ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples | Paper Citation Record

Observation 0e4e57c1-b755-49ca-a60a-fa13eeb3b440 · outbound

This paper cites OpenAI o1 System Card.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples OpenAI o1 System Card

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:23.928177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 450c0916-6b95-4f93-9157-9fdf49aee130 · outbound

This paper cites Nature , volume =.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Nature , volume =

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:24.006590Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e10c48c1-b611-4d29-88b3-ecf63eb507da · outbound

This paper cites DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:24.088146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2340d31-664f-444e-90bb-5f6515277157 · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:24.173789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64a91aa6-9641-4b7c-8eed-7f521c90c960 · outbound

This paper cites Qwen3 Technical Report.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Qwen3 Technical Report

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:24.240938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 360b6a8f-6196-442f-b298-6d016242c44c · outbound

This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:24.296105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7e73dca-5877-4ff9-be43-1fb21fe231ba · outbound

This paper cites 2024 , eprint=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples 2024 , eprint=

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:24.367087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 104fd3d2-3d38-4978-896d-7c756d512d2f · outbound

This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:24.456293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac960a03-5beb-4333-ae8a-a92078c66deb · outbound

This paper cites Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:24.544737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd2cf552-6097-47ec-87ef-e3049d793cd4 · outbound

This paper cites Proximal Policy Optimization Algorithms.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Proximal Policy Optimization Algorithms

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:24.608784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 986de566-4ebb-4d99-add4-7fd0c747c883 · outbound

This paper cites International conference on machine learning , pages=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples International conference on machine learning , pages=

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:24.718817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1def997a-e4da-48fa-b1cd-a2048e2d81e7 · outbound

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

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples High-Dimensional Continuous Control Using Generalized Advantage Estimation

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:24.802584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf3897f7-3cf1-4dd2-8641-827a86680b12 · outbound

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

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:24.906088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dca93f1-90c3-4970-bf38-5bce292e677c · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:24.982944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d398004d-dca2-4410-b88d-32b70387c35b · outbound

This paper cites Understanding R1-Zero-Like Training: A Critical Perspective.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Understanding R1-Zero-Like Training: A Critical Perspective

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:25.052567Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56514245-048e-4c88-a373-e180751db1be · outbound

This paper cites arXiv preprint arXiv:2507.20673 , year=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples arXiv preprint arXiv:2507.20673 , year=

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:25.055939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8522327a-21c8-42ba-924a-983938f2330c · outbound

This paper cites 2025 , eprint=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples 2025 , eprint=

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:25.058589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 786d679e-0833-4e47-a0a1-ed845b8e4855 · outbound

This paper cites Group Sequence Policy Optimization.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Group Sequence Policy Optimization

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:25.134121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1de4cc21-8ae0-4c05-b957-4778999137c0 · outbound

This paper cites Your Efficient RL Framework Secretly Brings You Off-Policy RL Training , url =.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Your Efficient RL Framework Secretly Brings You Off-Policy RL Training , url =

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:25.298585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4c92e99-8e6f-4e18-a5d5-b5e39c27a706 · outbound

This paper cites When Speed Kills Stability: Demystifying.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples When Speed Kills Stability: Demystifying

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:25.446955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8aaa4bc6-f4aa-421c-9d84-a588d0c4a3fb · outbound

This paper cites 2025 , eprint=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples 2025 , eprint=

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:25.588238Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7960eeb-f82d-4099-8439-dedf72049e49 · outbound

This paper cites 2025 , eprint=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples 2025 , eprint=

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:25.770620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d271953-69c3-468e-ae90-1b7a0bc3e4af · outbound

This paper cites Small Leak Can Sink a Great Ship--Boost RL Training on MoE with IcePop! , url =.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Small Leak Can Sink a Great Ship--Boost RL Training on MoE with IcePop! , url =

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:25.894447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bbb3002-cd38-4609-962a-455a163933af · outbound

