Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training | Paper Citation Record

Observation dde255fb-69d9-47bf-93b2-26ae663bc741 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.097425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b1004d0-8e86-4ba0-acc9-a77fabcfbf68 · outbound

This paper cites Qwen3: Think deeper, act faster.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Qwen3: Think deeper, act faster

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.101934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cb870a0-b175-494b-89ab-175ec8b24a55 · outbound

This paper cites Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.106030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0db09e6-e810-44d4-abf1-02bfcfc35d30 · outbound

This paper cites Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.109851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4783dcac-fb81-4275-ae38-5fd299f47c15 · outbound

This paper cites OpenAI o1 System Card.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training OpenAI o1 System Card

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.113465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e3c4d21-5be9-48e6-b420-5b18ebe0fa3d · outbound

This paper cites A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.117726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fe73304-4756-4f24-9074-56cf2419473f · outbound

This paper cites A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.123183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57d758f3-1b97-4d4c-9d63-46d981c56be9 · outbound

This paper cites Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.126406Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81a47dd3-d873-4495-8988-dc53c18df9fa · outbound

This paper cites Efficient reasoning models: A survey.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Efficient reasoning models: A survey

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.129950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06417ac6-4910-4b6a-9e4d-268a7dda7ebb · outbound

This paper cites A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training A Survey of Slow Thinking-based Reasoning LLMs using Reinforced Learning and Inference-time Scaling Law

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.133968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae20b146-0fc1-4cc3-af29-4eb8d57cdb3f · outbound

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

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training A survey of efficient reasoning for large reasoning models: Language, multimodality, and beyond

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.137934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f65cceea-64dd-4e52-a487-2a64bd7ad22d · outbound

This paper cites Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.140959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d505850f-8613-428d-92aa-6b3fe65699c6 · outbound

This paper cites Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Harnessing the Reasoning Economy: A Survey of Efficient Reasoning for Large Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.144176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b60d7ca0-91c5-4675-9c4f-cf8428f4c72a · outbound

This paper cites Effectively Controlling Reasoning Models through Thinking Intervention.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Effectively Controlling Reasoning Models through Thinking Intervention

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.148359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a37d5ae-d437-49e7-b5da-fe587ff80238 · outbound

This paper cites Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoning.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.152249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8c25046-715d-449f-a15b-5b191ea71827 · outbound

This paper cites DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.155796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dc9d088-f9ff-4413-bb47-904575b278b9 · outbound

This paper cites DeepSeek-V3 Technical Report.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training DeepSeek-V3 Technical Report

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.159139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c206e5a1-23d3-4b36-8897-683c6425109e · outbound

This paper cites Openmoe: An early effort on open mixture-of-experts language models.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Openmoe: An early effort on open mixture-of-experts language models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.162750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c990ef0d-fcc4-4993-9f05-81e58639c231 · outbound

This paper cites Working memory revived in older adults by synchronizing rhythmic brain circuits.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Working memory revived in older adults by synchronizing rhythmic brain circuits

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.165766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b7a775e-ae93-4b40-8181-20ffd9316f43 · outbound

This paper cites Neurocognitive, physiological, and biophysical effects of transcranial alternating current stimulation.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Neurocognitive, physiological, and biophysical effects of transcranial alternating current stimulation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.168743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d17cbb26-00f2-4e3f-a922-56a8d91ed203 · outbound

This paper cites Non-invasively targeting, probing and modulating a deep brain circuit for depression alleviation.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Non-invasively targeting, probing and modulating a deep brain circuit for depression alleviation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.172423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1184e70-71e2-4c89-b1b1-522fdb5efd50 · outbound

This paper cites High-frequency neuromodulation improves obsessive--compulsive behavior.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training High-frequency neuromodulation improves obsessive--compulsive behavior

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.175651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 545a8398-fcec-43c7-b945-6dee6d11de97 · outbound

This paper cites Normalized (pointwise) mutual information in collocation extraction.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Normalized (pointwise) mutual information in collocation extraction

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.179680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a989082-7d23-4866-bb14-cfc11d4a0626 · outbound

This paper cites Probing Semantic Routing in Large Mixture-of-Expert Models.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Probing Semantic Routing in Large Mixture-of-Expert Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.182908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5dcdb0a-850b-4959-afec-a43d3f4b3289 · outbound

This paper cites Aime problems and solutions.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Aime problems and solutions

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.187353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bdc1b01-9dba-49fc-89cb-5c654b19086f · outbound

This paper cites an unresolved cited work.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.191573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7d0f578-3ee1-4e05-a0dc-10afd508885d · outbound

This paper cites From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.195570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8d377b7-92dc-41a7-bb44-ead145118e50 · outbound

