SAVOIR: Learning Social Savoir-Faire via Shapley-based Reward Attribution

arXiv:2604.18982 · cs.AI · Submitted 2026-04-21 · Read on arXiv

cs.AI

Submitted: 2026-04-21

Updated: 2026-11-09

Comments: ACL 2026 Findings

License: http://creativecommons.org/licenses/by/4.0/

The gist: Social intelligence, the ability to navigate complex interpersonal interactions, presents a fundamental challenge for language agents.

Terminology

Abstract

Social intelligence, the ability to navigate complex interpersonal interactions, presents a fundamental challenge for language agents. Training such agents via reinforcement learning requires solving the credit assignment problem: determining how individual utterances contribute to multi-turn dialogue outcomes. Existing approaches directly employ language models to distribute episode-level rewards, yielding attributions that are retrospective and lack theoretical grounding. We propose SAVOIR (ShApley Value fOr SocIal RL), a novel principled framework grounded in cooperative game theory. Our approach combines two complementary principles: expected utility shifts evaluation from retrospective attribution to prospective valuation, capturing an utterance's strategic potential for enabling favorable future trajectories; Shapley values ensure fair credit distribution with axiomatic guarantees of efficiency, symmetry, and marginality. Experiments on the SOTOPIA benchmark demonstrate that SAVOIR achieves new state-of-the-art performance across all evaluation settings, with our 7B model matching or exceeding proprietary models including GPT-4o and Claude-3.5-Sonnet. Notably, even large reasoning models consistently underperform, suggesting social intelligence requires qualitatively different capabilities than analytical reasoning.

Sources

Related papers