Paper Citation Record · LEDGER

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

As of 13 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 75 inbound Pith citation observations for arXiv:2406.18629.

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

pith.paper-citation-record.v1
2406.18629 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-18T23:58:29.040819Z

measured 113 of 113 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 75 of 75 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T18:20:13.925085Z

measured 1 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

38 of 38 outbound references displayed

verified exact35
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch3

External citation measurements

1
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 6cc6da4a-7f20-472c-93af-ce641a20af4b · outbound

This paper cites GPT-4 Technical Report.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs GPT-4 Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:58:29.068590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5f81d01a-12e0-41f1-9710-d4a4fd8518b2 · outbound

This paper cites Llemma: An Open Language Model For Mathematics.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Llemma: An Open Language Model For Mathematics

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-19T08:17:47.048289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8911546b-1d35-42c6-abb5-1068da101f26 · outbound

This paper cites Qwen Technical Report.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Qwen Technical Report

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:58:29.085943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 95df9dbc-b51e-4716-84d4-a1ff874671d7 · outbound

This paper cites AlphaMath Almost Zero: Process Supervision without Process.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs AlphaMath Almost Zero: Process Supervision without Process

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.092722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 036242d0-3f62-4f0a-9799-50689a486566 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Training Verifiers to Solve Math Word Problems

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:58:29.098112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0d4146c7-3b79-4bed-a7f4-c373ae647493 · outbound

This paper cites ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-19T09:19:36.299641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4fdd0d13-c785-45f0-b0d0-cd0d1c5cbc16 · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Measuring Mathematical Problem Solving With the MATH Dataset

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:58:29.109676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e81133a8-39b6-4626-b85e-6c14d1e98abd · outbound

This paper cites ORPO: Monolithic Preference Optimization without Reference Model.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs ORPO: Monolithic Preference Optimization without Reference Model

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:58:29.115187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation aa8c5b32-a312-4b29-ac0b-f19dd3af5479 · outbound

This paper cites Common 7B Language Models Already Possess Strong Math Capabilities.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Common 7B Language Models Already Possess Strong Math Capabilities

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.120167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 489efe0a-d477-4c8b-94b2-47078a1d17a9 · outbound

This paper cites MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.125069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c0eaa2a6-8da8-4363-8916-3cc0dc939799 · outbound

This paper cites Let's Verify Step by Step.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Let's Verify Step by Step

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:58:29.129806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4b075053-92a5-4a37-8f89-3f69aefd8a91 · outbound

This paper cites Rho-1: Not All Tokens Are What You Need.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Rho-1: Not All Tokens Are What You Need

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.135044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation bb851368-450b-43be-a9a0-49a5e3f9781d · outbound

This paper cites Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:58:29.139816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation fb61548a-ef33-449e-a772-18361de229fc · outbound

This paper cites Augmenting Math Word Problems via Iterative Question Composing.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Augmenting Math Word Problems via Iterative Question Composing

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T23:58:29.144173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9707572d-5283-4e31-93c5-8370a9918894 · outbound

This paper cites Improving Large Language Model Fine-tuning for Solving Math Problems.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Improving Large Language Model Fine-tuning for Solving Math Problems

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.148772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 7ca1941d-7477-4e79-a4dd-3ff3a5abb369 · outbound

This paper cites MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMs.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs MathGenie: Generating Synthetic Data with Question Back-translation for Enhancing Mathematical Reasoning of LLMs

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.153407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b50c459f-c26c-4ef3-86ac-73c93556487d · outbound

This paper cites WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:58:29.158159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation bd279192-e885-45f5-9df8-41ea13196fb9 · outbound

This paper cites Orca-Math: Unlocking the potential of SLMs in Grade School Math.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Orca-Math: Unlocking the potential of SLMs in Grade School Math

Reference 18

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T23:58:29.162986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0d86d06d-2721-4ab5-af11-1b427c1e8f62 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:58:29.167115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 2b98df74-23c5-4bb5-8021-7ac74090b29d · outbound

This paper cites Code Llama: Open Foundation Models for Code.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Code Llama: Open Foundation Models for Code

