Agentic Search
Search documents
X @Avi Chawla
Avi Chawla· 2026-03-30 09:02
RAG is a distraction!Here's how Google and Microsoft actually give context to their production agents:To understand this, think about what "give an agent context" actually means in production.In production, data lives across Slack, Gmail, Jira, Drive, Salesforce, GitHub, and SQL databases. Each source has different auth, different data formats, different update cycles.A query like "summarize all activity on the auth migration this week" needs to pull from five sources simultaneously, filter by time, check p ...
先解行为,再训Agent:CMU开源首份Agentic Search日志数据,把Agent拆开给你看
机器之心· 2026-02-09 01:18
Core Insights - The article discusses the lack of systematic characterization and analysis of how intelligent agents perform queries, rewrite them, and utilize retrieved information in the context of Agentic Search driven by large language models [2][7]. Group 1: Research Contributions - The CMU team organized over 14 million Agentic Search requests and approximately 4 million sessions from six months of real traffic, releasing the first open-source Agentic Search behavior log dataset [7][8]. - A three-layer analytical framework was proposed, consisting of session intent (Declarative / Procedural / Reasoning), trajectory actions (Specialization / Generalization / Exploration / Repetition), and the Context-driven Term Adoption Rate (CTAR) to measure the adoption of retrieved information [2][8]. Group 2: Data and Platform Overview - The DeepResearchGym (DRGym) platform was established for research purposes, providing a unified search API based on dense retrieval from fixed web corpus snapshots [12]. - The dataset includes logs from 25 countries and nearly 600 IP addresses, ensuring diverse usage and anonymity through data cleaning and anonymization processes [13][14]. Group 3: Session Analysis Methodology - A semantic and temporal joint sessionization strategy was employed to analyze behavior patterns, resulting in approximately 4 million sessions characterized by high-frequency and iterative queries [16][19]. - The analysis revealed that the majority of queries were concentrated in a dispersed semantic space, with low overlap with common Agentic Benchmark tasks [18]. Group 4: Intent and Trajectory Dynamics - The research categorized multi-turn sessions into three types of session intents: Declarative, Procedural, and Reasoning, with distinct characteristics in session length and retrieval configurations [22][25]. - Four types of trajectory moves were identified: Specialization, Generalization, Exploration, and Repetition, with a notable "drill-down bias" observed in the agents' behavior [27][32]. Group 5: CTAR Insights - The CTAR metric indicated that over half of new terms in queries could be traced back to previously retrieved documents, highlighting the agents' reliance on historical context [34][35]. - Different trajectory moves exhibited significant variations in CTAR, with Specialization and Exploration showing higher rates of term adoption compared to Repetition [36][37]. Group 6: System Design Implications - The findings suggest that repeated actions could signal potential stagnation in the agent's search process, prompting the need for system interventions to trigger exploration or generalization strategies [41]. - The retrieval budget should adapt based on task intent and trajectory state, allowing for more effective document coverage and query refinement [42]. - Incorporating CTAR and similar metrics into system monitoring can help assess whether agents are effectively utilizing retrieved information [43]. Group 7: Overall Contributions - The research provides the first open-source dataset for Agentic Search behavior logs, establishing a reproducible data foundation for future studies [46]. - It introduces an analytical framework for understanding Agentic Search processes, offering tools for behavior modeling and strategy comparison [47]. - The study also translates empirical observations into quantifiable design recommendations for improving agentic search systems [48].
Etsy (ETSY) FY Conference Transcript
2025-05-13 20:10
Summary of Etsy (ETSY) FY Conference Call - May 13, 2025 Company Overview - Etsy is a leading two-sided marketplace with approximately 95 million active buyers and over 100 million listings from more than 8 million active sellers, primarily focused on unique, creative, and handmade goods [2][2] - Estimated to generate $12 billion in Gross Merchandise Sales (GMS) for the year, with 26% adjusted EBITDA margins and $600 million in free cash flow [2][2] Macro Environment and Consumer Trends - The macro environment remains volatile, but Etsy has not observed significant changes in consumer spending despite market fluctuations [6][6] - Etsy experienced substantial growth during the pandemic, with GMS increasing from $4.9 billion pre-pandemic to nearly $11 billion in 2024 [5][5] - The company has shown resilience against supply shocks and inflation, with sellers not passing on price increases as seen in other markets [7][8] Competitive Landscape - The e-commerce market is highly competitive, with major players like Amazon and Walmart actively participating [11][11] - Etsy is focusing on local sellers to mitigate tariff impacts, with over 90% of supplies sourced domestically [16][16][20][20] - The advertising market remains strong, and Etsy is enhancing its marketing technology to improve performance [12][12] Growth Strategies - Etsy is recalibrating its strategy to balance near-term conversions with long-term initiatives, particularly focusing on app development and personalized experiences [24][24][41][41] - The company has shifted resources to improve the app experience, with 44.5% of GMS now coming from app purchases [38][38] - Emphasis on quality and personalization through a new search engine architecture that prioritizes customer experience [30][30] Advertising and Revenue Growth - Etsy has seen growth in revenue despite GMS declines, primarily through Etsy Payments and Etsy Ads, which enhance seller profitability [57][57][58][58] - The company is exploring off-site ads as a cooperative advertising program to further drive sales for sellers [62][62] Financial Performance and Profitability - Etsy has maintained a strong take rate and gross margins, with expectations for continued profitability in 2025 [65][65][76][76] - The divestiture of Reverb is expected to improve overall profit margins for Etsy [71][71][73][73] Future Outlook - Etsy's unique marketplace model positions it as a valuable alternative in a consolidating e-commerce landscape [78][78] - The company is optimistic about its growth potential, leveraging its distinct offerings to attract consumers seeking alternatives to traditional e-commerce [78][78]