Social-R1: Towards Human-like Social Reasoning in LLMs

• URL: http://arxiv.org/abs/2603.09249v1
• Date: Tue, 10 Mar 2026 06:26:24 GMT
• Title: Social-R1: Towards Human-like Social Reasoning in LLMs
• Abstract summary: We argue that cultivating human-like social intelligence requires training with challenging cases that resist shortcut solutions.<n>We propose Social-R1, a reinforcement learning framework that aligns model reasoning with human cognition through multi-dimensional rewards.
• Score: 74.32494331695837
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While large language models demonstrate remarkable capabilities across numerous domains, social intelligence - the capacity to perceive social cues, infer mental states, and generate appropriate responses - remains a critical challenge, particularly for enabling effective human-AI collaboration and developing AI that truly serves human needs. Current models often rely on superficial patterns rather than genuine social reasoning. We argue that cultivating human-like social intelligence requires training with challenging cases that resist shortcut solutions. To this end, we introduce ToMBench-Hard, an adversarial benchmark designed to provide hard training examples for social reasoning. Building on this, we propose Social-R1, a reinforcement learning framework that aligns model reasoning with human cognition through multi-dimensional rewards. Unlike outcome-based RL, Social-R1 supervises the entire reasoning process, enforcing structural alignment, logical integrity, and information density. Results show that our approach enables a 4B parameter model to surpass much larger counterparts and generalize robustly across eight diverse benchmarks. These findings demonstrate that challenging training cases with trajectory-level alignment offer a path toward efficient and reliable social intelligence.

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)
• One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence [25.89075578734277]
  This paper introduces OMAR: One Model, All Roles, a reinforcement learning framework for AI.<n>OMAR allows a single model to role-play all participants in a conversation simultaneously, learning to achieve long-term goals and complex social norms.<n>We show that trained models develop fine-grained, emergent social intelligence, such as empathy, persuasion, and compromise seeking.
  arXiv  Detail & Related papers  (2026-02-03T05:09:49Z)
• MARO: Learning Stronger Reasoning from Social Interaction [7.77506109184819]
  Multi-Agent Reward Optimization (MARO) is a method that enables large language models to acquire stronger reasoning abilities.<n> Experimental results demonstrate that MARO achieves significant improvements in social reasoning capabilities.
  arXiv  Detail & Related papers  (2026-01-18T09:10:08Z)
• SocialNLI: A Dialogue-Centric Social Inference Dataset [49.60157928163403]
  We introduce SocialNLI -- the first social dialogue inference dataset.<n>SocialNLI consists of a collection of dialogue transcripts hand-picked to center complex social nuances.<n>We evaluate reasoning models theory-of-mind ability through multi-step counterfactual reasoning.
  arXiv  Detail & Related papers  (2025-10-06T23:42:01Z)
• Sotopia-RL: Reward Design for Social Intelligence [52.59432715228559]
  Sotopia-RL is a novel framework that refines coarse episode-level feedback into utterance-level, multi-dimensional rewards.<n>Experiments in Sotopia, an open-ended social learning environment, demonstrate that Sotopia-RL achieves state-of-the-art social goal completion scores.
  arXiv  Detail & Related papers  (2025-08-05T20:43:42Z)
• Social Genome: Grounded Social Reasoning Abilities of Multimodal Models [61.88413918026431]
  Social reasoning abilities are crucial for AI systems to interpret and respond to multimodal human communication and interaction within social contexts.<n>We introduce SOCIAL GENOME, the first benchmark for fine-grained, grounded social reasoning abilities of multimodal models.
  arXiv  Detail & Related papers  (2025-02-21T00:05:40Z)
• 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)
• Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMs [77.88043871260466]
  We show that one of today's largest language models lacks this kind of social intelligence out-of-the box. We conclude that person-centric NLP approaches might be more effective towards neural Theory of Mind.
  arXiv  Detail & Related papers  (2022-10-24T14:58:58Z)

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.