Paper Detail

Learning to Reason with Predictive Gains for Generative Recommendation

Zhuoyang Li, Teng Shi, Jiakai Tang, Weijie Yu, Guofu Xie, Xiao Zhang, Lei Kou, Yang Yu, Lei Shen, Xin Chen, Bing Wang, Xiaoyi Zeng, Jun Xu

arxiv Score 15.3

Published 2026-11-16 · First seen 2026-11-17

General AI

Abstract

Reasoning-enhanced generative recommendation (GR) has attracted increasing attention for leveraging the reasoning capabilities of large language models (LLMs) to improve next-item prediction. However, existing methods primarily optimize reasoning through Group Relative Policy Optimization (GRPO) with rule-based rewards determined by final recommendation performance, which faces two key limitations: (i) unmeasured predictive contributions within reasoning, where the predictive contributions of individual reasoning steps are not directly reflected in optimization signals, and (ii) weakly discriminative learning signals within groups, where different reasoning trajectories within the group often receive indistinguishable rewards, limiting effective policy optimization. In this paper, we propose GainReason, a simple yet effective training framework that optimizes reasoning through Predictive Gain (PG). Specifically, PG measures changes in target Semantic ID (SID) log-likelihood induced by individual reasoning sentences, providing contribution-aware and discriminative rewards. We further theoretically establish the alignment between expected PG and the recommendation ranking objective. Building on this signal, we develop PG-based Reasoning Optimization (PGRO) to optimize reasoning generation with sentence-level rewards, supported by a custom causal attention mechanism for efficient PG computation. Additionally, an auxiliary PG-based Reasoning Utilization (PGRU) task adaptively strengthens reasoning-conditioned prediction to complement PGRO. Extensive experiments on three public benchmarks demonstrate that GainReason consistently outperforms competitive baselines and achieves substantial performance gains from reasoning.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{li2026learning,
  title = {Learning to Reason with Predictive Gains for Generative Recommendation},
  author = {Zhuoyang Li and Teng Shi and Jiakai Tang and Weijie Yu and Guofu Xie and Xiao Zhang and Lei Kou and Yang Yu and Lei Shen and Xin Chen and Bing Wang and Xiaoyi Zeng and Jun Xu},
  year = {2026},
  abstract = {Reasoning-enhanced generative recommendation (GR) has attracted increasing attention for leveraging the reasoning capabilities of large language models (LLMs) to improve next-item prediction. However, existing methods primarily optimize reasoning through Group Relative Policy Optimization (GRPO) with rule-based rewards determined by final recommendation performance, which faces two key limitations: (i) unmeasured predictive contributions within reasoning, where the predictive contributions of in},
  url = {https://arxiv.org/abs/2611.21441},
  keywords = {cs.AI},
  eprint = {2611.21441},
  archiveprefix = {arXiv},
}

Metadata

{}