Paper Citation Record · LEDGER

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1

As of 7 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 3 inbound Pith citation observations for arXiv:2506.19235.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2506.19235 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:12:33.875901Z

measured 42 of 42 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-07-31T15:16:36.284072Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-01T17:25:51.272020Z

Reference resolution

39 of 39 outbound references displayed

verified exact0
verified fuzzy11
unresolved28
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 97ae766d-9af7-486d-8c84-23a3e1a74090 · outbound

This paper cites GPT-4 Technical Report.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:30.692673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34b0f6be-4581-4066-aff6-85c6a3977597 · outbound

This paper cites Reinforcement learning based recommender systems: A survey.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Reinforcement learning based recommender systems: A survey

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:30.725331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 130a9e2c-3b63-4d38-9bf0-4fa19e436d94 · outbound

This paper cites Language models are few-shot learners.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Language models are few-shot learners

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:30.805607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e760fceb-6a17-4112-99ae-838258a2de64 · outbound

This paper cites Twin: Two-stage interest network for lifelong user behavior modeling in ctr prediction at kuaishou.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Twin: Two-stage interest network for lifelong user behavior modeling in ctr prediction at kuaishou

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:12:35.662028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation eed36b7d-a357-4938-98a8-6bf3c507493d · outbound

This paper cites Wide & deep learning for recommender systems.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Wide & deep learning for recommender systems

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:12:35.608732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 24ee761f-9be1-44eb-8546-972628a2ca31 · outbound

This paper cites Deep neural networks for youtube recommenda- tions.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Deep neural networks for youtube recommenda- tions

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:12:35.408453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7a2d09e1-dc40-4535-8cb9-a20d9ac91fbd · outbound

This paper cites Flashattention: Fast and memory-efficient exact attention with io-awareness.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Flashattention: Fast and memory-efficient exact attention with io-awareness

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:31.185452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc6abfcb-890a-4e8f-927e-4da5563e87b3 · outbound

This paper cites Bert: Pre-training of deep bidirectional transformers for language understanding.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Bert: Pre-training of deep bidirectional transformers for language understanding

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:31.298128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c42f9214-9bfe-4dbc-8201-f17b69056f76 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:31.465019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28801878-da4f-4c7c-8d31-ec04558d3def · outbound

This paper cites DeepFM: A Factorization-Machine based Neural Network for CTR Prediction.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 DeepFM: A Factorization-Machine based Neural Network for CTR Prediction

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:31.633989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2c7126d-f7b1-45eb-ae0a-6b06c28c8506 · outbound

This paper cites Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:31.742209Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea9f42bd-c89a-4cf1-b46f-25804ee9904f · outbound

This paper cites Neural collaborative filtering.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Neural collaborative filtering

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:31.831740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c2f5c2d-7d15-4d33-8493-b03ab0e29e96 · outbound

This paper cites Session-based Recommendations with Recurrent Neural Networks.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Session-based Recommendations with Recurrent Neural Networks

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:31.924775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b11b211-b806-45c7-a53d-dc24d565891f · outbound

This paper cites Factual and Personalized Recommendations using Language Models and Reinforcement Learning.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Factual and Personalized Recommendations using Language Models and Reinforcement Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:32.008803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e9e8c6e-888d-46b0-ae30-8a298d9a3f66 · outbound

This paper cites Genrec: Large language model for generative recommendation.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Genrec: Large language model for generative recommendation

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:12:35.268155Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9f4f6a9e-d85c-4ac2-b6ca-0cb54f9f9c80 · outbound

This paper cites Self-attentive sequential recommendation.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Self-attentive sequential recommendation

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:32.145328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 378042bc-9a5b-426e-ad55-61dc63f23aad · outbound

This paper cites Matrix factorization techniques for recom- mender systems.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Matrix factorization techniques for recom- mender systems

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:32.213858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3898939a-803c-4bef-b330-1e6d4fa7d26b · outbound

This paper cites GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 GPT4Rec: A Generative Framework for Personalized Recommendation and User Interests Interpretation

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:32.288506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9daa28f9-c4e3-4621-b328-396bd34e7994 · outbound

This paper cites Llara: Large language-recommendation assistant.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Llara: Large language-recommendation assistant

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:12:35.153438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ef15a54c-ffdd-406b-b832-fa79fd60956a · outbound

This paper cites Cascade ranking for operational e-commerce search.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Cascade ranking for operational e-commerce search

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:12:35.087673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ffb7c52d-7b33-4c9f-a3e8-666fd7c90c46 · outbound

