Paper Citation Record · LEDGER

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization

As of 18 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 2 inbound Pith citation observations for arXiv:2412.18279.

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

pith.paper-citation-record.v1
2412.18279 v1

Coverage vector

measured 51 of 51 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T04:56:22.548936Z

measured 53 of 53 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T19:28:58.286475Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-10T22:20:49.395329Z

Reference resolution

51 of 51 outbound references displayed

verified exact1
verified fuzzy20
unresolved30
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 47f27bd7-943a-4824-8900-f8c17c71916e · outbound

This paper cites Kakade, Jason D.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Kakade, Jason D

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:56:23.242182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ef117a35-1d9e-497b-8b5b-f445757d78ad · outbound

This paper cites Back to basics: Revisiting reinforce-style optimization for learning from human feedback in llms.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Back to basics: Revisiting reinforce-style optimization for learning from human feedback in llms

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:56:23.230453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 0c0ec4a2-7d79-49e2-8452-275762ab279b · outbound

This paper cites Enhancing textual textbook question answering with large language models and retrieval augmented generation.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Enhancing textual textbook question answering with large language models and retrieval augmented generation

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.327850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c47b805-0b1f-487b-a9b9-bba92ad26948 · outbound

This paper cites Program Synthesis with Large Language Models.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Program Synthesis with Large Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.336962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8c4c37a-24b1-48ac-8771-73cdd995ceb5 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.340941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1765773-f787-4b03-a31c-4fa9e89d699c · outbound

This paper cites an unresolved cited work.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Unresolved cited work

Reference 7

Resolution: unresolved; raw_fallback, observed 2026-08-11T04:56:23.217534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 99cd411f-1c7d-46c9-a656-002b7db112ae · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Evaluating Large Language Models Trained on Code

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.349602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5337f7a0-db0f-4db6-810a-0c2116f91ab6 · outbound

This paper cites Teaching Large Language Models to Self-Debug.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Teaching Large Language Models to Self-Debug

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.353461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c27dda19-e679-4c18-9591-2be4b11cb8c1 · outbound

This paper cites Christiano, Jan Leike, Tom B.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Christiano, Jan Leike, Tom B

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:56:23.204999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 55f5ec46-89e8-42f3-b854-8b03b886ca60 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Training Verifiers to Solve Math Word Problems

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.361804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2d7ee51-ec5b-4c3e-90dd-60c61f6c5f97 · outbound

This paper cites RAFT: reward ranked finetuning for generative foundation model alignment.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization RAFT: reward ranked finetuning for generative foundation model alignment

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:56:23.192380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5840476f-026e-4cfc-886f-316930502ecf · outbound

This paper cites Addressing function approximation error in actor- critic methods.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Addressing function approximation error in actor- critic methods

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:56:23.179569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d79406e0-fc3d-4b9e-b4a1-e2be2aeeb154 · outbound

This paper cites On Designing Effective RL Reward at Training Time for LLM Reasoning.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization On Designing Effective RL Reward at Training Time for LLM Reasoning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.373566Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60a9534b-3660-473d-bc99-93e66693ff89 · outbound

This paper cites Step-level Value Preference Optimization for Mathematical Reasoning.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Step-level Value Preference Optimization for Mathematical Reasoning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.377628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09f37b5b-361d-44c2-9c7f-82f495636f97 · outbound

This paper cites Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:56:23.166167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 80ef1a1f-0d61-4c7b-b409-ce1a98a8d3b2 · outbound

This paper cites PSYDIAL: Personality-based Synthetic Dialogue Generation using Large Language Models.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization PSYDIAL: Personality-based Synthetic Dialogue Generation using Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.386035Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95cf2eee-ae1f-4735-9b12-c788d09b6494 · outbound

This paper cites Olympiadbench: A challenging benchmark for promoting AGI with olympiad-level bilingual multimodal scientific problems.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Olympiadbench: A challenging benchmark for promoting AGI with olympiad-level bilingual multimodal scientific problems

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:56:23.152947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation eba2264f-08e8-43ee-b19d-ac7f41ad7f62 · outbound

This paper cites Measuring mathematical problem solving with the MATH dataset.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Measuring mathematical problem solving with the MATH dataset

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.395440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bce6134c-d52e-4ad5-9ed0-bca3103a838c · outbound

This paper cites LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.400256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e019d461-189d-42f9-a85d-d39da7808a20 · outbound

This paper cites Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.405941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc6fcc9b-15a1-4f2f-a100-8df140d98083 · outbound

This paper cites SWE-bench: Can Language Models Resolve Real-World GitHub Issues?.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.410383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

This paper cites Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs.