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:58:29.171477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e8ed9e34-afb2-4b82-8dd0-7d5de9925bf6 · outbound

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

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:58:29.175855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6de8ae2e-03b9-44ec-a1c8-60d64d7d8cbd · outbound

This paper cites MathScale: Scaling Instruction Tuning for Mathematical Reasoning.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs MathScale: Scaling Instruction Tuning for Mathematical Reasoning

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.180880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 889dc090-5a34-4059-9d08-6d37ed4e0238 · outbound

This paper cites Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.185916Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d17fe6da-b6cc-4608-972f-a4cf8b53a4e7 · outbound

This paper cites OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.190696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1a383ce5-5ad3-408e-8c76-85838ec2650c · outbound

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

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs LLaMA: Open and Efficient Foundation Language Models

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:58:29.195217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ec1fd29b-da13-44ce-961b-f320537be3cc · outbound

This paper cites Zephyr: Direct Distillation of LM Alignment.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Zephyr: Direct Distillation of LM Alignment

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:58:29.200511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d0abb843-beab-40b5-a7d1-4f466f8d5266 · outbound

This paper cites MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.205867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b9903deb-c0fe-4bc6-b8b1-85f6d9478e51 · outbound

This paper cites DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic Data

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.210896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b0635685-0424-427f-954b-7dae3584314e · outbound

This paper cites ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.215547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 26791200-3458-4d05-8142-c370e8dc9306 · outbound

This paper cites InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs InternLM-Math: Open Math Large Language Models Toward Verifiable Reasoning

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.220895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9e3522f4-4a64-419a-8bb9-b4f87a7d88a2 · outbound

This paper cites Answering Questions by Meta-Reasoning over Multiple Chains of Thought.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Answering Questions by Meta-Reasoning over Multiple Chains of Thought

Reference 31

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T23:58:29.225691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 859f9129-73d9-43d8-84d4-4772f4109909 · outbound

This paper cites MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:58:29.230072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 48280907-40fd-4801-94bb-c33f2fdc1998 · outbound

This paper cites Scaling Relationship on Learning Mathematical Reasoning with Large Language Models.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:58:29.234743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 94c1f6e1-2a00-4a6c-9985-8f2832498306 · outbound

This paper cites MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:58:29.240596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 923df388-c29d-4125-bfce-3ad63a44236e · outbound

This paper cites MAmmoTH2: Scaling Instructions from the Web.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs MAmmoTH2: Scaling Instructions from the Web

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.245776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 17f98e61-12f4-4375-90f7-b28e009959fa · outbound

This paper cites Least-to-Most Prompting Enables Complex Reasoning in Large Language Models.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs Least-to-Most Prompting Enables Complex Reasoning in Large Language Models

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:58:29.251197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 80e66f49-39ce-4d1d-82d9-3d72e932817a · outbound

This paper cites JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.256685Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b76230c7-eec0-420b-a315-402e3895a086 · outbound

This paper cites DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence.

Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-05-18T23:58:29.261388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Pith citing papers

Observation fa4bf688-ed37-43a3-8817-050c10a3402a · inbound

Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents cites this paper.

Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-05-20T09:42:04.287817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5b0a0db2-e7bf-4f99-b7c4-43cfa6aff57d · inbound

Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization cites this paper.

Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 43

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.262663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation bf05dcc1-26d7-43c1-8876-d01f3cb28f33 · inbound

PSPO*: An Effective Process-supervised Policy Optimization for Reasoning Alignment cites this paper.

PSPO*: An Effective Process-supervised Policy Optimization for Reasoning Alignment Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T18:20:13.925085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6ee085e-1b7d-49ac-a12d-16e73d18f24b · inbound

Preference Optimization for Reasoning with Pseudo Feedback cites this paper.

Preference Optimization for Reasoning with Pseudo Feedback Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T13:21:05.606869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 90bd06fd-699c-4981-a096-0ddeb21a5be2 · inbound

Mars-PO: Multi-Agent Reasoning System Preference Optimization cites this paper.

Mars-PO: Multi-Agent Reasoning System Preference Optimization Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T10:39:36.883872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 232c31f4-a495-4526-85c3-39f190e2e66e · inbound

Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability cites this paper.

Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T05:43:31.521431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37ad7b07-5d02-43ae-a588-8ce714176bf7 · inbound

A Systematic Examination of Preference Learning through the Lens of Instruction-Following cites this paper.

A Systematic Examination of Preference Learning through the Lens of Instruction-Following Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T12:41:20.695300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6784637-1a2b-4c90-840f-60079620f06e · inbound

A Systematic Examination of Preference Learning through the Lens of Instruction-Following cites this paper.

A Systematic Examination of Preference Learning through the Lens of Instruction-Following Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T12:41:20.698420Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 076dad93-3150-45f2-97f7-fa92d32b0265 · inbound

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization cites this paper.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.417074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca2d97d6-65c3-449a-a8e3-ee73b60c5396 · inbound

Plug-and-Play Training Framework for Preference Optimization cites this paper.

Plug-and-Play Training Framework for Preference Optimization Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T23:21:34.108960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93ce969c-ecec-4fb8-aeb2-2c5092d15dd2 · inbound

Enhancing Reasoning through Process Supervision with Monte Carlo Tree Search cites this paper.

Enhancing Reasoning through Process Supervision with Monte Carlo Tree Search Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-10T22:37:07.176830Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c88df6c2-b598-4e56-bd5f-faeed1545a19 · inbound

SDPO: Segment-Level Direct Preference Optimization for Social Agents cites this paper.

SDPO: Segment-Level Direct Preference Optimization for Social Agents Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T22:28:56.735753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ae5de45-65db-4af0-9cce-29c3e93d268a · inbound

VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning cites this paper.

VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-10T20:54:13.255347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation be8edc1b-2d84-466a-aeca-f54a9f5890cb · inbound

Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step cites this paper.

Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-10T15:32:46.315309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7fa5bfa-b430-4b78-a825-3df5b72de4c3 · inbound

Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages cites this paper.

Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T15:49:27.751399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30af0243-2239-4962-b88d-f4ad59925137 · inbound

Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models cites this paper.

Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 169

Resolution: unresolved; no resolver link, observed 2026-08-10T18:04:34.721346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91d6dd8e-0e46-4c22-ad3b-e4a5371bbc10 · inbound

LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information cites this paper.

LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Information Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-09T13:25:52.021917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bce7f0a-c59f-4953-aeb5-9971afb79efa · inbound

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach cites this paper.

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 86

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.262663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4f4307c2-cea9-4983-a12e-5a00a1d79f35 · inbound

PIPA: Preference Alignment as Prior-Informed Statistical Estimation cites this paper.

PIPA: Preference Alignment as Prior-Informed Statistical Estimation Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-08T18:10:53.393381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 290e26b9-8ff6-43c0-ada4-d2130980bf9c · inbound

Harness Local Rewards for Global Benefits: Effective Text-to-Video Generation Alignment with Patch-level Reward Models cites this paper.

Harness Local Rewards for Global Benefits: Effective Text-to-Video Generation Alignment with Patch-level Reward Models Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-09T11:26:17.321272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48c1bd92-9ef3-44f5-81fb-ac6f08efd1f9 · inbound

From System 1 to System 2: A Survey of Reasoning Large Language Models cites this paper.

From System 1 to System 2: A Survey of Reasoning Large Language Models Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 181

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.262663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 794dfe46-4d9f-44d7-bc45-92f56829af41 · inbound

ReTool: Reinforcement Learning for Strategic Tool Use in LLMs cites this paper.

ReTool: Reinforcement Learning for Strategic Tool Use in LLMs Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.262663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c5476062-0026-4499-be03-a071d6d1d788 · inbound

ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning cites this paper.

ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:22:59.458706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6883d3c8-a050-40a8-8301-f9d80190edc0 · inbound

Large Language Models for Planning: A Comprehensive and Systematic Survey cites this paper.

Large Language Models for Planning: A Comprehensive and Systematic Survey Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 124

Resolution: unresolved; no resolver link, observed 2026-08-07T14:11:58.907511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93167904-f699-4575-8d5c-3297e29e1fcb · inbound

Amulet: Putting Complex Multi-Turn Conversations on the Stand with LLM Juries cites this paper.