This paper cites Generative AI Act II: Test Time Scaling Drives Cognition Engineering.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Generative AI Act II: Test Time Scaling Drives Cognition Engineering

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.199466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e50066b5-1817-45f6-a1cd-4897491e5557 · outbound

This paper cites Qwq: Reflect deeply on the boundaries of the unknown.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Qwq: Reflect deeply on the boundaries of the unknown

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.203634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 874b3349-7f6b-497e-b1ae-1d942749facb · outbound

This paper cites Claude 3.7 sonnet.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Claude 3.7 sonnet

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.206752Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8843a690-5b26-41b2-ad6e-60025642029c · outbound

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

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.210382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cea28f27-83b8-4804-a994-4846600618d7 · outbound

This paper cites an unresolved cited work.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Unresolved cited work

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.213155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f6994b1-f328-45bc-8184-b65ecc33ec7a · outbound

This paper cites The llama 4 herd: The beginning of a new era of natively multimodal ai innovation.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training The llama 4 herd: The beginning of a new era of natively multimodal ai innovation

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.216185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d150de9-74ed-4206-9810-1cea3a9a15db · outbound

This paper cites OLMoE: Open Mixture-of-Experts Language Models.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training OLMoE: Open Mixture-of-Experts Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.219070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d1d7fcb-05d2-45dd-96bc-5ae5793625d6 · outbound

This paper cites Le, Geoffrey E.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Le, Geoffrey E

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.222795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11723429-ce56-481e-bf43-948f023e8b90 · outbound

This paper cites Mixture of Tunable Experts -- Behavior Modification of DeepSeek-R1 at Inference Time.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Mixture of Tunable Experts -- Behavior Modification of DeepSeek-R1 at Inference Time

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.226587Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2c38890-4b3d-4cbf-8d23-c8c4b35b65ec · outbound

This paper cites Under the hood of a reasoning model.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Under the hood of a reasoning model

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.230426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdff6091-894d-47a2-9361-38318dccc481 · outbound

This paper cites Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.233904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3599f3c2-c32f-4c1b-9b91-08c8c01615e6 · outbound

This paper cites The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.237359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca3d24b8-33bf-48f6-950d-d073526d2b13 · outbound

This paper cites Trading Inference-Time Compute for Adversarial Robustness.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Trading Inference-Time Compute for Adversarial Robustness

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.241064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb42e7d4-88d1-4b98-a70c-9a1a12e0f147 · outbound

This paper cites The relationship between reasoning and performance in large language models--o3 (mini) thinks harder, not longer.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training The relationship between reasoning and performance in large language models--o3 (mini) thinks harder, not longer

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.244296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b2b8ab6-f233-4d67-893c-1e784f71941c · outbound

This paper cites Learning to Stop Overthinking at Test Time.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Learning to Stop Overthinking at Test Time

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.248333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0eef2f8d-8868-4796-b00b-0a76d99d611e · outbound

This paper cites Dynamic Parallel Tree Search for Efficient LLM Reasoning.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Dynamic Parallel Tree Search for Efficient LLM Reasoning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.251549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa462b08-872f-457b-96c4-99548657c1f1 · outbound

This paper cites Can Atomic Step Decomposition Enhance the Self-structured Reasoning of Multimodal Large Models?.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Can Atomic Step Decomposition Enhance the Self-structured Reasoning of Multimodal Large Models?

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.256005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a40f1f38-edaf-4ab6-b4b3-435222c6dbad · outbound

This paper cites Reasoning Models Can Be Effective Without Thinking.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Reasoning Models Can Be Effective Without Thinking

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.259987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d26b707b-19cd-40f1-af7d-85666a99ddf2 · outbound

This paper cites s1: Simple test-time scaling.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training s1: Simple test-time scaling

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.263321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0de894f-502b-4ab2-9710-ef5f52d0ae58 · outbound

This paper cites Token-Budget-Aware LLM Reasoning.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Token-Budget-Aware LLM Reasoning

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.266706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddf7d854-3cc9-4a7e-a8b5-cc892e465656 · outbound

This paper cites Aytes, Jinheon Baek, and Sung Ju Hwang.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Aytes, Jinheon Baek, and Sung Ju Hwang

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.270087Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 920b4382-3696-4fc2-a1c0-e3937411a2bd · outbound

This paper cites Lightthinker: Thinking step-by-step compression.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Lightthinker: Thinking step-by-step compression

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.273270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59372352-24a5-439e-a24c-4eb217982bc5 · outbound

This paper cites Seal: Steerable reasoning calibration of large language models for free.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Seal: Steerable reasoning calibration of large language models for free

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.276350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 211e0d5a-ec77-4f57-9028-ae44158348f6 · outbound

