Efficient Reasoning on the Edge | Paper Citation Record

Observation e733315b-49b9-4d8d-ab82-b165f36eacd4 · outbound

This paper cites The claude 3 model family: Opus, sonnet, haiku.

Efficient Reasoning on the Edge The claude 3 model family: Opus, sonnet, haiku

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ca74055-f30c-45d4-8d74-027fad47d768 · outbound

This paper cites OpenAI o1 System Card.

Efficient Reasoning on the Edge OpenAI o1 System Card

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db947c1d-2fe2-4a2b-9c35-351b60fbfd5e · outbound

This paper cites an unresolved cited work.

Efficient Reasoning on the Edge Unresolved cited work

Reference 3

Resolution: parse uncertain; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fc2f093-d3c2-4311-8256-bfe399a15cea · outbound

This paper cites First proof.arXiv preprint arXiv:2602.05192, 5 February 2026.

Efficient Reasoning on the Edge First proof.arXiv preprint arXiv:2602.05192, 5 February 2026

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0eb6f198-ad5b-41ec-8b7b-2ecbbc93e5bd · outbound

This paper cites Evaluating frontier LLMs on PhD-level mathematical reasoning: A benchmark on a textbook in theoretical computer science about randomized algorithms.

Efficient Reasoning on the Edge Evaluating frontier LLMs on PhD-level mathematical reasoning: A benchmark on a textbook in theoretical computer science about randomized algorithms

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 287a434b-05de-4602-97b8-43e53cb71613 · outbound

This paper cites T owards autonomous mathematics research.

Efficient Reasoning on the Edge T owards autonomous mathematics research

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e8c3d63-f63c-4a62-b4d5-307d82fa78a1 · outbound

This paper cites an unresolved cited work.

Efficient Reasoning on the Edge Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56395c5d-8a41-44d9-9602-4b5d65420f76 · outbound

This paper cites ReAct: Synergizing reasoning and acting in language models.

Efficient Reasoning on the Edge ReAct: Synergizing reasoning and acting in language models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3bd099f-b0a2-4e4f-a38f-95b279343b48 · outbound

This paper cites MAI-UI technical report: Real-world centric foundation GUI agents.

Efficient Reasoning on the Edge MAI-UI technical report: Real-world centric foundation GUI agents

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 603594aa-1ba9-40eb-98e7-a4ee0e5cf224 · outbound

This paper cites 26 Chaolin Jin, Chen Li, Hao Chen, Haoli Chen, Jian Chen, Qinghao Zhao, and Guang Shi.

Efficient Reasoning on the Edge 26 Chaolin Jin, Chen Li, Hao Chen, Haoli Chen, Jian Chen, Qinghao Zhao, and Guang Shi

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 147e2bdc-78b5-4d96-aad7-dc3e9b64364b · outbound

This paper cites UI-venus-1.5 technical report.

Efficient Reasoning on the Edge UI-venus-1.5 technical report

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab4a6150-1794-4317-878d-f71f4f8c33e0 · outbound

This paper cites https://nousresearch.

Efficient Reasoning on the Edge https://nousresearch

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 669b24ec-b00b-464b-8951-d2a6e3b25ad9 · outbound

This paper cites LLM in a flash: Efficient large language model inference with limited memory.

Efficient Reasoning on the Edge LLM in a flash: Efficient large language model inference with limited memory

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48a6e8cd-0e6f-4933-8ce3-4a61f0400909 · outbound

This paper cites Understanding large language models in your pockets: Performance study on COTS mobile devices.

Efficient Reasoning on the Edge Understanding large language models in your pockets: Performance study on COTS mobile devices

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03189118-44c6-4d81-9f5f-1ab1367da937 · outbound

This paper cites Lora: Low-rank adaptation of large language models.

Efficient Reasoning on the Edge Lora: Low-rank adaptation of large language models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3082d675-eecc-4b5d-b8db-52476bc36cfb · outbound

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

Efficient Reasoning on the Edge DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a31780e-6c1b-4a3b-9f3a-7fa8cbb5f597 · outbound

This paper cites s1: Simple test-time scaling.

Efficient Reasoning on the Edge s1: Simple test-time scaling

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67313d49-0389-4646-a396-9575b30f074c · outbound

This paper cites Steering LLM Thinking with Budget Guidance.

Efficient Reasoning on the Edge Steering LLM Thinking with Budget Guidance

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa71bfda-5cf2-4155-90e9-508a16a17ab6 · outbound

This paper cites https://github.com/ Qualcomm-AI-research/fastforward.

Efficient Reasoning on the Edge https://github.com/ Qualcomm-AI-research/fastforward

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a3c10b9-3586-4dcb-b7b9-33a1ebf60822 · outbound

This paper cites https://www.qualcomm.com/developer/ software/gen-ai-inference-extensions.

Efficient Reasoning on the Edge https://www.qualcomm.com/developer/ software/gen-ai-inference-extensions

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94318df7-127d-47d0-8e0d-fb8313eeac0f · outbound

This paper cites Large language models are zero-shot reasoners.

Efficient Reasoning on the Edge Large language models are zero-shot reasoners

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ae2751e-12ec-4a3d-be42-c3521ff448c3 · outbound

This paper cites Show your work: Scratchpads for intermediate computation with language models, 2022.