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 634a185a-7fa5-4cf9-9d14-268eb4571d06 · outbound

This paper cites Deep Reinforcement Learning and the Deadly Triad.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Deep Reinforcement Learning and the Deadly Triad

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.421332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7919dcf5-3e18-4426-88e6-46a6140037a1 · outbound

This paper cites Ramasesh, AmbroseSlone, CemAnil, ImanolSchlag, TheoGutman-Solo, YuhuaiWu, BehnamNeyshabur, Guy Gur-Ari, and Vedant Misra.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Ramasesh, AmbroseSlone, CemAnil, ImanolSchlag, TheoGutman-Solo, YuhuaiWu, BehnamNeyshabur, Guy Gur-Ari, and Vedant Misra

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:56:23.132145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2ae719b7-e628-427b-b802-9ddf63d8f4d6 · outbound

This paper cites TACO: Topics in Algorithmic COde generation dataset.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization TACO: Topics in Algorithmic COde generation dataset

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.434443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76b19d65-81c5-4dd2-b439-c1dfedd28cb4 · outbound

This paper cites Remax: A simple, effective, and efficient reinforcement learning method for aligning large language models.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Remax: A simple, effective, and efficient reinforcement learning method for aligning large language models

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:56:23.113005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2b1f2dc6-3753-4552-a39a-932993fef074 · outbound

This paper cites On the Linear Convergence of Policy Gradient under Hadamard Parameterization.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization On the Linear Convergence of Policy Gradient under Hadamard Parameterization

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-08-11T04:56:22.741664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation a9b96a0d-0917-453d-a1c3-81d6901e0bda · outbound

This paper cites On the Convergence of Projected Policy Gradient for Any Constant Step Sizes.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization On the Convergence of Projected Policy Gradient for Any Constant Step Sizes

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.449036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53de0872-a891-4fab-9ada-976fdf1488b8 · outbound

This paper cites Elementary Analysis of Policy Gradient Methods.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Elementary Analysis of Policy Gradient Methods

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.453068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e31126b9-e4bd-4a0d-96cd-7dd6e9fbb037 · outbound

This paper cites Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Step-Controlled DPO: Leveraging Stepwise Error for Enhanced Mathematical Reasoning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.457607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 852b9206-1902-4753-8ec6-d59310ff5c86 · outbound

This paper cites Leveraging non-uniformity in first-order non-convex optimization.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Leveraging non-uniformity in first-order non-convex optimization

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:56:23.099144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation ec528c7f-09e1-4b22-8040-7c2b3297a825 · outbound

This paper cites On the global convergence rates of softmax policy gradient methods.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization On the global convergence rates of softmax policy gradient methods

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:56:23.080227Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 09fe81e4-c924-4628-9635-d61c9acecac8 · outbound

This paper cites Skywork-o1 open series.https://huggingface.co/Skywork, November 2024.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Skywork-o1 open series.https://huggingface.co/Skywork, November 2024

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:56:23.066134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 89f9c63b-54dd-48ed-bdb1-11d45a586f9d · outbound

This paper cites Manning, Stefano Ermon, and Chelsea Finn.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Manning, Stefano Ermon, and Chelsea Finn

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:56:23.054411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 621e3870-a4e6-4683-b07d-6e202d0c3c6b · outbound

This paper cites Offline Regularised Reinforcement Learning for Large Language Models Alignment.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Offline Regularised Reinforcement Learning for Large Language Models Alignment

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.480620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5175a9c0-ea33-4ca2-bb68-d8fda1743e83 · outbound