This paper cites Integrating large language models into recommendation via mutual augmentation and adaptive aggregation.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Integrating large language models into recommendation via mutual augmentation and adaptive aggregation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:32.519992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f047dc14-655c-4a39-ac5f-a4da5245144b · outbound

This paper cites Human-level control through deep reinforcement learning.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Human-level control through deep reinforcement learning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:32.644503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d034671-8f2e-45a7-81f1-49609fe7a2db · outbound

This paper cites Training language models to follow instructions with human feedback.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Training language models to follow instructions with human feedback

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:32.713350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdef5190-5935-4a90-a143-b96c92849146 · outbound

This paper cites Large language model based long-tail query rewriting in taobao search.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Large language model based long-tail query rewriting in taobao search

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:12:34.967595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 057d0cc7-415f-4deb-83d2-6910b71dc400 · outbound

This paper cites Rankflow: Joint optimization of multi-stage cascade ranking systems as flows.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Rankflow: Joint optimization of multi-stage cascade ranking systems as flows

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:12:34.937120Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e4ad6fc9-d1e7-44a4-9888-a0ac34df5051 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Direct preference optimization: Your language model is secretly a reward model

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:32.938700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dbbb977-4b79-4568-8da1-7b7093d4630f · outbound

This paper cites Recommender systems with generative retrieval.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Recommender systems with generative retrieval

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:33.010097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9f09756-f522-4026-be76-82782b589466 · outbound

This paper cites Proximal Policy Optimization Algorithms.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Proximal Policy Optimization Algorithms

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:33.093052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3789c514-58a4-4d09-91aa-d06644610368 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:33.171005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d76c055-c758-4975-b431-e0b0da8ffbc5 · outbound

This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 HybridFlow: A Flexible and Efficient RLHF Framework

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:33.229167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f5341ee-59b9-4769-b59f-56cbbad49b78 · outbound

This paper cites Learning to summarize with human feedback.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Learning to summarize with human feedback

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:33.308287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e3bc0a5-59c6-44f5-97d9-3cc99f7c03ef · outbound

This paper cites Bert4rec: Sequential recommendation with bidirectional encoder representations from transformer.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Bert4rec: Sequential recommendation with bidirectional encoder representations from transformer

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:12:34.807458Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2c78550a-e9ff-452b-bcbf-efc5fc1b878f · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 LLaMA: Open and Efficient Foundation Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:33.416496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 097aa803-1f42-4562-ab1e-f0891b819b15 · outbound

This paper cites Kerl: A knowledge-guided reinforcement learning model for sequential recommendation.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Kerl: A knowledge-guided reinforcement learning model for sequential recommendation

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:12:34.565605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 99a8b067-e3fc-4988-a874-df705a14f3f4 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Chain-of-thought prompting elicits reasoning in large language models

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:33.615151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bd8d4bf-7194-45c8-b172-be0827d6c01a · outbound

This paper cites PALR: Personalization Aware LLMs for Recommendation.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 PALR: Personalization Aware LLMs for Recommendation

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:33.694178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 481ac885-beb2-4f72-a162-7174c3a6be73 · outbound

This paper cites Feature-level deeper self-attention network for sequential recommendation.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Feature-level deeper self-attention network for sequential recommendation

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:12:34.300878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2cb6e1b4-a622-47e9-96fe-14893ee14302 · outbound

This paper cites Deep interest network for click-through rate prediction.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 Deep interest network for click-through rate prediction

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:33.831335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37362ac1-d24e-4014-b74e-2b2e02f3b96a · outbound

This paper cites S3-rec: Self-supervised learning for sequential recommendation with mutual information maximization.

RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1 S3-rec: Self-supervised learning for sequential recommendation with mutual information maximization

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T23:12:33.875901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 13e11885-dd8a-4e4c-8915-2f8240635264 · inbound

RecRM-Bench: Benchmarking Multidimensional Reward Modeling for Agentic Recommender Systems cites this paper.

RecRM-Bench: Benchmarking Multidimensional Reward Modeling for Agentic Recommender Systems RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-13T05:07:17.520568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9ca45276-c3f9-447a-b9eb-192a5ea914a9 · inbound

Intuition-Guided Latent Reasoning for LLM-Based Recommendation cites this paper.

Intuition-Guided Latent Reasoning for LLM-Based Recommendation RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-07-01T17:25:51.273725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 256a2bc7-e757-49fd-98e6-8408da8096ee · inbound

MAViE: A Multi-scale Adaptive Vision Encoder for Fine-grained Visual Perception and Efficient Multimodal Reasoning cites this paper.

MAViE: A Multi-scale Adaptive Vision Encoder for Fine-grained Visual Perception and Efficient Multimodal Reasoning RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-31T15:16:36.284072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.