Author

Xiaohongshu Tech REDtech

Official account of the Xiaohongshu tech team, sharing tech innovations and problem insights, advancing together.

139

Articles

Likes

1.2k

Views

Comments

Latest from Xiaohongshu Tech REDtech

100 recent articles max

Xiaohongshu Tech REDtech

Oct 16, 2026 · Artificial Intelligence

Skill2Env: Auto-Generating Evolving Agent Training Tasks from Skills

Xiaohongshu's AllSpark team introduces Skill2Env, a framework that automatically synthesizes executable agent training environments from existing skills by mapping capability requirements to reusable difficulty patterns, iteratively strengthening tasks based on execution feedback, and generating 1.5K high-quality trajectories that improve a Qwen model across seven agent benchmarks.

DoclingLLM agentsSkill2Env

0 likes · 15 min read

Skill2Env: Auto-Generating Evolving Agent Training Tasks from Skills

Xiaohongshu Tech REDtech

Oct 15, 2026 · Artificial Intelligence

CompoWorld: Compositional Environment Scaling Boosts Agent Performance by 9.17 Points

Xiaohongshu's AllSpark team introduces CompoWorld, a compositional environment scaling framework that combines 448 reusable services with 10,130 tools to train agents on cross-application workflows, achieving a 9.17-point average improvement across eight benchmarks and tripling success rates on AutomationBench.

Agent TrainingAllSparkAutomationBench

0 likes · 12 min read

CompoWorld: Compositional Environment Scaling Boosts Agent Performance by 9.17 Points

Xiaohongshu Tech REDtech

Oct 13, 2026 · Artificial Intelligence

AdaptEvo: From Rule Matching to Evidence-Based Contextual Decisions in AI Agents

Xiaohongshu's AllSpark team and university researchers propose AdaptEvo, a framework combining confidence-adaptive reinforcement learning with evolving decision knowledge to teach AI agents evidence-based contextual decision-making for rule-governed tasks like content moderation, outperforming Gemini 3.8-Flash and GRPO on both current and changed rules.

AdaptEvoAgent learningCA-GRPO

0 likes · 14 min read

AdaptEvo: From Rule Matching to Evidence-Based Contextual Decisions in AI Agents

Xiaohongshu Tech REDtech

Oct 9, 2026 · Backend Development

RED OHC Open-Sourced: New Java Off-Heap Cache SOTA, 3.38x Multi-Threaded Throughput

Xiaohongshu open-sources RED OHC, a Java off-heap cache achieving 3.38x throughput over Cassandra OHC in 32-thread reads via lock-free reads, epoch-based reclamation, background actor for eviction and memory return, and cache-line-aligned data structures, with benchmarks showing near-zero heap allocation and GC.

Cassandra OHCJavaS3-FIFO

0 likes · 25 min read

RED OHC Open-Sourced: New Java Off-Heap Cache SOTA, 3.38x Multi-Threaded Throughput

Xiaohongshu Tech REDtech

Sep 30, 2026 · Backend Development

Xiaohongshu's Agentic Release Harness: Managing Overnight Deployments at Scale

Xiaohongshu engineered a Harness system to manage agent-driven recommendation releases spanning 10+ hours across thousands of pods, using persistent tasks, declarative templates, a reconciliation engine, and effect-verified external actions to reliably execute cross-day deployments with human-in-the-loop governance.

Agentic SystemsHarness²Long-running Tasks

0 likes · 24 min read

Xiaohongshu's Agentic Release Harness: Managing Overnight Deployments at Scale

Xiaohongshu Tech REDtech

Aug 14, 2026 · Artificial Intelligence

dots3-note Preview: A First Step Toward Long‑Term Agents for Real‑World Service

The open‑source dots3-note Preview model, a 280B‑parameter multimodal agent with 512K context, introduces the TEMPO training scheme to improve long‑term reinforcement learning, achieves benchmark gains of up to 31.5% over baselines, and is evaluated on new VibeSearchBench and VibeLifeBench suites while acknowledging current limitations.

Agentic AIOpen Sourcebenchmark

0 likes · 27 min read

dots3-note Preview: A First Step Toward Long‑Term Agents for Real‑World Service

Xiaohongshu Tech REDtech

Aug 13, 2026 · Artificial Intelligence

dots.tts: Open‑Source Continuous Autoregressive TTS Model for Sustainable, Scalable Voice Synthesis

dots.tts is a 2‑billion‑parameter, fully continuous, end‑to‑end autoregressive TTS model released by the Xiaohongshu dots team, offering state‑of‑the‑art zero‑shot voice cloning, low‑step inference, 1‑to‑1 audio‑text streaming, and an extensible training pipeline for research and deployment.

TTSaudio-text streamingautoregressive

0 likes · 22 min read

dots.tts: Open‑Source Continuous Autoregressive TTS Model for Sustainable, Scalable Voice Synthesis

Xiaohongshu Tech REDtech

Aug 7, 2026 · Artificial Intelligence

Can AI Translation Miss Memes? CULTURE‑MT Benchmark at ICML 2026

The authors introduce CULTURE‑MT, the first Chinese‑English social‑media translation benchmark that evaluates cultural effectiveness, define a new metric, release the JUDGER automatic evaluator (86 % accuracy, κ = 0.72), and show that even top models like Gemini 3 pro achieve only 38 % perfect cultural translations.

AI translationbenchmarkcultural evaluation

0 likes · 10 min read

Can AI Translation Miss Memes? CULTURE‑MT Benchmark at ICML 2026

Xiaohongshu Tech REDtech

Aug 5, 2026 · Artificial Intelligence

Accelerating Xiaohongshu ‘Ask’ Inference: Slim Vision Tokens, Focused MoE

The article details how Xiaohongshu’s multimodal “Ask” service reduces visual token bloat and MoE expert compute by applying dynamic Vision Token compression (VisionZip) and similarity‑based expert re‑routing (SERE), achieving up to 13% lower first‑token latency and 16.5% faster end‑to‑end throughput while preserving answer quality.

MoE expert routingQwen modelsSERE

0 likes · 19 min read

Accelerating Xiaohongshu ‘Ask’ Inference: Slim Vision Tokens, Focused MoE

Xiaohongshu Tech REDtech

Jul 28, 2026 · Artificial Intelligence

Vision-OPD Enables Multimodal LLMs to See Fine Details in a Single Forward Pass

Vision-OPD introduces an online self‑distillation framework that lets a 9B multimodal LLM internalize fine‑grained visual evidence from whole images, achieving state‑of‑the‑art results on six detailed visual‑understanding benchmarks without extra inference tools.

Self-DistillationVision-OPDbenchmark

0 likes · 13 min read

Vision-OPD Enables Multimodal LLMs to See Fine Details in a Single Forward Pass