DREAM Technical Report

• URL: http://arxiv.org/abs/2608.09408v3
• Date: Thu, 13 Aug 2026 13:55:36 GMT
• Title: DREAM Technical Report
• Abstract summary: We present DREAM, an autonomous optimization control architecture that adds a perception-aware, orchestrable, and auditable policy layer atop existing pipelines without replacing them.<n> DREAM has two core components. First, a three-tier Intent Engine fuses on-device signals into structured L0/L1/L2 intent representations; its edge-cloud trigger chain reduces reporting volume to approximately 8.7%.<n>Second, a Meta Engine uses a MetaModel for layered M1-to-M2-to-M3 reasoning: intent summarization, strategy planning informed by Strategy Memory, and parameter translation. It dispatches the resulting parameters through a unified outlet with
• Score: 53.37525197047151
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Industrial recommender systems commonly use cascaded retrieval, ranking, and re-ranking pipelines. Although efficient, these pipelines fragment information and objectives across modules, rely on rigid rules, and have limited awareness of real-time intent, leaving session-level shifts among browsing, comparison, and purchase insufficiently addressed. We present DREAM (Developing Recommender Engine with Agentic Methods), an autonomous optimization control architecture that adds a perception-aware, orchestrable, and auditable policy layer atop existing pipelines without replacing them. DREAM has two core components. First, a three-tier Intent Engine fuses on-device signals into structured L0/L1/L2 intent representations; its edge-cloud trigger chain reduces reporting volume to approximately 8.7%. Second, a Meta Engine uses a MetaModel for layered M1-to-M2-to-M3 reasoning: intent summarization, strategy planning informed by Strategy Memory, and parameter translation. It dispatches the resulting parameters through a unified outlet with safety guardrails. A Reward Dual Loop continuously optimizes both components by combining offline simulation for strategy-space exploration with online feedback for outcome calibration, forming a cycle of generation, execution, evaluation, and experience accumulation. Large-scale A/B tests on Taobao's homepage feed show that re-ranking control alone improves IPV by 2.06%, Core IPV by 2.39%, and GMV by 0.88%. Extending control to fine ranking raises these gains to 2.71%, 3.06%, and 1.31%, respectively, while consistently improving PV by more than 1%. These gains require neither replacement of pipeline models nor compromise of serving stability, supporting agentic meta-control as a viable paradigm for industrial recommendation.

Related papers

• A Deployment-Oriented and Resource-Efficient Neuro-Symbolic Framework for Explainable DDoS Detection in Operational Technology Networks [1.202468381202799]
  This paper presents a neuro-symbolic framework specifically designed for robust DDoS detection in resource-constrained environments.<n>The framework fuses a gated recurrent unit (GRU) neural network with a shallow decision tree as a symbolic component.<n>The hybrid model is evaluated on three real-world benchmark DDoS datasets.
  arXiv  Detail & Related papers  (2026-08-17T16:18:15Z)
• MGSB: Manifold Gated Signature Branch Pressure-Domain Baseline Architecture for Two-Phase Pipeline Flows Under Distributional Shift [0.0]
  Leak detection models for multiphase pipelines often degrade when deployed under flow regimes that differ from training.<n>We propose a regime-aware architecture combining regime-conditioned feature fusion, a TT-RoughPath encoder, and Mean-Teacher consistency regularization to improve robustness under distribution shift.<n>Under leave-one-group-out evaluation, MGSB achieves a detection F1 of 0.930 and an OOD F1 of 0.783, substantially outperforming CNN-LSTM and fully connected baselines.
  arXiv  Detail & Related papers  (2026-08-05T13:12:03Z)
• GR2 Technical Report [58.300302585605095]
  GR2 is an end-to-end framework that combines mid-training on semantic IDs with reasoning-trace distilled from a stronger teacher.<n> GR2 delivers +18.7% R@1, +7.1% R@3, and +9.6% N@3 over legacy baselines on industrial-scale traffic.
  arXiv  Detail & Related papers  (2026-06-30T17:22:22Z)
• TriSP: Tri-Signal Structured Pruning for Large Language Models [0.0]
  Large language models (LLMs) achieve strong performance across diverse tasks but their deployment is constrained by the memory and compute cost of their parameters.<n> Structured pruning addresses this by removing entire structures such as attention heads and Multi-Layer Perceptron (MLP) neurons to produce smaller dense models that run efficiently on standard hardware.<n>We propose TriSP (Tri-Signal Structured Pruning), an importance metric that combines weight magnitude scaled by activation norm with first-order gradient sensitivity via a geometric mean.
  arXiv  Detail & Related papers  (2026-06-09T17:02:14Z)
• LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval [10.896685094390136]
  Multi-stage retrieval systems underpin modern AI applications -- spanning visual search, recommendation engines, and multi-modal question answering.<n>We address this limitation with a phase-aware large language model (LLM) agent that navigates the coupled parameter space across phase-ed exploration, exploitation, and fine-tuning stages.
  arXiv  Detail & Related papers  (2026-06-03T22:28:34Z)
• GIRL: Generative Imagination Reinforcement Learning via Information-Theoretic Hallucination Control [0.0]
  We introduce GIRL (Generative Imagination Reinforcement Learning), a latent world-model framework that addresses this failure mode with two key components.<n> GIRL reduces latent rollout drift by 38 to 61 percent across tasks relative to DreamerV3, improves return, and requires fewer environment interactions on long-horizon tasks.<n>A distilled-prior variant reduces overhead and improves computational efficiency relative to the full model.
  arXiv  Detail & Related papers  (2026-04-08T17:14:21Z)
• REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge [83.2858110368572]
  We propose textbfREAL (underlineREgression-underlineAware Reinforcement underlineLThought), a principled RL framework designed to optimize regression rewards.<n>We show that REAL consistently outperforms both regression-aware SFT baselines and standard RL methods.
  arXiv  Detail & Related papers  (2026-03-17T21:19:08Z)
• MiniOneRec: An Open-Source Framework for Scaling Generative Recommendation [44.05859062614669]
  MiniOneRec is the first fully open-source generative recommendation framework.<n>It provides an end-to-end workflow spanning SID construction, supervised fine-tuning, and recommendation-oriented reinforcement learning.<n>Our experiments reveal a consistent downward trend in both training and evaluation losses with increasing model size.
  arXiv  Detail & Related papers  (2025-10-28T13:58:36Z)
• MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources [113.33902847941941]
  Variance-Aware Sampling (VAS) is a data selection strategy guided by Variance Promotion Score (VPS)<n>We release large-scale, carefully curated resources containing 1.6M long CoT cold-start data and 15k RL QA pairs.<n> Experiments across mathematical reasoning benchmarks demonstrate the effectiveness of both the curated data and the proposed VAS.
  arXiv  Detail & Related papers  (2025-09-25T14:58:29Z)
• OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System [61.12400636463362]
  OnePiece is a unified framework that seamlessly integrates LLM-style context engineering and reasoning into both retrieval and ranking models.<n>OnePiece has been deployed in the main personalized search scenario of Shopee and achieves consistent online gains across different key business metrics.
  arXiv  Detail & Related papers  (2025-09-22T17:59:07Z)
• Reinforced Model Merging [53.84354455400038]
  We present an innovative framework termed Reinforced Model Merging (RMM), which encompasses an environment and agent tailored for merging tasks.<n>By utilizing data subsets during the evaluation process, we addressed the bottleneck in the reward feedback phase, thereby accelerating RMM by up to 100 times.
  arXiv  Detail & Related papers  (2025-03-27T08:52:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.