Official account of the DataFun community, dedicated to sharing big data and AI industry summit news and speaker talks, with regular downloadable resource packs.
This article explains how JD's team built an attribution‑analysis Agent that maps analysts' investigative steps into a plan‑and‑action loop, uses parallel search with pruning, script constraints, and dynamic structured memory to make data‑driven root‑cause analysis faster, more reliable, and interactive.
The DIVE study shows that expanding the diversity of tool pools and task structures, rather than merely increasing the amount of homogeneous training data, dramatically improves LLM agents' ability to generalize to unseen tools, as demonstrated by a 12k‑vs‑48k experiment and reinforced by a four‑stage synthesis pipeline and RL fine‑tuning.
The article analyzes the technical evolution of AI‑driven recommendation and search, covering Alibaba Cloud's Agentic RAG architecture, Huawei Noah's LLM‑enhanced recommendation pipeline, and Baidu's generative ranking model GRAB, while presenting design choices, performance metrics, and real‑world deployment results.
The article explains how Tencent CodeBuddy’s AI DLC platform unifies Spark batch processing and Ray training to eliminate data movement, turning agent trajectories into reusable training fuel, which reduces monthly‑level training cycles to weekly, enables in‑place computation on billions of features, and cuts operational costs by 60%.
The article analyzes why GUI agents trained on both desktop (mouse‑click) and mobile (touch) interactions suffer from behavior collapse and catastrophic forgetting, introduces the UI‑MOPD framework that assigns platform‑specific teachers through on‑policy distillation, and shows an 8B model surpassing a 235B baseline on OSWorld and MobileWorld benchmarks while preserving general GUI understanding.
The paper identifies the broadcast‑style credit assignment of GRPO as a bottleneck for RL‑LLM math reasoning, proposes the Outcome‑Grounded Advantage Reshaping (OAR) framework with token‑importance estimation, and demonstrates that its two variants, OAR‑P and OAR‑G, consistently improve accuracy, training efficiency, and stability across multiple math benchmarks.
Palantir CEO Alex Karp argues that in the AI era firms must embed specialized, AI‑enhanced infrastructure into their core processes or face extinction, emphasizing that generic AI is a trap and that true competitive advantage comes from domain‑specific knowledge and practice‑driven methodology.
The article details how GenericAgent autonomously reads messages from 31 WeChat groups, extracts and cleans 79 posts, uses a large language model to summarize topics, reverse‑engineers an undocumented image API, and generates a stylized daily report poster without any human intervention.
The article explains how Ctrip leveraged mature large‑language models to overcome traditional data‑product challenges—such as inconsistent metrics and manual attribution—by designing a ChatBI system that combines a multi‑agent framework, memory management, Harness‑driven tool orchestration, and Skill‑based data access, while also evaluating alternatives like Claude SDK and Ali Agent Scope.
In a July 2 live broadcast, three experts dissected the engineering of AI agents—covering architecture choices, the shift from heavyweight frameworks to modular skills, multi‑agent collaboration, evaluation beyond correctness, cost‑control strategies, and the crucial human‑in‑the‑loop responsibility—offering a pragmatic roadmap for stable, accountable agent deployment.
