Social World Model for Lifelong Social Intelligence

• URL: http://arxiv.org/abs/2606.21315v1
• Date: Fri, 19 Jun 2026 10:55:30 GMT
• Title: Social World Model for Lifelong Social Intelligence
• Abstract summary: Social intelligence is a core competency for language agents.<n>Currently, two methodological pain points exist: social interaction trajectories lack unified structured representations to form iterable learning signals.<n>We propose the Social World Model to build a closed-loop learning framework.
• Score: 5.7991979365088815
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Social intelligence is a core competency for language agents, yet current research primarily focuses on static capability evaluation rather than how these skills are continuously shaped and accumulated. This gap calls for a shift toward sustainable learning paradigms. Currently, two methodological pain points exist: social interaction trajectories lack unified structured representations to form iterable learning signals, and capability improvement and retention are typically studied in isolation, hindering the assessment of continuous evolution. To bridge this gap, we propose the Social World Model. We decompose social interaction into five dimensions (scene setting, observation, mental state, action, and dialogue) to build a closed-loop learning framework. In this setup, agents collect interaction experiences, convert them into preference signals for model updating, and redeploy the updated policy for continued learning. Additionally, we provide a reusable data synthesis mechanism and a lifelong learning benchmark, transforming social capabilities from an "object of evaluation" into an "object of sustainable training". Validating our framework on the ASCENT-Bench, the interactively trained Qwen2.5-7B model outperforms its baseline across all five core metrics. Notably, it matches the closed-source Gemini 3 Flash in completion rate, exceeds it in pass rate, and achieves zero forgetting across three difficulty levels. Unlike prior works that merely report static comparisons or capability decay, this end-to-end approach provides a trainable, verifiable, and retainable pathway, demonstrating that small open-source models can sustainably acquire competitive social coordination capabilities.

Related papers

• SocialRL: Refining LLMs' Social Intelligence through Multi-turn Reinforcement Learning and Reward Design [52.69818441707104]
  Social intelligence enables agents to read social context, infer intent, and adapt over sustained dialogue.<n>Existing reinforcement learning methods optimize single-turn utterances and sparse outcome rewards.<n>We propose SocialRL, a multi-turn reinforcement learning framework addressing both challenges.
  arXiv  Detail & Related papers  (2026-09-09T06:06:34Z)
• Trajectory Learning with Graph Representations for Social Robot Navigation [1.0732935873226022]
  We propose an imitation learning framework that leverages social dynamics for socially compliant navigation.<n>We present a navigation module that captures temporal dynamics and mitigates error accumulations.<n>Our framework outperforms established data-driven baselines on simulation and a real-world dataset across diverse social metrics.
  arXiv  Detail & Related papers  (2026-06-21T23:57:54Z)
• Social-Mamba: Socially-Aware Trajectory Forecasting with State-Space Models [81.44955493339835]
  Social-Mamba is a forecasting architecture that reformulates social interactions as structured sequential processes.<n>Social-Mamba organizes agents on an egocentric grid and introduces social triplet factorization.<n>Experiments on five trajectory forecasting benchmarks show that Social-Mamba achieves state-of-the-art accuracy.
  arXiv  Detail & Related papers  (2026-05-14T21:16:01Z)
• SAVOIR: Learning Social Savoir-Faire via Shapley-based Reward Attribution [82.31558282651811]
  Social intelligence, the ability to navigate complex interpersonal interactions, presents a fundamental challenge for language agents.<n>Existing approaches directly employ language models to distribute episode-level rewards, yielding attributions that are retrospective and lack theoretical grounding.<n>We propose SAVOIR, a novel principled framework grounded in cooperative game theory.
  arXiv  Detail & Related papers  (2026-04-21T02:08:25Z)
• SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models [86.19617358080016]
  Social Omni is a benchmark that operationalizes the evaluation of conversational interactivity across three core dimensions.<n>Social Omni features 2,000 perception samples and a quality-controlled diagnostic set of 209 interaction-generation instances.<n>Our analysis reveals a pronounced decoupling between a model's perceptual accuracy and its ability to generate contextually appropriate interruptions.
  arXiv  Detail & Related papers  (2026-03-17T17:58:44Z)
• EduVerse: A User-Defined Multi-Agent Simulation Space for Education Scenario [17.971148824199187]
  We present EduVerse, the first user-defined multi-agent simulation space that supports environment, agent, and session customization.<n>We validate EduVerse in middle-school Chinese classes across three text genres, environments, and multiple sessions.
  arXiv  Detail & Related papers  (2025-10-07T07:58:32Z)
• SocialMaze: A Benchmark for Evaluating Social Reasoning in Large Language Models [41.68365456601248]
  We introduce SocialMaze, a new benchmark specifically designed to evaluate social reasoning.<n>SocialMaze systematically incorporates three core challenges: deep reasoning, dynamic interaction, and information uncertainty.<n>It provides six diverse tasks across three key settings: social reasoning games, daily-life interactions, and digital community platforms.
  arXiv  Detail & Related papers  (2025-05-29T17:47:36Z)
• Reinforced Interactive Continual Learning via Real-time Noisy Human Feedback [59.768119380109084]
  This paper introduces an interactive continual learning paradigm where AI models dynamically learn new skills from real-time human feedback.<n>We propose RiCL, a Reinforced interactive Continual Learning framework leveraging Large Language Models (LLMs)<n>Our RiCL approach substantially outperforms existing combinations of state-of-the-art online continual learning and noisy-label learning methods.
  arXiv  Detail & Related papers  (2025-05-15T03:22:03Z)
• Neural Networks Remember More: The Power of Parameter Isolation and Combination [3.2430260063115233]
  Catastrophic forgetting is a pervasive issue for pre-trained language models.<n>Key to solving this problem is to find a trade-off between the plasticity and stability of the model.<n>We propose a novel method to achieve a balance between model stability and plasticity.
  arXiv  Detail & Related papers  (2025-02-16T02:58:57Z)
• 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)
• Time Will Change Things: An Empirical Study on Dynamic Language Understanding in Social Media Classification [5.075802830306718]
  We empirically study social media NLU in a dynamic setup, where models are trained on the past data and test on the future. We show that auto-encoding and pseudo-labeling collaboratively show the best robustness in dynamicity.
  arXiv  Detail & Related papers  (2022-10-06T12:18:28Z)

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.