This paper cites Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.279507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5de77e3d-851e-4323-808f-0ca3b53aa012 · outbound

This paper cites Thinkedit: Interpretable weight editing to mitigate overly short thinking in reasoning models.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Thinkedit: Interpretable weight editing to mitigate overly short thinking in reasoning models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.283460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06a73e45-0374-4964-984f-18b422e6f7fd · outbound

This paper cites LIMO: Less is More for Reasoning.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training LIMO: Less is More for Reasoning

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.287504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bce3938-2fec-42c9-8b12-b0a81ee85ddd · outbound

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

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.290884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ca71676-a3cc-45af-b056-808f460aa723 · outbound

This paper cites Training Large Language Models to Reason in a Continuous Latent Space.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Training Large Language Models to Reason in a Continuous Latent Space

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.294059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bab0c8e-bce7-46b5-aec0-628e49a04412 · outbound

This paper cites C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training C3PO: Critical-Layer, Core-Expert, Collaborative Pathway Optimization for Test-Time Expert Re-Mixing

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.297512Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 413e6c4f-a0ef-4bf0-8058-7d9f858e2d28 · outbound

This paper cites Unveiling Hidden Collaboration within Mixture-of-Experts in Large Language Models.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Unveiling Hidden Collaboration within Mixture-of-Experts in Large Language Models

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-08-07T15:36:06.897941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 74c62790-e0fe-4152-bc5b-56ac50717ced · outbound

This paper cites @esa (Ref.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training @esa (Ref

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.304924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cbca74a-98a1-415f-85ad-e34903769a76 · outbound

This paper cites an unresolved cited work.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Unresolved cited work

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.308588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85696020-767c-4186-ba30-4a7059a76822 · outbound

This paper cites an unresolved cited work.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Unresolved cited work

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.312141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5668d442-49b1-4bcc-94a6-b89a4d34bfd5 · outbound

This paper cites an unresolved cited work.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Unresolved cited work

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.315624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21abcae5-f18a-4f40-b107-0720c7b7cd6f · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.318473Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20a64d52-2935-47af-b9c1-a553aa111a4b · outbound

This paper cites GPT-4 Technical Report.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training GPT-4 Technical Report

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.321890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09662989-9801-4a1f-a2ad-27e8eee8589a · outbound

This paper cites COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.325426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52a9be16-ce12-44b2-adee-e2b3b92fdbcd · outbound

This paper cites Comprehensive Exploration of Synthetic Data Generation: A Survey.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Comprehensive Exploration of Synthetic Data Generation: A Survey

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.328740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5aa4bde-b879-4805-9a29-7d54defcacc7 · outbound

This paper cites DeepSeek LLM: Scaling Open-Source Language Models with Longtermism.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training DeepSeek LLM: Scaling Open-Source Language Models with Longtermism

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.332583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f90a61bc-80c7-44b3-b79d-3bf89ca6a168 · outbound

This paper cites On the resemblance and containment of documents.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training On the resemblance and containment of documents

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.335828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d88b97c-7e2b-4861-9c60-b23408cca9f8 · outbound

This paper cites Large Language Models as Tool Makers.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Large Language Models as Tool Makers

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.338637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afa15b21-dbdf-4136-ba27-ff584da8e596 · outbound

This paper cites On the Possibilities of AI-Generated Text Detection.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training On the Possibilities of AI-Generated Text Detection

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.342022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21b7229e-1fbf-4a27-b830-66a15c5cadb5 · outbound

This paper cites Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.345351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1405ed2e-a45e-4470-84b2-701684b1d8bb · outbound

This paper cites Picle: Eliciting diverse behaviors from large language models with persona in-context learning.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Picle: Eliciting diverse behaviors from large language models with persona in-context learning

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.349742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a51461d-e2dd-4efe-b594-ce34873f2643 · outbound

This paper cites Redpajama: an open dataset for training large language models, 2023.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Redpajama: an open dataset for training large language models, 2023

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.352562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7413d78d-95e2-4d9f-acd9-2984b93bf6d5 · outbound

This paper cites Language Modeling Is Compression.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Language Modeling Is Compression

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.356177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ae4fb71-06e8-49bc-8eca-89de8e887beb · outbound

This paper cites A Tale of Tails: Model Collapse as a Change of Scaling Laws.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training A Tale of Tails: Model Collapse as a Change of Scaling Laws

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.359664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4faf4db1-debf-4a2f-8ddc-b2fc06b7122e · outbound

This paper cites Strategic Reasoning with Language Models.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Strategic Reasoning with Language Models

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.362578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d726a659-b00e-4df7-aaf4-a2d1286460d4 · outbound

This paper cites In-context autoencoder for context compression in a large language model.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training In-context autoencoder for context compression in a large language model

