","created":"2025-10-22","cited_by_count":5,"area":"agents"},{"id":"2605.16116","title":"ShopGym: An Integrated Framework for Realistic Simulation and Scalable Benchmarking of E-Commerce Web Agents","created":"2026-05-15","cited_by_count":5,"area":"agents"},{"id":"2602.01443","title":"SimGym: Traffic-Grounded Browser Agents for Offline A/B Testing in E-Commerce","created":"2026-02-01","cited_by_count":4,"area":"agents"},{"id":"2604.16385","title":"StressWeb: A Diagnostic Benchmark for Web Agent Robustness under Realistic Interaction Variability","created":"2026-03-27","cited_by_count":2,"area":"agents"},{"id":"2608.09282","title":"ComboShoppingBench: Evaluating LLM Agents for Budget-Constrained Basket Shopping with Coupons","created":"2026-08-10","cited_by_count":2,"area":"agents"},{"id":"2601.18202","title":"SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback","created":"2026-01-26","cited_by_count":1,"area":"agents"},{"id":"2605.19219","title":"SimGym: A Framework for A/B Test Simulation in E-Commerce with Traffic-Grounded VLM Agents","created":"2026-05-19","cited_by_count":1,"area":"agents"},{"id":"2608.02441","title":"Agentic Commerce World: An Auditable and Verifiable Environment for Vibe Commerce","created":"2026-08-03","cited_by_count":1,"area":"agents"},{"id":"2604.13531","title":"RiskWebWorld: A Realistic Interactive Benchmark for GUI Agents in E-commerce Risk Management","created":"2026-04-15","cited_by_count":0,"area":"agents"},{"id":"2605.18805","title":"RecoAtlas: From Semantic Plausibility to Set-Level Utility in LLM Recommendation Agents","created":"2026-05-11","cited_by_count":0,"area":"agents"},{"id":"2607.22689","title":"Beyond Sequential Interaction: Benchmarking Parallel Execution and Coordination for GUI Agents","created":"2026-07-17","cited_by_count":0,"area":"agents"},{"id":"2610.17378","title":"Get In, Decide, Prove: A Merchant-Side Readiness Benchmark for Agentic Commerce","created":"2026-10-12","cited_by_count":0,"area":"agents"}],"next_cursor":null}