This paper cites Riedmiller, Roland Hafner, Thomas Lampe, Michael Neunert, Jonas Degrave, Tom Van de Wiele, Vlad Mnih, Nicolas Heess, and Jost Tobias Springenberg.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Riedmiller, Roland Hafner, Thomas Lampe, Michael Neunert, Jonas Degrave, Tom Van de Wiele, Vlad Mnih, Nicolas Heess, and Jost Tobias Springenberg

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:56:23.042722Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 7148fab6-237d-4722-9a0a-58ff2335d79c · outbound

This paper cites High-Dimensional Continuous Control Using Generalized Advantage Estimation.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization High-Dimensional Continuous Control Using Generalized Advantage Estimation

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.491649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 667f61e7-6ec8-47ff-aa8e-eea2ea2da1c8 · outbound

This paper cites Proximal Policy Optimization Algorithms.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Proximal Policy Optimization Algorithms

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.496036Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c945365-0fb6-44fb-aec4-c5771848d22d · outbound

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

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.500768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4af85cb5-331a-4a79-978b-a870a480247d · outbound

This paper cites Sutton, David McAllester, Satinder Singh, and Yishay Mansour.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Sutton, David McAllester, Satinder Singh, and Yishay Mansour

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:56:23.028279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5af334ff-287e-476f-921f-dd0f1a6ca420 · outbound

This paper cites Mathscale: Scaling instruction tuning for mathematical reasoning.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Mathscale: Scaling instruction tuning for mathematical reasoning

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:56:23.014407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 337596f2-d442-4880-899e-b11c7c5a4c75 · outbound

This paper cites Qwen2.5: A party of foundation models, September 2024.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Qwen2.5: A party of foundation models, September 2024

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.513048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94800a6a-203e-4372-a873-cb8be31f73a1 · outbound

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

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization LLaMA: Open and Efficient Foundation Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.517239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eabccda1-291c-40b6-a596-f6d342763f57 · outbound

This paper cites Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.521338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1cf4d63-f665-4fa2-bdaf-958ccaaaa325 · outbound

This paper cites Mathcoder: Seamless code integration in llms for enhanced mathematical reasoning.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Mathcoder: Seamless code integration in llms for enhanced mathematical reasoning

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:56:22.991257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 5ea1bca7-7164-4177-8a73-8898b12f94bb · outbound

This paper cites Math-shepherd: Verify and reinforce llms step-by-step without human annotations.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Math-shepherd: Verify and reinforce llms step-by-step without human annotations

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:56:22.976182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 2d4b108a-5b06-4fc9-a75e-23e4fbb235d0 · outbound

This paper cites Brown, and Ken Goldberg.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Brown, and Ken Goldberg

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:56:22.962709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 37573d63-20d1-49e6-94eb-0d990791ef1a · outbound

This paper cites Qwen2 Technical Report.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Qwen2 Technical Report

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.536918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08d47d4b-e6a4-4e4a-81fc-127386ad2ec4 · outbound

This paper cites Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.540940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e2e0133-219c-409f-ad96-6553b1331efa · outbound

This paper cites Kwok, Zhenguo Li, Adrian Weller, and Weiyang Liu.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Kwok, Zhenguo Li, Adrian Weller, and Weiyang Liu

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T04:56:22.949709Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e69b9c43-c12c-4c06-9502-eb7e9d24e244 · outbound

This paper cites Skywork-Math: Data Scaling Laws for Mathematical Reasoning in Large Language Models -- The Story Goes On.

Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization Skywork-Math: Data Scaling Laws for Mathematical Reasoning in Large Language Models -- The Story Goes On

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-11T04:56:22.548936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 13723c2e-df2d-4094-92f3-2598b454f8e0 · inbound

Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents cites this paper.

Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T19:28:58.286475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8b1cd13-a158-4d77-8c29-25dfaa2c2a60 · inbound

Application-Driven Pedagogical Knowledge Optimization of Open-Source LLMs via Reinforcement Learning and Supervised Fine-Tuning cites this paper.

Application-Driven Pedagogical Knowledge Optimization of Open-Source LLMs via Reinforcement Learning and Supervised Fine-Tuning Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage Policy Optimization

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:20:49.396977Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.