Dedicated to sharing and discussing big data and AI technology applications, aiming to empower a million data scientists. Regularly hosts live tech talks and curates articles on big data, recommendation/search algorithms, advertising algorithms, NLP, intelligent risk control, autonomous driving, and machine learning/deep learning.
vivo AI Lab introduces CAPO-SLT, a confidence-aware policy optimization method that stabilizes sign language translation by giving each token a dynamic clipping bound based on old-policy confidence, achieving state-of-the-art results on Chinese and American sign language benchmarks using only pose input.
A 2026 survey paper introduces Graph Engineering as the next phase for LLM agents, shifting focus from individual model capabilities to system-level organization via explicit task DAGs, runtime state management with provenance and recovery, capability-based agent coordination, and a graph-native control plane that treats tasks, agents, and state as first-class system objects.
Palantir provides templates for Claude, OpenAI, and Google agent SDKs that share Ontology resources, authentication, MCP interfaces, and deployment pipelines, standardizing the enterprise integration layer while letting each framework retain its native reasoning loop, revealing that business objects, permissions, and action boundaries—not models—are the enduring foundation for production agents.
A 2026 survey paper introduces Graph Engineering as the system layer that organizes LLM agents into reliable multi-agent workflows through explicit DAGs, runtime state management, fault tolerance, and a control plane, shifting focus from individual agent capabilities to system-level engineering.
Palantir's August 18 update to AIP Analyst introduces Skills and Analysis Lookup, adding a "method memory" layer that lets agents reuse analytical workflows and tool chains rather than just retrieving past content, all grounded in the Ontology framework.
Palantir's August 27 update adds Automate tools to AI FDE, enabling agents to create and modify business automations — defining triggers, actions, retries, and fallbacks — within a governed branching and approval system, moving enterprise AI from question-answering to workflow orchestration.
This article analyzes MemoHarness, a framework that evolves AI agents by optimizing six external harness dimensions—context assembly, tool interaction, generation control, task orchestration, memory management, and output processing—instead of model weights, demonstrating gains on terminal, coding, and finance tasks while noting limited experimental scale and selective cross-task transfer.
Hologres evolves from a real-time data warehouse into an AI data infrastructure, integrating multimodal data via Object Tables and Dynamic Tables, providing AI Functions for hybrid search within SQL, an AI Assistant for automated warehouse operations, and a long-term memory service for cross-session agent recall.
Snowflake's new Data Lineage for Cortex Agents tracks agent data reachability through governed semantic views, extending lineage from tables to AI agents; Databricks pursues similar governance via Unity Catalog and Genie Ontology, positioning the semantic layer as a critical AI governance boundary for accuracy, authorization, consistency, and auditability.
As data platforms become increasingly intelligent, operational complexity rises due to heterogeneous workloads and finer‑grained configurations, but Tencent Cloud's TCInsight introduces system intelligence with specialized agents that automate selection, migration, usage and tuning, cutting migration time by 50%, reducing resource waste by 15% and shrinking fault‑diagnosis from hours to minutes.
