ASARL: Autonomous Social-Aware Relevance Learning for QQ Search

• URL: http://arxiv.org/abs/2607.26593v1
• Date: Wed, 29 Jul 2026 08:14:00 GMT
• Title: ASARL: Autonomous Social-Aware Relevance Learning for QQ Search
• Abstract summary: We propose a fully automated framework that integrates multi-agent data curation with staged model training.<n>We show significant improvements in both offline relevance metrics and online user engagement indicators.<n>These results validate the effectiveness of combining autonomous, socially grounded data governance with preference-aligned training in practical search systems.
• Score: 10.185075952030294
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid growth of online social platforms has transformed communication and information retrieval, giving rise to social search, where queries-titles are typically expressed in informal, community-specific language. While large language models provide strong general-purpose semantic understanding, their effectiveness in social search is constrained by contextual discrepancy, data scarcity, and behavior-driven dynamics. To address these challenges, we propose the Autonomous Social-Aware Relevance Learning (ASARL), a fully automated framework that integrates multi-agent data curation with staged model training. ASARL leverages a collaborative agent system: ReasonAgent generates interpretable relevance labels grounded in social attributes, CriticAgent validates and ensures logical consistency, and GenAgent augments long-tail data through synthetic query-title pairs. Building on the curated dataset, ASARL employs three-stage training: Social Context Training (SCT) to capture social language patterns, Preference-Guided Optimization (PGO) to align model predictions with behavioral signals, and Social Distillation (SD) to transfer these improvements into compact models for efficient deployment. Extensive offline and online experiments on the QQ search platform demonstrate significant improvements in both offline relevance metrics and online user engagement indicators, along with enhanced annotation efficiency. These results validate the effectiveness of combining autonomous, socially grounded data governance with preference-aligned training in practical search systems.

Related papers

• ALSO: Adversarial Online Strategy Optimization for Social Agents [63.84788516416339]
  We propose textbfALSO (textbfAdrial ontextbfLine textbfStrategy textbfOptimization) as the first framework for online strategy optimization in social simulation.<n> ALSO formulates multi-turn interaction as an adversarial bandit problem, where combinations of static personas and dynamic strategy instructions are treated as arms.<n>Also introduces a lightweight neural surrogate to predict rewards from interaction histories, enabling sample-efficient exploration and continuous online adaptation.
  arXiv  Detail & Related papers  (2026-05-15T09:25:15Z)
• CHORUS: An Agentic Framework for Generating Realistic Deliberation Data [0.0]
  Chorus is an agentic framework that orchestrates actors with behaviorally consistent personas to generate realistic deliberation discussions.<n>The framework was deployed on the textscDeliberate platform and evaluated by 30 expert participants across three dimensions.
  arXiv  Detail & Related papers  (2026-04-22T15:01:02Z)
• FedRio: Personalized Federated Social Bot Detection via Cooperative Reinforced Contrastive Adversarial Distillation [52.56850762009136]
  Social bot detection is critical to the stability and security of online social platforms.<n>Current state-of-the-art bot detection models are largely developed in isolation.<n>We propose FedRio as a cross-platform and cross-model detection framework.
  arXiv  Detail & Related papers  (2026-04-12T15:13:41Z)
• Using Large Language Models to Detect Socially Shared Regulation of Collaborative Learning [15.567266973412815]
  We extend predictive models to automatically detect socially shared regulation of learning behaviors using embedding-based approaches.<n>We leverage large language models (LLMs) as summarization tools to generate task-aware representations of student dialogue aligned with system logs.<n>Results show that text-only embeddings often achieve stronger performance in detecting SSRL behaviors related to enactment or group dynamics.
  arXiv  Detail & Related papers  (2026-01-08T00:30:46Z)
• Linking Heterogeneous Data with Coordinated Agent Flows for Social Media Analysis [24.70488591952602]
  Social media platforms generate massive volumes of heterogeneous data.<n>We present SIA (Social Insight Agents), an agent system that links heterogeneous multi-modal data.<n>We show that SIA effectively discovers diverse and meaningful insights from social media.
  arXiv  Detail & Related papers  (2025-10-30T06:22:49Z)
• ReGUIDE: Data Efficient GUI Grounding via Spatial Reasoning and Search [53.40810298627443]
  ReGUIDE is a framework for web grounding that enables MLLMs to learn data efficiently through self-generated reasoning and spatial-aware criticism.<n>Our experiments demonstrate that ReGUIDE significantly advances web grounding performance across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-05-21T08:36:18Z)
• Sentiment analysis of texts from social networks based on machine learning methods for monitoring public sentiment [0.0]
  A sentiment analysis system powered by machine learning was created in this study to improve real-time social network public opinion monitoring.<n>The system achieved an accuracy of up to 80-85% using transformer models in real-world scenarios.<n>Despite the system's impressive performance, issues with computing overhead, data quality, and domain-specific terminology still exist.
  arXiv  Detail & Related papers  (2025-02-24T13:34:35Z)
• QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search [89.97082652805904]
  We propose QLASS (Q-guided Language Agent Stepwise Search), to automatically generate annotations by estimating Q-values.<n>With the stepwise guidance, we propose a Q-guided generation strategy to enable language agents to better adapt to long-term value.<n>We empirically demonstrate that QLASS can lead to more effective decision making through qualitative analysis.
  arXiv  Detail & Related papers  (2025-02-04T18:58:31Z)
• Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments [33.83610929282721]
  Learn-by-interact is a data-centric framework to adapt large language models (LLMs) to any given environments without human annotations.<n>We assess the quality of our synthetic data by using them in both training-based scenarios and training-free in-context learning (ICL)<n>Experiments on SWE-bench, WebArena, OSWorld and Spider2-V spanning across realistic coding, web, and desktop environments show the effectiveness of Learn-by-interact.
  arXiv  Detail & Related papers  (2025-01-18T22:34:41Z)
• DialogAgent: An Auto-engagement Agent for Code Question Answering Data Production [5.030384831047144]
  We present DialogAgent, an automated tool for generating synthetic training data that closely mimics real developer interactions.<n>The tool significantly reduces the reliance on manual data generation, increasing efficiency by 4.8 times compared to traditional methods.
  arXiv  Detail & Related papers  (2024-12-11T03:31:36Z)
• Multi-Agent Dynamic Relational Reasoning for Social Robot Navigation [50.01551945190676]
  Social robot navigation can be helpful in various contexts of daily life but requires safe human-robot interactions and efficient trajectory planning. We propose a systematic relational reasoning approach with explicit inference of the underlying dynamically evolving relational structures. We demonstrate its effectiveness for multi-agent trajectory prediction and social robot navigation.
  arXiv  Detail & Related papers  (2024-01-22T18:58:22Z)
• Training Socially Aligned Language Models on Simulated Social Interactions [99.39979111807388]
  Social alignment in AI systems aims to ensure that these models behave according to established societal values. Current language models (LMs) are trained to rigidly replicate their training corpus in isolation. This work presents a novel training paradigm that permits LMs to learn from simulated social interactions.
  arXiv  Detail & Related papers  (2023-05-26T14:17:36Z)

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.