Paper Citation Record · LEDGER

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

As of 15 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 15 inbound Pith citation observations for arXiv:2505.14810.

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

pith.paper-citation-record.v1
2505.14810 v2

Coverage vector

measured 54 of 54 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:33:14.622826Z

measured 69 of 69 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 15 of 15 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-15T17:56:41.028809Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T01:27:30.780707Z

Reference resolution

54 of 54 outbound references displayed

verified exact0
verified fuzzy8
unresolved45
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 44568d9e-23c9-485f-8e98-0824b2d06ecf · outbound

This paper cites A survey of efficient reasoning for large reasoning models: Language, multimodality, and beyond.arXiv preprint arXiv:2503.21614, 2025.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models A survey of efficient reasoning for large reasoning models: Language, multimodality, and beyond.arXiv preprint arXiv:2503.21614, 2025

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.157381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65eaa0d6-7f87-479e-9758-3cc235820994 · outbound

This paper cites Introducing openai o3 and o4-mini.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Introducing openai o3 and o4-mini

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:17.316784Z

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 47a35041-50e0-4fdc-8ffb-97c75c48fe23 · outbound

This paper cites Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.246442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c7a2c4f-99c9-4c9a-ae76-32bfbf88e23c · outbound

This paper cites an unresolved cited work.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.307082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b26cc8b-3281-4877-8961-b99584ef6053 · outbound

This paper cites Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems, 2024.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Olympiadbench: A challenging benchmark for promoting agi with olympiad-level bilingual multimodal scientific problems, 2024

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.370272Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9b5b964-b0ef-4d25-b0a2-003cf15c219e · outbound

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

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Measuring Mathematical Problem Solving With the MATH Dataset

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.452157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b153dfa-26f1-4809-be95-e2b9b1e63776 · outbound

This paper cites Aime problem set 1983-2024, 2023.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Aime problem set 1983-2024, 2023

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.518270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dd24725-91cb-47cd-b3a2-efc412a34f00 · outbound

This paper cites an unresolved cited work.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.568995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18bd3729-b3b4-4c53-b40a-9fd402adf3d2 · outbound

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

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Chain-of-thought prompting elicits reasoning in large language models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.639989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 242ded00-ce83-493d-b0a4-cd4920915107 · outbound

This paper cites Crossing the reward bridge: Expanding rl with verifiable rewards across diverse domains, 2025.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Crossing the reward bridge: Expanding rl with verifiable rewards across diverse domains, 2025

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:17.080686Z

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 f6dd2e34-7add-447c-b744-8234be23c9b3 · outbound

This paper cites A survey on llm-as-a-judge, 2025.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models A survey on llm-as-a-judge, 2025

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.783973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a33b4e24-dc98-45f0-a3e2-f428740bf069 · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Instruction-Following Evaluation for Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.861362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e794753-fe77-449e-8d01-208d32f78d11 · outbound

This paper cites FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models FollowBench: A Multi-level Fine-grained Constraints Following Benchmark for Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.940404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5964b2cc-872b-4985-9287-f2872170f483 · outbound

This paper cites s1: Simple test-time scaling.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models s1: Simple test-time scaling

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:10.981211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb7d4fd3-53a1-4468-a2f1-8d85f9fd58e9 · outbound

This paper cites Limo: Less is more for reasoning, 2025.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Limo: Less is more for reasoning, 2025

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:11.057906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d988746a-3274-4130-af2b-b319f12ac6f4 · outbound

This paper cites Demystifying long chain-of-thought reasoning in llms, 2025.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Demystifying long chain-of-thought reasoning in llms, 2025

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:11.148146Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27eceab6-b648-490e-8d28-ce69017e3b3d · outbound

This paper cites SFT memorizes, RL generalizes: A comparative study of foundation model post-training.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models SFT memorizes, RL generalizes: A comparative study of foundation model post-training

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:11.225305Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f344a563-8832-4594-b617-c98677f4577a · outbound

This paper cites There may not be aha moment in r1-zero-like training — a pilot study.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models There may not be aha moment in r1-zero-like training — a pilot study

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:11.311589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a25740f0-4537-4d6f-8f54-d60862085901 · outbound

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

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:11.407955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d772c21-66fd-496d-8fcd-fbe6ccde9a3d · outbound

This paper cites Process Reinforcement through Implicit Rewards.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Process Reinforcement through Implicit Rewards

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:11.486382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92ce5b9b-bf31-467e-aafe-b599b15e1fdb · outbound

This paper cites Learning to reason under off-policy guidance, 2025.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Learning to reason under off-policy guidance, 2025

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:11.560154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de45736f-69f1-464f-8f18-338b7dba298d · outbound

This paper cites Thinking Preference Optimization.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Thinking Preference Optimization

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:11.638080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0162cf0f-ef5e-40e7-bfb3-9c06587da67c · outbound

This paper cites Hashimoto.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Hashimoto