Amulet: Putting Complex Multi-Turn Conversations on the Stand with LLM Juries Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T13:59:54.505939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1122bdd9-2470-4da0-a66b-0cc656f55190 · inbound

Why Distillation can Outperform Zero-RL: The Role of Flexible Reasoning cites this paper.

Why Distillation can Outperform Zero-RL: The Role of Flexible Reasoning Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T13:46:40.944799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c01072d5-3cee-4766-bfb9-26bbf4b826a7 · inbound

Infi-MMR: Curriculum-based Unlocking Multimodal Reasoning via Phased Reinforcement Learning in Multimodal Small Language Models cites this paper.

Infi-MMR: Curriculum-based Unlocking Multimodal Reasoning via Phased Reinforcement Learning in Multimodal Small Language Models Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T12:59:19.624700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da8f3bc5-b4f0-4027-9da9-3c0cee68f900 · inbound

APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training cites this paper.

APT: Improving Specialist LLM Performance with Weakness Case Acquisition and Iterative Preference Training Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T11:07:11.100055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96a52f76-7061-4763-814e-a502ca788c4c · inbound

A Survey on Large Language Models for Mathematical Reasoning cites this paper.

A Survey on Large Language Models for Mathematical Reasoning Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:47.300557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d19fd706-3403-47a2-ad12-cb865ce56a1b · inbound

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization cites this paper.

ConfPO: Exploiting Policy Model Confidence for Critical Token Selection in Preference Optimization Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T05:14:43.248348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b40b769e-4c06-48e5-9d9d-e10fc34fc93c · inbound

MDPO: Multi-Granularity Direct Preference Optimization for Mathematical Reasoning cites this paper.

MDPO: Multi-Granularity Direct Preference Optimization for Mathematical Reasoning Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-07T12:29:34.795071Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9653dec-3380-4c78-8316-8b21d5210f57 · inbound

Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation cites this paper.

Enhancing Spatial Reasoning in Multimodal Large Language Models through Reasoning-based Segmentation Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T21:53:00.558586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a898ff4-7998-4ad4-9dd9-40d056379cdf · inbound

From Fragments to Facts: A Curriculum-Driven DPO Approach for Generating Hindi News Veracity Explanations cites this paper.

From Fragments to Facts: A Curriculum-Driven DPO Approach for Generating Hindi News Veracity Explanations Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-19T06:12:07.162976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation edf792c8-05a7-415b-8318-369e1b8a0856 · inbound

Not All Preferences are What You Need for Post-Training: Selective Alignment Strategy for Preference Optimization cites this paper.

Not All Preferences are What You Need for Post-Training: Selective Alignment Strategy for Preference Optimization Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T18:38:09.880112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00092c23-b383-49c4-b201-bfa48500b59f · inbound

Mitigating Object Hallucinations via Sentence-Level Early Intervention cites this paper.

Mitigating Object Hallucinations via Sentence-Level Early Intervention Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-25T08:35:32.638911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c3f08595-d6ec-47d1-b174-aa944314cf68 · inbound

Mitigating Think-Answer Mismatch in LLM Reasoning Through Noise-Aware Advantage Reweighting cites this paper.

Mitigating Think-Answer Mismatch in LLM Reasoning Through Noise-Aware Advantage Reweighting Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-05T23:10:24.477083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e3cd6c3-9c29-4b23-8a4a-9af3c335d1af · inbound

Sample-efficient LLM Optimization with Reset Replay cites this paper.

Sample-efficient LLM Optimization with Reset Replay Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.262663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 564cad11-567b-4dad-a399-c7f3cfefca93 · inbound

A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems cites this paper.

A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.262663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 808fbd4d-c3e0-4f1f-88bc-b8bff91c6cc2 · inbound

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey cites this paper.

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.262663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 49446334-2c1d-4385-a9e1-a519bf67dd97 · inbound

Future Policy Approximation for Offline Reinforcement Learning Improves Mathematical Reasoning cites this paper.

