Pith. sign in

REVIEW 6 cited by

Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.05069 v2 pith:KR43MMWC submitted 2025-06-05 cs.IR cs.AI

Reason-to-Recommend: Using Interaction-of-Thought Reasoning to Enhance LLM Recommendation

classification cs.IR cs.AI
keywords reasoningrecommendationtextbfchainscodeenhanceexplicitimplicit
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Driven by advances in Large Language Models (LLMs), integrating them into recommendation tasks has gained interest due to their strong semantic understanding and prompt flexibility. Prior work encoded user-item interactions or metadata into prompts for recommendations. In parallel, LLM reasoning, boosted by test-time scaling and reinforcement learning, has excelled in fields like mathematics and code, where reasoning traces and correctness signals are clear, enabling high performance and interpretability. However, directly applying these reasoning methods to recommendation is ineffective because user feedback is implicit and lacks reasoning supervision. To address this, we propose $\textbf{R2Rec}$, a reasoning-enhanced recommendation framework that samples interaction chains from the user-item graph and converts them into structured interaction-of-thoughts via a progressive masked prompting strategy, with each thought representing stepwise reasoning grounded in interaction context. This allows LLMs to simulate step-by-step decision-making based on implicit patterns. We design a two-stage training pipeline: supervised fine-tuning teaches basic reasoning from high-quality traces, and reinforcement learning refines reasoning via reward signals, alleviating sparse explicit supervision. Experiments on three real-world datasets show R2Rec outperforms classical and LLM-based baselines with an average $\textbf{10.48%}$ improvement in HitRatio@1 and $\textbf{131.81%}$ gain over the original LLM. Furthermore, the explicit reasoning chains enhance interpretability by revealing the decision process. Our code is available at: https://anonymous.4open.science/r/R2Rec-7C5D.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Uncovering the Representation Geometry of Minimal Cores in Overcomplete Reasoning Traces

    cs.AI 2026-05 unverdicted novelty 7.0

    Language models produce overcomplete reasoning traces where on average 46% of steps can be removed while preserving the answer in 86% of cases, with necessity concentrated in the top three steps.

  2. User Simulator-Guided Multi-Turn Preference Optimization for Reasoning LLM-based Conversational Recommendation

    cs.IR 2026-04 unverdicted novelty 7.0

    SMTPO uses multi-task SFT to improve simulator feedback quality and RL with fine-grained rewards to optimize multi-turn preference reasoning in LLM-based conversational recommendation.

  3. From Understanding to Action: Feedback-Grounded Policy Discovery for Generative Recommendation

    cs.IR 2026-07 conditional novelty 6.0

    A feedback-grounded framework discovers recommendation policies by their measured advantage over intent-only baselines and distills them into two latent tokens of a lightweight Semantic-ID recommender.

  4. Factorized Latent Reasoning for LLM-based Recommendation

    cs.IR 2026-04 unverdicted novelty 6.0

    FLR factorizes latent reasoning into multiple preference factors using multi-factor attention and regularizations, outperforming baselines on recommendation benchmarks while adding robustness and interpretability.

  5. A Survey on Generative Recommendation: Data, Model, and Tasks

    cs.IR 2025-10 accept novelty 6.0

    This survey organizes generative recommendation into data, model, and task dimensions, identifying five advantages including world knowledge integration and creative generation while noting challenges in benchmarks an...

  6. Think2Go: Generative Next POI Recommendation with LLM Reasoning

    cs.IR 2026-07 conditional novelty 4.0

    Think2Go couples SFT and RL-based reasoning in one LLM, with KDE- and reward-gap-based advantage calibration, and reports state-of-the-art Acc@1 on NYC, Tokyo, and California check-in data.