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:11.738840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a56b2ab7-afc0-4d9c-8d4e-716add35b17c · outbound

This paper cites Gonzalez, Ion Stoica, and Eric P.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Gonzalez, Ion Stoica, and Eric P

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:11.809584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd55063f-3abd-499a-95a8-4b6a268df8c6 · outbound

This paper cites FOFO: A benchmark to evaluate LLMs’ format-following capability.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models FOFO: A benchmark to evaluate LLMs’ format-following capability

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:16.800930Z

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 e94cee61-4939-4de0-b284-97e4471d10c5 · outbound

This paper cites an unresolved cited work.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:33:16.608320Z

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 8bb70e02-d4e0-48a9-bcff-a8cc018a5b53 · outbound

This paper cites Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:12.154089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17fbfcef-6d59-4686-aad8-7d66ebad32a5 · outbound

This paper cites StructFlowBench: A Structured Flow Benchmark for Multi-turn Instruction Following.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models StructFlowBench: A Structured Flow Benchmark for Multi-turn Instruction Following

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:12.228882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 022c8737-095b-40c0-96c4-b31b2ec9154c · outbound

This paper cites Can language models follow multiple turns of entangled instructions?arXiv preprint arXiv:2503.13222, 2025.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Can language models follow multiple turns of entangled instructions?arXiv preprint arXiv:2503.13222, 2025

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:12.305782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e46e7b3-0481-483d-8932-7b2ab6cebf05 · outbound

This paper cites MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:12.420401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28e29008-b9b2-4a36-879c-89128bc6f3d3 · outbound

This paper cites LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context Scenarios

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:12.524178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41151d93-1676-4dfb-97cf-ecc2cea02dcc · outbound

This paper cites Xifbench: Evaluating large language models on multilingual instruction following.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Xifbench: Evaluating large language models on multilingual instruction following

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:12.608031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbd99d66-e41f-4dc3-ac5d-80aa18f35783 · outbound

This paper cites IHEval: Evaluating language models on following the instruction hierarchy.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models IHEval: Evaluating language models on following the instruction hierarchy

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:16.432287Z

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 53abe998-55b1-4760-922b-e120406ac5de · outbound

This paper cites Chain-of-instructions: Compositional instruction tuning on large language models.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Chain-of-instructions: Compositional instruction tuning on large language models

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:16.265814Z

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 53656fb6-10c5-43f2-b5c3-cdc3f7ae0f64 · outbound

This paper cites RefuteBench: Evaluating refuting instruction-following for large language models.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models RefuteBench: Evaluating refuting instruction-following for large language models

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:16.093504Z

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 a81c3877-1496-43b9-8e72-46959fe21fe1 · outbound

This paper cites Refutebench 2.0 – agentic benchmark for dynamic evaluation of llm responses to refutation instruction, 2025.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Refutebench 2.0 – agentic benchmark for dynamic evaluation of llm responses to refutation instruction, 2025

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:15.938425Z

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 1dc49d07-536f-49d5-af35-f5ed750fec17 · outbound

This paper cites Benchmarking complex instruction-following with multiple constraints composition.Advances in Neural Information Processing Systems, 37:137610– 137645, 2024.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Benchmarking complex instruction-following with multiple constraints composition.Advances in Neural Information Processing Systems, 37:137610– 137645, 2024

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:13.132176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c15a7049-461a-4614-9ebf-2a802448278b · outbound

This paper cites GPT-4o System Card.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models GPT-4o System Card

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:13.201382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10907a57-b443-4eff-8db6-2aa6a0c68a11 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Training Verifiers to Solve Math Word Problems

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:13.276979Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3db8243-d059-40b1-8ece-eb9e9b71d518 · outbound

This paper cites Minerva: Accelerating data analysis in next-generation ssds.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Minerva: Accelerating data analysis in next-generation ssds

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:33:15.745229Z

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 81bdc687-70e6-4f71-af8d-29c061b47e1a · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Gonzalez, Hao Zhang, and Ion Stoica

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:13.429582Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11a41faa-a906-4367-b22e-7db1df5f14e5 · outbound

This paper cites Qwen3, April 2025.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Qwen3, April 2025

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:13.532662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55f2cf9e-82ae-4bbc-9a03-aa64511f35d8 · outbound

This paper cites SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:13.621188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79fa9c6b-3bd0-4099-9b08-824846a7d1f1 · outbound

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

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:13.735556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f49f2bd5-2c6d-4f20-8d8d-a2dddf292488 · outbound

This paper cites Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Li Erran Li, Raluca Ada Popa, and Ion Stoica.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Li Erran Li, Raluca Ada Popa, and Ion Stoica

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:13.835666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcec4b4d-7758-4c3d-9930-0c4c215f67e4 · outbound

This paper cites L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:13.910728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cac9504-c05f-4349-a0ec-c1b24cc81c41 · outbound

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

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:14.005401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6dc24a3-efa5-479b-adbe-fac5ed3701fe · outbound

This paper cites Open r1: A fully open reproduction of deepseek-r1, January 2025.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Open r1: A fully open reproduction of deepseek-r1, January 2025

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:14.083554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f43c058a-ad96-4a97-8379-471d5590d1fc · outbound

This paper cites Qwq-32b: Embracing the power of reinforcement learning, March 2025.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Qwq-32b: Embracing the power of reinforcement learning, March 2025

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:14.221930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79f0a2f6-98d9-45a0-ac80-fb90fb618d74 · outbound

This paper cites Open-reasoner-zero: An open source approach to scaling up reinforcement learning on the base model, 2025.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Open-reasoner-zero: An open source approach to scaling up reinforcement learning on the base model, 2025

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:14.341149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c73eeb6f-0dd0-42b2-85bc-58f3076f5df9 · outbound

This paper cites Roformer: Enhanced transformer with rotary position embedding.Neurocomputing, 568:127063, 2024.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Roformer: Enhanced transformer with rotary position embedding.Neurocomputing, 568:127063, 2024

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:14.438481Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bd12cc8-133b-4fd6-8560-9ffb777bc94e · outbound

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

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:14.543415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ebf27aa1-fe25-4327-a976-0eac331754cd · outbound

This paper cites The impact of reasoning step length on large language models.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models The impact of reasoning step length on large language models

Reference 53

Resolution: malformed identifier; raw_fallback, observed 2026-08-07T15:33:15.469178Z

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 2ff083fc-448b-4229-a8eb-0199ed4cec8c · outbound

This paper cites an unresolved cited work.

Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models Unresolved cited work

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-07T15:33:12.796349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 1e8854ce-8f38-4ae7-9e39-60f8befb076a · inbound

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

Learning to Reason under Off-Policy Guidance Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-05-15T23:17:02.898250Z

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 cd451d3a-100f-4632-acb7-9f442874c142 · inbound

Activation Steering for Chain-of-Thought Compression cites this paper.

Activation Steering for Chain-of-Thought Compression Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T19:46:47.158980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87a3f983-2e7c-44fb-b190-219dd66e7440 · inbound

Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey cites this paper.

Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T17:53:47.566505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08201b88-4bc2-466f-99b0-7405c37ae0b0 · inbound

The Policy Cliff: A Theoretical Analysis of Reward-Policy Maps in Large Language Models cites this paper.

The Policy Cliff: A Theoretical Analysis of Reward-Policy Maps in Large Language Models Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T17:56:41.028809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4143950-2e76-456e-a840-66278d750e9e · inbound

AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning cites this paper.

AutoTIR: Autonomous Tools Integrated Reasoning via Reinforcement Learning Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T12:23:55.086609Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6669c185-6eed-49d6-8c25-434a3bc8cafb · inbound

Evaluating Language Model Reasoning about Confidential Information cites this paper.

Evaluating Language Model Reasoning about Confidential Information Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-15T16:52:47.432140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df7b24f1-6691-41a3-8471-0b59b258279a · inbound

A Survey of Reinforcement Learning for Large Reasoning Models cites this paper.

A Survey of Reinforcement Learning for Large Reasoning Models Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

Reference 146

Resolution: verified exact; arxiv_id, observed 2026-05-18T00:02:25.397403Z

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 1244e1a4-09af-45f5-bc65-927153f45db9 · inbound

Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts cites this paper.

Retrieval-of-Thought: Efficient Reasoning via Reusing Thoughts Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-18T13:42:38.628885Z

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 cd80a8e1-9df3-4476-a93e-309dba05edbc · inbound

Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards cites this paper.

Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-18T14:26:28.356258Z

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 87d182f8-0347-494b-810b-8fad257b7d11 · inbound

Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards cites this paper.

Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-15T15:48:29.038311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b236504-6262-4cd1-b48f-05ee07634c87 · inbound

Reasoning Up the Instruction Ladder for Controllable Language Models cites this paper.

Reasoning Up the Instruction Ladder for Controllable Language Models Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T07:07:52.626304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 035981a2-0272-45d4-abc0-f931a2a19ce8 · inbound

ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following cites this paper.

ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

Reference 1

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T08:00:44.619454Z

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 5d43761b-0d0d-4906-a652-117b55d16885 · inbound

Expert-Aware Refusal Steering cites this paper.

Expert-Aware Refusal Steering Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-07-02T03:26:29.106120Z

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 a5be2a59-61f1-4517-b01d-8da2e092dabe · inbound

When Built-in Thinking Helps and Hurts: Constraint-Level Error Shifts in Instruction Following cites this paper.

When Built-in Thinking Helps and Hurts: Constraint-Level Error Shifts in Instruction Following Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T01:27:30.782222Z

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 f2244e3d-ae28-4746-96ff-a48ba458ff32 · inbound

Structured Thoughts For Improved Reasoning And Context Pruning cites this paper.

Structured Thoughts For Improved Reasoning And Context Pruning Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-14T12:08:05.502310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.