This paper cites Reward Hacking in Reinforcement Learning.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Reward Hacking in Reinforcement Learning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:26.043996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce7b66e2-fe00-47f2-9e65-f8d5409ac127 · outbound

This paper cites International Conference on Machine Learning , pages=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples International Conference on Machine Learning , pages=

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:26.169322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5181479d-b2d4-4764-b6a3-63147c4bdc3e · outbound

This paper cites an unresolved cited work.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:26.324565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75e1e575-ceae-4910-b4be-8f1b294b5501 · outbound

This paper cites arXiv preprint arXiv:2510.22543 , year=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples arXiv preprint arXiv:2510.22543 , year=

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:26.485479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6ee98a5-88fd-4b88-afd1-bd1fff59d1b6 · outbound

This paper cites Why Language Models Hallucinate.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Why Language Models Hallucinate

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:26.610302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 644ec384-f034-42a5-b532-3af159802735 · outbound

This paper cites arXiv preprint arXiv:2509.09177 , year=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples arXiv preprint arXiv:2509.09177 , year=

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:26.753190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1f20914-edae-452f-bf14-017970f5e5bf · outbound

This paper cites arXiv preprint arXiv:2508.17850 , year=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples arXiv preprint arXiv:2508.17850 , year=

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:26.879211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c05e314c-dd90-4047-aaac-b1b841762423 · outbound

This paper cites Advances in Neural Information Processing Systems (NeurIPS) , volume=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Advances in Neural Information Processing Systems (NeurIPS) , volume=

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:27.022813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a741d53-da2c-4f08-9894-e3d11f428091 · outbound

This paper cites Advances in neural information processing systems , volume=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Advances in neural information processing systems , volume=

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:27.135881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52d4cd12-08db-4a46-9185-101a8416eb73 · outbound

This paper cites On a few pitfalls in KL divergence gradient estimation for RL.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples On a few pitfalls in KL divergence gradient estimation for RL

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:27.338911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8268c740-42ef-4ac1-8371-7bfda21e2a1e · outbound

This paper cites arXiv preprint arXiv:2512.21852 , year=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples arXiv preprint arXiv:2512.21852 , year=

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:27.495012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2250deb4-8107-49ac-9686-a8c2265794d8 · outbound

This paper cites arXiv preprint arXiv:2510.20817 , year=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples arXiv preprint arXiv:2510.20817 , year=

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:27.584045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 791ae013-e99d-4e5c-9fe0-14095100ee33 · outbound

This paper cites Beyond Reverse.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Beyond Reverse

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:27.635901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a94f418-4dc3-47e1-900f-7c6878ac2504 · outbound

This paper cites First Conference on Language Modeling , year=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples First Conference on Language Modeling , year=

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:27.740294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e73d123-5477-4d87-b305-e231911add6d · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Advances in Neural Information Processing Systems , volume=

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:27.805767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf03e8f2-4be6-42ff-8570-0a3750bf6877 · outbound

This paper cites 2021 , eprint=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples 2021 , eprint=

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:27.878462Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0af955a8-16ca-4abe-8d0d-10a7dafbf55a · outbound

This paper cites Does Reinforcement Learning Really Incentivize Reasoning Capacity in.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Does Reinforcement Learning Really Incentivize Reasoning Capacity in

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:27.968153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d932ad8-5103-4abf-8d8e-3a68b7e1d25b · outbound

This paper cites The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples The Entropy Mechanism of Reinforcement Learning for Reasoning Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:28.043198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6f435ce-a6d7-4e87-9064-dc2720359b4f · outbound

This paper cites Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:28.120890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12a94e09-3547-486a-90a6-3ad997509fb6 · outbound

This paper cites 2023 , cdate=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples 2023 , cdate=

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:28.195301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cfdfc1eb-6ad9-477e-8379-337302f35f1e · outbound

This paper cites Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:28.266130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53f87756-ad26-448a-93e4-ff1191eadeb9 · outbound

This paper cites Learning to Reason under Off-Policy Guidance.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Learning to Reason under Off-Policy Guidance

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:28.362049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7de04c6c-5efd-4ba3-ab2a-02f49bb48455 · outbound

This paper cites arXiv preprint arXiv:2506.07527 , year=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples arXiv preprint arXiv:2506.07527 , year=

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:28.452592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e7b7907b-ccc5-4b9b-be3f-b7943ba9f25f · outbound

This paper cites SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples SRFT: A Single-Stage Method with Supervised and Reinforcement Fine-Tuning for Reasoning

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:28.545828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebad1479-c453-443e-9776-30c06c72f2f6 · outbound

This paper cites arXiv preprint arXiv:2509.04419 , year=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples arXiv preprint arXiv:2509.04419 , year=

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:28.622105Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35b8c770-1527-4917-8fb3-60869d0916a8 · outbound

This paper cites RePO: Replay-Enhanced Policy Optimization.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples RePO: Replay-Enhanced Policy Optimization

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:28.717603Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6ba5694-badf-4fad-8793-20ff8e40f96b · outbound

This paper cites Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:28.818300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb6a0f3c-58e8-49d2-94f5-7c88251d8adf · outbound

This paper cites arXiv preprint arXiv:2510.02245 , year=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples arXiv preprint arXiv:2510.02245 , year=

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:28.913789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e769e426-7214-4d05-bd84-4105242bdd2e · outbound

This paper cites RLEP: Reinforcement Learning with Experience Replay for LLM Reasoning.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples RLEP: Reinforcement Learning with Experience Replay for LLM Reasoning

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:29.013207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7fe8cac-6531-4408-99c4-1bd10dd168f0 · outbound

This paper cites Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:29.108343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8577ebe5-249b-4800-bb18-c975f86e57a1 · outbound

This paper cites arXiv preprint arXiv:2510.03865 , year=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples arXiv preprint arXiv:2510.03865 , year=

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:29.154734Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44e25a45-8a51-4105-a098-e97129606755 · outbound

This paper cites arXiv preprint arXiv:2509.07430 , year=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples arXiv preprint arXiv:2509.07430 , year=

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:29.245333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd617188-aaca-41c7-8cff-f6e816320646 · outbound

This paper cites The Twelfth International Conference on Learning Representations , year=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples The Twelfth International Conference on Learning Representations , year=

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:29.404192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b022685-e7d2-4fbb-aa66-842bfd501e22 · outbound

This paper cites MiMo-V2-Flash Technical Report.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples MiMo-V2-Flash Technical Report

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:29.526424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28cdf359-2843-4333-b14d-b21f1a92d30f · outbound

This paper cites arXiv preprint arXiv:2603.22117 , year=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples arXiv preprint arXiv:2603.22117 , year=

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:29.693770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 682775fd-3a03-44a7-aa4c-dab4e66ddea5 · outbound

This paper cites arXiv preprint arXiv:2603.19835 , year=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples arXiv preprint arXiv:2603.19835 , year=

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:29.817926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06234128-6f8c-46a4-a1cf-4929522df424 · outbound

This paper cites arXiv preprint arXiv:2603.22446 , year=.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples arXiv preprint arXiv:2603.22446 , year=

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:29.943795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79e6168e-577f-4be5-ba8a-bb1cfab2dcca · outbound

This paper cites Experience Augmented Policy Optimization for LLM Reasoning.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Experience Augmented Policy Optimization for LLM Reasoning

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:30.079906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b5031bc-8e80-4294-bedd-c73a5983a727 · outbound

This paper cites One-Way Policy Optimization for Self-Evolving LLMs.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples One-Way Policy Optimization for Self-Evolving LLMs

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:30.215870Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50e9359a-fb92-42cc-a5c2-a388db996a82 · outbound

This paper cites Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals.

ARMOR: Stabilizing On-Policy LLM RL with Off-Policy Anchor Samples Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-02T07:23:30.344213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers