Paper Citation Record · LEDGER

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation

As of 15 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2608.09271.

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

pith.paper-citation-record.v1
2608.09271 v1

Coverage vector

measured 48 of 48 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T20:29:03.988127Z

measured 48 of 48 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

48 of 48 outbound references displayed

verified exact2
verified fuzzy18
unresolved28
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 48b53655-8338-455c-9072-cc43d51e5d70 · outbound

This paper cites Maximum a posteriori policy optimisation.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Maximum a posteriori policy optimisation

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:29:05.154815Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b55a5c17-6a6d-44f5-821f-3c6cfdbe5ed4 · outbound

This paper cites On-policy distillation of language models: Learning from self-generated mistakes.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation On-policy distillation of language models: Learning from self-generated mistakes

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.758603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 525ca485-55f0-49a7-b7e6-8fad8d4166b5 · outbound

This paper cites Escaping the Verifier: Learning to Reason via Demonstrations.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Escaping the Verifier: Learning to Reason via Demonstrations

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.762979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c081b2c-b1cc-43ae-826a-154f1b865aa2 · outbound

This paper cites MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.767752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e21b2de8-8e72-4244-a467-cbf86dfbdcbb · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Training Verifiers to Solve Math Word Problems

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.773626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e92ab6a6-f12e-4c5c-bf29-15f1bc327298 · outbound

This paper cites What is the objective of reasoning with reinforcement learning?arXiv preprint arXiv:2510.13651, 2025.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation What is the objective of reasoning with reinforcement learning?arXiv preprint arXiv:2510.13651, 2025

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.779243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f13f1dd0-43c6-4c6d-9695-30ca959afb0a · outbound

This paper cites Imagenet: A large-scale hierarchical image database.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Imagenet: A large-scale hierarchical image database

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.783941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84f6e10f-4685-4e7f-8cc3-fb2d32f8e0f2 · outbound

This paper cites Openvlthinker: Complex vision-language reasoning via iterative sft-rl cycles.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Openvlthinker: Complex vision-language reasoning via iterative sft-rl cycles

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:29:05.111003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 20687639-1a63-447a-a10a-f63fbced52b2 · outbound

This paper cites Cold-startreinforcementlearningwithsoftmaxpolicygradient.AdvancesinNeuralInformation Processing Systems, 30, 2017.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Cold-startreinforcementlearningwithsoftmaxpolicygradient.AdvancesinNeuralInformation Processing Systems, 30, 2017

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:29:05.094454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 26e738b6-6dd2-424a-8a0f-45140ae1f74a · outbound

This paper cites Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.802470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7beda436-9439-4ca8-a003-b6981708edcb · outbound

This paper cites OpenThoughts: Data Recipes for Reasoning Models.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation OpenThoughts: Data Recipes for Reasoning Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.807561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a17ffd8-7427-4f11-9cf7-79adc4121cf3 · outbound

This paper cites Learning to reason for long-form story generation.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Learning to reason for long-form story generation

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:29:05.075028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 48f9ec6e-9262-4274-afaa-6fb7501c6178 · outbound

This paper cites RLP: Reinforcement as a pretraining objective.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation RLP: Reinforcement as a pretraining objective

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:29:05.054235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 05494d81-0622-43c3-b6f8-6e8f374f2ce4 · outbound

This paper cites Deep residual learning for image recognition.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Deep residual learning for image recognition

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.823062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cfee7c8-6f4c-48d2-9d30-2b7b50364774 · outbound

This paper cites Shah, Qihua Dong, Zilin Xiao, Jaywon Koo, and Vicente Ordonez.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Shah, Qihua Dong, Zilin Xiao, Jaywon Koo, and Vicente Ordonez

Reference 15

Resolution: verified exact; raw_fallback, observed 2026-08-11T20:29:04.545909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 35b152db-d9c5-4e67-be3b-5f387a809020 · outbound

This paper cites Deepmath-103k: A large-scale, challenging, decontaminated, and verifiable mathematical dataset for advancing reasoning.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Deepmath-103k: A large-scale, challenging, decontaminated, and verifiable mathematical dataset for advancing reasoning

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:29:05.022024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 9b185181-cef0-4488-85ec-28312844286e · outbound

This paper cites Measuring massive multitask language understanding.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Measuring massive multitask language understanding

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:29:05.003190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 15b122f3-3271-47d1-a85e-1056e4c2a181 · outbound

This paper cites MeetingBank: A benchmark dataset for meeting summarization.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation MeetingBank: A benchmark dataset for meeting summarization

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.841893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c36242e-055c-4d68-baa6-1c03b07921da · outbound

This paper cites Answer-consistent chain-of-thought reinforcement learning for multi-modal large langauge models.arXiv preprint arXiv:2510.10104, 2025.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Answer-consistent chain-of-thought reinforcement learning for multi-modal large langauge models.arXiv preprint arXiv:2510.10104, 2025

Reference 19

Resolution: verified exact; raw_fallback, observed 2026-08-11T20:29:04.467803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 795c7606-06d9-4595-9f60-48d13b5bff96 · outbound

This paper cites OpenAI o1 System Card.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation OpenAI o1 System Card

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.849865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa3ffc40-e62f-4a9e-ba83-fd47bd5756da · outbound

This paper cites Understanding r1- zero-like training: A critical perspective.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Understanding r1- zero-like training: A critical perspective

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:29:04.984900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation bbf87a8c-ddbe-4498-8be6-dde95ef68651 · outbound

This paper cites Decoupled Weight Decay Regularization.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Decoupled Weight Decay Regularization

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.858538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4fd2436-2fc2-4385-b832-dbd69df5c953 · outbound

This paper cites On-policy distillation.Thinking Machines Lab: Connectionism, 2025.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation On-policy distillation.Thinking Machines Lab: Connectionism, 2025

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.861966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52b88f80-ef63-4ff9-8573-7d2bbb375abc · outbound

This paper cites General-Reasoner: Advancing LLM Reasoning Across All Domains.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation General-Reasoner: Advancing LLM Reasoning Across All Domains

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.866650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8ec9b47-7531-485b-acc9-1ae53493c044 · outbound

This paper cites Reward augmented maximum likelihood for neural structured prediction.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Reward augmented maximum likelihood for neural structured prediction

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:29:04.967759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a1ef6423-ea6a-4ad1-a018-93043bdfcc5d · outbound

This paper cites Iterative reasoning preference optimization.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Iterative reasoning preference optimization

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:29:04.951654Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 51f6a1b5-835f-47b5-8420-966b7dbfdea3 · outbound

This paper cites Rethinking the Trust Region in LLM Reinforcement Learning.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Rethinking the Trust Region in LLM Reinforcement Learning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.881817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55fe61b9-3264-4cfd-b253-47e751c87af8 · outbound

This paper cites an unresolved cited work.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.889681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 179e6939-895e-4b35-80e7-2111e926cea2 · outbound

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

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Direct preference optimization: Your language model is secretly a reward model

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:29:04.911990Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 3fe1534d-def2-40eb-a0e7-b2d07c77d067 · outbound

This paper cites an unresolved cited work.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-11T20:29:04.890952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 453e334e-fed7-4919-985c-4d93a7cf781a · outbound

This paper cites Optimal completion distillation for sequence learning.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Optimal completion distillation for sequence learning

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:29:04.856233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c449c312-c2ba-4e89-8204-79e2a2a4606b · outbound

This paper cites Proximal Policy Optimization Algorithms.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Proximal Policy Optimization Algorithms

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.921502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f039705-4656-4b94-8dfe-0fa5e4a2df2b · outbound

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

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.926196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0f34d5e-7215-45a8-a781-3358ef13b455 · outbound

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

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation HybridFlow: A Flexible and Efficient RLHF Framework

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.931344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c91d0b00-6ba4-407d-9136-bf043f5db81e · outbound

This paper cites Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.935373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1e7ee22-279d-4e3f-b327-ce76786d6063 · outbound

This paper cites Maximum likelihood reinforcement learning.arXiv preprint arXiv:2602.02710, 2026.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Maximum likelihood reinforcement learning.arXiv preprint arXiv:2602.02710, 2026

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.940136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3f0d3d6-0693-4bf6-9d57-009fef5ea153 · outbound

This paper cites Vl-rethinker: Incentivizing self- reflection of vision-language models with reinforcement learning.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Vl-rethinker: Incentivizing self- reflection of vision-language models with reinforcement learning

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:29:04.844077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5b43ec2a-b9e5-4ed5-a44e-8c85cc8456b3 · outbound

This paper cites Sota with less: Mcts-guided sample selection for data-efficient visual reasoning self-improvement.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Sota with less: Mcts-guided sample selection for data-efficient visual reasoning self-improvement

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:29:04.830899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 002ece37-9b4a-47f5-9574-3e38074cefb9 · outbound

This paper cites Thoughts are all over the place: On the underthinking of long reasoning models.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Thoughts are all over the place: On the underthinking of long reasoning models

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:29:04.812235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5eaaa617-1b79-453c-91ba-0f1d303e262f · outbound

This paper cites Sportr: A benchmark for multimodal large language model reasoning in sports, 2026.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Sportr: A benchmark for multimodal large language model reasoning in sports, 2026

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.957406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d40d4dbe-5ab3-4b13-98ad-cca8b8785645 · outbound

This paper cites Proxythinker: Test-time guidance through small visual reasoners.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Proxythinker: Test-time guidance through small visual reasoners

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:29:04.797570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 2e12425e-c792-4fb2-82e7-bcae2d64769a · outbound

This paper cites Qwen3 Technical Report.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Qwen3 Technical Report

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.965787Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3a193c2-0a9a-41db-833d-8db2ba8ccc8a · outbound

This paper cites DAPO: An open-source LLM reinforcement learning system at scale.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation DAPO: An open-source LLM reinforcement learning system at scale

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.970117Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d210592-509d-4f11-8a92-9c657cc31ef6 · outbound

This paper cites STar: Bootstrapping reasoning with reasoning.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation STar: Bootstrapping reasoning with reasoning

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.974838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b00b7bd6-e5af-4951-b3f8-389e1fe0f17d · outbound

This paper cites KAT-V1: Kwai-AutoThink Technical Report.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation KAT-V1: Kwai-AutoThink Technical Report

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T20:29:03.979079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b41180f-ec8e-476d-ad7e-6b1f00cae5c5 · outbound

This paper cites Reinforcing general reasoning without verifiers.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Reinforcing general reasoning without verifiers

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:29:04.757871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation bb7d2340-b2b4-46a5-866f-c891faa92bc3 · outbound

This paper cites an unresolved cited work.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Unresolved cited work

Reference 2024

Resolution: unresolved; raw_fallback, observed 2026-08-11T20:29:04.871224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 0ab855d8-2657-4615-997b-dada58adeac7 · outbound

This paper cites Please reason step by step, and put your final answer within \boxed{}.

SoftmaxGRPO: Learning to Reason using Softmax Advantage Group Estimation Please reason step by step, and put your final answer within \boxed{}

Reference 2026

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T20:29:04.742339Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Pith citing papers

No inbound Pith citation observations are available.