Future Policy Approximation for Offline Reinforcement Learning Improves Mathematical Reasoning Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T23:58:29.262663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation eec23df6-7e9f-4b05-95c8-180768cf78a1 · inbound

SHE: Stepwise Hybrid Examination Reinforcement Learning Framework for E-commerce Search Relevance cites this paper.

SHE: Stepwise Hybrid Examination Reinforcement Learning Framework for E-commerce Search Relevance Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.262663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c015ebd5-0bb5-4d99-86fc-21eb80bd959a · inbound

TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance cites this paper.

TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-04T10:53:08.480368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c37e923-e5d4-4838-b5d0-fba9af9e4bdc · inbound

PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling cites this paper.

PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.262663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation fb12e888-3d24-44dd-b835-dc5ce12a995f · inbound

Hard Negative Sample-Augmented DPO Post-Training for Small Language Models cites this paper.

Hard Negative Sample-Augmented DPO Post-Training for Small Language Models Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.262663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 3aee8528-579a-4fed-8205-11dc1dea540c · inbound

Advancing Multimodal Judge Models through a Capability-Oriented Benchmark and MCTS-Driven Data Generation cites this paper.

Advancing Multimodal Judge Models through a Capability-Oriented Benchmark and MCTS-Driven Data Generation Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T19:56:29.025781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7b9b8bd-b4c5-4748-82ce-a4918d724865 · inbound

Curr-RLCER:Curriculum Reinforcement Learning For Coherence Explainable Recommendation cites this paper.

Curr-RLCER:Curriculum Reinforcement Learning For Coherence Explainable Recommendation Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T23:58:29.262663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation cddd1db6-ec81-4b3c-a7e5-c64dcf347b56 · inbound

Decomposing the Delta: What Do Models Actually Learn from Preference Pairs? cites this paper.

Decomposing the Delta: What Do Models Actually Learn from Preference Pairs? Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.262663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f443fea7-b8cd-4791-b487-5ca6d634b5ac · inbound

On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization cites this paper.

On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.262663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6c56e097-7310-4955-acda-b5063cb3d4bd · inbound

Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding cites this paper.

Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher Decoding Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 47

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T23:58:29.262663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4cdde1c5-a6fa-4195-bf6e-12b1b00d862e · inbound

MedThink: Enhancing Diagnostic Accuracy in Small Models via Teacher-Guided Reasoning Correction cites this paper.

MedThink: Enhancing Diagnostic Accuracy in Small Models via Teacher-Guided Reasoning Correction Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.262663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e145583c-698b-40c5-8677-aaac3491cc14 · inbound

Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models cites this paper.

Mid-Training with Self-Generated Data Improves Reinforcement Learning in Language Models Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.262663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8970bf92-f524-4ea3-b4d6-39a3f68b7ccf · inbound

Reasoning Is Not Free: Robust Adaptive Cost-Efficient Routing for LLM-as-a-Judge cites this paper.

Reasoning Is Not Free: Robust Adaptive Cost-Efficient Routing for LLM-as-a-Judge Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-18T23:58:29.262663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f459a32c-788c-4e36-b98d-4479abf8e8f0 · inbound

YFPO: A Preliminary Study of Yoked Feature Preference Optimization with Neuron-Guided Rewards for Mathematical Reasoning cites this paper.

YFPO: A Preliminary Study of Yoked Feature Preference Optimization with Neuron-Guided Rewards for Mathematical Reasoning Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T23:58:29.262663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d0349acd-d333-4845-8385-e9e4ec6bbcf1 · inbound

Enhancing LLM Metacognition via Cognitive Pairwise Training cites this paper.

Enhancing LLM Metacognition via Cognitive Pairwise Training Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 83

Resolution: verified exact; local_arxiv, observed 2026-06-28T19:02:33.922491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b7776c39-e0cf-4b81-9ecd-8433735cd0b0 · inbound

DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling cites this paper.

DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 18

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T16:57:10.030422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d6322ad5-456d-46c5-b859-1e7907ebcf31 · inbound

Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery cites this paper.

Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 178

Resolution: verified exact; local_arxiv, observed 2026-07-02T22:47:25.924065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 2ff953ea-7321-44d2-9486-31e62b458d5e · inbound

Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery cites this paper.