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.366714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7192de9-1256-4ad8-b904-268727dd568d · outbound

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

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Measuring Mathematical Problem Solving With the MATH Dataset

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.369829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06432e54-e417-44d7-9902-2eb4ccfde470 · outbound

This paper cites Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.373531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b5bc89c-99c8-4400-b84a-031101db309c · outbound

This paper cites Faithful Persona-based Conversational Dataset Generation with Large Language Models.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Faithful Persona-based Conversational Dataset Generation with Large Language Models

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.376808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee75c507-c25e-4733-9c31-0d82864e5e88 · outbound

This paper cites Scaling Laws for Neural Language Models.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Scaling Laws for Neural Language Models

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.380190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 560a043a-ec6b-49b2-a8fe-9d6f48442fb0 · outbound

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

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Common 7B Language Models Already Possess Strong Math Capabilities

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.383838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fe56072-f9ae-47de-be6a-3ad2ccabe180 · outbound

This paper cites Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.387394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e659dce-8972-4e91-98ea-2f1ccbee1ba5 · outbound

This paper cites On the steerability of large language models toward data-driven personas.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training On the steerability of large language models toward data-driven personas

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.391546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71e9b821-fd5c-42ee-b616-ab7b1d148288 · outbound

This paper cites Textbooks Are All You Need II: phi-1.5 technical report.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Textbooks Are All You Need II: phi-1.5 technical report

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.394612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8edad706-d3c8-40b0-8ebf-6afbea63334e · outbound

This paper cites Best Practices and Lessons Learned on Synthetic Data.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Best Practices and Lessons Learned on Synthetic Data

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.398779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cf7383f-98b0-4199-9d5c-07e4f4053c91 · outbound

This paper cites A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.402644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f419473-e6d6-437e-a476-a105c49ab2c8 · outbound

This paper cites Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.407101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d04cee5b-e914-4db7-827a-78d179741f41 · outbound

This paper cites On the Risk of Misinformation Pollution with Large Language Models.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training On the Risk of Misinformation Pollution with Large Language Models

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.410393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a14e6e12-d476-42c7-8230-441855efed1c · outbound

This paper cites Generative agents: Interactive simulacra of human behavior.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Generative agents: Interactive simulacra of human behavior

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.413628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f46e2c8-64e6-4053-893a-9ff517eac8c5 · outbound

This paper cites Toolformer: Language models can teach themselves to use tools.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Toolformer: Language models can teach themselves to use tools

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.416532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd91a9fb-20eb-4044-91e3-eb6fc23421de · outbound

This paper cites Role play with large language models.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Role play with large language models

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.420215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0096578c-eaad-445a-a237-1b52dcfc26c4 · outbound

This paper cites The Curse of Recursion: Training on Generated Data Makes Models Forget.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training The Curse of Recursion: Training on Generated Data Makes Models Forget

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.423517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6391e0cf-ee5e-4b28-9c9a-685b4e98ca96 · outbound

This paper cites Introducing qwen1.5, February 2024.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Introducing qwen1.5, February 2024

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:36:07.503540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f15f7804-c85e-479e-974a-1e584c3f7231 · outbound

This paper cites An experimental study of the small world problem.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training An experimental study of the small world problem

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:36:07.494829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 99162bc3-e811-43b2-9a9d-b354e8315ef5 · outbound

This paper cites Position: Will we run out of data? limits of llm scaling based on human-generated data.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Position: Will we run out of data? limits of llm scaling based on human-generated data

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.433028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ac6abfd-775f-4358-9e43-fbd191d1ff3e · outbound

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

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.435967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d40511d-7006-4ef1-aa8d-2ef011792d77 · outbound

This paper cites Self-Instruct: Aligning Language Models with Self-Generated Instructions.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Self-Instruct: Aligning Language Models with Self-Generated Instructions

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.439307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4788c87d-1a02-44d3-86ac-ed09f94eb227 · outbound

This paper cites Unleashing the emergent cognitive synergy in large language models: A task-solving agent through multi-persona self-collaboration.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Unleashing the emergent cognitive synergy in large language models: A task-solving agent through multi-persona self-collaboration

Reference 98

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:36:07.480301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 21b16f2e-9ee1-4108-a381-27e20d616894 · outbound

This paper cites Hallucination is Inevitable: An Innate Limitation of Large Language Models.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Hallucination is Inevitable: An Innate Limitation of Large Language Models

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.445499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 110233b7-af77-46b2-9ff7-b83af62e853a · outbound

This paper cites Yi: Open Foundation Models by 01.AI.

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training Yi: Open Foundation Models by 01.AI

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-07T15:36:06.449701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers