SAGER: Self-Evolving User Policy Skills for Recommendation Agent

TL;DR

SAGER introduces personalized, evolving reasoning policies for recommendation agents, enabling continuous improvement in decision-making by individual users through structured natural-language skills.

Contribution

It proposes a novel framework where each user has a dedicated, evolving policy skill that enhances reasoning and personalization in recommendation systems.

Findings

SAGER achieves state-of-the-art performance on four benchmarks.

Personalized reasoning skills improve recommendation accuracy independently of memory updates.

The framework effectively diagnoses and corrects reasoning flaws through contrastive analysis.

Abstract

Large language model (LLM) based recommendation agents personalize what they know through evolving per-user semantic memory, yet how they reason remains a universal, static system prompt shared identically across all users. This asymmetry is a fundamental bottleneck: when a recommendation fails, the agent updates its memory of user preferences but never interrogates the decision logic that produced the failure, leaving its reasoning process structurally unchanged regardless of how many mistakes it accumulates. To address this bottleneck, we propose SAGER (Self-Evolving Agent for Personalized Recommendation), the first recommendation agent framework in which each user is equipped with a dedicated policy skill, a structured natural-language document encoding personalized decision principles that evolves continuously through interaction. SAGER introduces a two-representation skill architecture that decouples a rich evolution substrate from a minimal inference-time injection, an incremental contrastive chain-of-thought engine that diagnoses reasoning flaws by contrasting accepted against unchosen items while preserving accumulated priors, and skill-augmented listwise reasoning that creates fine-grained decision boundaries where the evolved skill provides genuine discriminative value. Experiments on four public benchmarks demonstrate that SAGER achieves state-of-the-art performance, with gains orthogonal to memory accumulation, confirming that personalizing the reasoning process itself is a qualitatively distinct source of recommendation improvement.