Reference 178

Resolution: unresolved; no resolver link, observed 2026-08-02T12:05:18.089147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 765c1947-6e7a-40f9-a237-21b4d3aeec03 · inbound

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning cites this paper.

TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 56

Resolution: metadata mismatch; local_arxiv, observed 2026-07-03T04:27:36.668377Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0138b81b-b3bd-49ee-90ad-45c393ff9032 · inbound

APPO: Agentic Procedural Policy Optimization cites this paper.

APPO: Agentic Procedural Policy Optimization Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-07-03T09:37:49.416543Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d88db0e8-6e3c-4970-8b32-4f9170e4df84 · inbound

APPO: Agentic Procedural Policy Optimization cites this paper.

APPO: Agentic Procedural Policy Optimization Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T02:12:27.879246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 165fabcd-4440-4baf-a1cd-42f140a0680d · inbound

ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning cites this paper.

ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-07-03T15:08:33.402998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1a30c586-887c-4550-8011-78f8f7c1b6de · inbound

ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning cites this paper.

ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T02:12:19.127147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa580899-0bc5-4646-a750-1e0487fdcf0a · inbound

Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence cites this paper.

Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-07-03T17:38:44.174836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 6d9ae9eb-77f8-48ae-80d4-99f0a7491913 · inbound

Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents cites this paper.

Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 110

Resolution: verified exact; local_arxiv, observed 2026-07-04T20:40:07.843363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation d4408eb1-6fd1-4e65-a041-39d1f3336854 · inbound

Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM cites this paper.

Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 6

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T13:33:28.303470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation dbbdc301-8aa1-432d-8792-d5fdf14ce555 · inbound

DiARC: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language Models cites this paper.

DiARC: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language Models Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T13:09:50.060500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 1187e579-c9d9-4db7-bdca-02c9bfc88a57 · inbound

DiARC: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language Models cites this paper.

DiARC: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language Models Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T17:23:45.531776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation bcd9bee0-47a9-4340-8155-476652639379 · inbound

Flow Reasoning Models: Scaling Reasoning Through Iterative Self-Refinement cites this paper.

Flow Reasoning Models: Scaling Reasoning Through Iterative Self-Refinement Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 14

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T08:04:28.377800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation cfa2c755-5b1e-4f8a-9995-6e32ecd56d6b · inbound

StrucTab: A Structured Optimization Framework for Table Parsing cites this paper.

StrucTab: A Structured Optimization Framework for Table Parsing Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T06:24:18.922918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 08ae0c01-cea2-4452-afda-ac733a5a2c7d · inbound

Best-of-Better-$N$: Generating Pre-Aligned Responses with In-Context Learning cites this paper.

Best-of-Better-$N$: Generating Pre-Aligned Responses with In-Context Learning Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-12T02:23:04.515705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52443909-5f8f-4eee-b2b7-9b01f26e98cb · inbound

Multi-Turn On-Policy Distillation with Prefix Replay cites this paper.

Multi-Turn On-Policy Distillation with Prefix Replay Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 96

Resolution: unresolved; no resolver link, observed 2026-07-11T13:53:36.775836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85614d0d-d12e-484e-976e-8ffddea0d4f4 · inbound

Multi-Turn On-Policy Distillation with Prefix Replay cites this paper.

Multi-Turn On-Policy Distillation with Prefix Replay Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-02T08:40:42.479453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87b2b2cf-224f-4ae4-9ad6-dde87fe12866 · inbound

Agentic-DPO: From Imitation to Agentic Policy Optimization on Expert Trajectories cites this paper.

Agentic-DPO: From Imitation to Agentic Policy Optimization on Expert Trajectories Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-14T10:33:54.851493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ad3e2a1-1796-4da4-ae1e-a62d7563a082 · inbound

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding cites this paper.

DC-Leap: Training-Free Acceleration of dLLMs via Draft-Guided Contiguous Leaping Decoding Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T13:42:24.987811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e050620a-34d5-46d5-b4d6-852f9bc765c1 · inbound

Se-DPO: Self-Evolving Token Credit for Direct Preference Optimization cites this paper.

Se-DPO: Self-Evolving Token Credit for Direct Preference Optimization Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-11T14:59:12.114561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.