Efficient Reasoning on the Edge Show your work: Scratchpads for intermediate computation with language models, 2022

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52961f33-b697-4f8a-a5fb-fe03b6caef02 · outbound

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

Efficient Reasoning on the Edge Chain-of-thought prompting elicits reasoning in large language mod- els

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f803da0e-4eef-40ce-bd83-f7d3c4e7a549 · outbound

This paper cites Tina: Tiny Reasoning Models via LoRA.

Efficient Reasoning on the Edge Tina: Tiny Reasoning Models via LoRA

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 63751b55-7c61-468e-9330-42c61068092e · outbound

This paper cites Phi-4-Mini-Reasoning: Exploring the Limits of Small Reasoning Language Models in Math.

Efficient Reasoning on the Edge Phi-4-Mini-Reasoning: Exploring the Limits of Small Reasoning Language Models in Math

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f7b5512-257c-4ef5-bd9d-7048e409a4fc · outbound

This paper cites Think Only When You Need with Large Hybrid-Reasoning Models.

Efficient Reasoning on the Edge Think Only When You Need with Large Hybrid-Reasoning Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation decf824f-a0a1-413c-9d2a-aeb9bb6d5564 · outbound

This paper cites Lora without regret, 2025.

Efficient Reasoning on the Edge Lora without regret, 2025

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 604cc654-1611-494a-a9f5-b122ba7c947b · outbound

This paper cites AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning.

Efficient Reasoning on the Edge AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c40d8ab2-0327-4ace-891f-93d85c41112e · outbound

This paper cites Reinforcement learning for reasoning in small llms: What works and what doesn’t.

Efficient Reasoning on the Edge Reinforcement learning for reasoning in small llms: What works and what doesn’t

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a621ebbc-27c2-40d2-a369-2f58274ed11d · outbound

This paper cites Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs.

Efficient Reasoning on the Edge Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e64fd363-a7f0-4157-a401-aeae21a5137a · outbound

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

Efficient Reasoning on the Edge DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53443657-dd35-43c9-896d-137d31f1a7f1 · outbound

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

Efficient Reasoning on the Edge Qwq-32b: Embracing the power of reinforcement learning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e5c09ac-b62f-4466-a2a8-806c3efc2e86 · outbound

This paper cites OpenThoughts: Data Recipes for Reasoning Models.

Efficient Reasoning on the Edge OpenThoughts: Data Recipes for Reasoning Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a8b0d4b-b8a6-466e-99e0-7ef62afdfa49 · outbound

This paper cites Qwen2.5 Technical Report.

Efficient Reasoning on the Edge Qwen2.5 Technical Report

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40e1dc2f-d761-4f06-87e2-c0e28f5d45df · outbound

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

Efficient Reasoning on the Edge Open r1: A fully open reproduction of deepseek-r1, January 2025

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc38a614-7dde-4f02-9c41-2c37a21bb2b6 · outbound

This paper cites aime problems and solutions.

Efficient Reasoning on the Edge aime problems and solutions

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4fa6a9a-91d2-4349-8153-60494a74c1d4 · outbound

This paper cites amc problems and solutions.

Efficient Reasoning on the Edge amc problems and solutions

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d94c9fd-8080-4bb1-802d-ab0feded36e4 · outbound

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

Efficient Reasoning on the Edge Measuring Mathematical Problem Solving With the MATH Dataset

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac32b727-7e3a-4795-95f3-ed083128158b · outbound

This paper cites Gpqa: A graduate-level google-proof q&a benchmark.

Efficient Reasoning on the Edge Gpqa: A graduate-level google-proof q&a benchmark

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68b27006-879e-4e39-94ac-ef9530d97847 · outbound

This paper cites LiveCodeBench: Holistic and contamination free evaluation of large language models for code.

Efficient Reasoning on the Edge LiveCodeBench: Holistic and contamination free evaluation of large language models for code

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43d5eec6-e30e-4942-adb5-8cf740270f71 · outbound

This paper cites Evaluating large language models trained on code.

Efficient Reasoning on the Edge Evaluating large language models trained on code

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b82bae7-2b84-46ec-be29-5b22b168a3a6 · outbound

This paper cites Program synthesis with large language mod- els.

Efficient Reasoning on the Edge Program synthesis with large language mod- els

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eca9aa0e-066b-45ff-8d02-2e31d4433932 · outbound

This paper cites Is your code generated by ChatGPT really correct? rigorous evaluation of large language models for code generation.

Efficient Reasoning on the Edge Is your code generated by ChatGPT really correct? rigorous evaluation of large language models for code generation

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21960035-40b2-48c0-9c25-6e78852cb395 · outbound

This paper cites Lighteval: A lightweight framework for llm evaluation, 2023.

Efficient Reasoning on the Edge Lighteval: A lightweight framework for llm evaluation, 2023

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20c83f12-dc98-45ff-8891-159e1401235c · outbound

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

Efficient Reasoning on the Edge Gonzalez, Hao Zhang, and Ion Stoica

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 620fd849-106b-4381-b137-7bbea98b681c · outbound

This paper cites Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning.

Efficient Reasoning on the Edge Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fd74f86-2dce-4167-9895-984cf0bb598c · outbound

This paper cites Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training.

Efficient Reasoning on the Edge Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c6fe474-2374-40ac-8641-6f246140a297 · outbound

This paper cites Know what you don’t know: Unanswerable questions for squad,.

Efficient Reasoning on the Edge Know what you don’t know: Unanswerable questions for squad,

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f556a92-6e30-47f0-b4bb-f56b5baf61de · outbound

This paper cites Know What You Don't Know: Unanswerable Questions for SQuAD.

Efficient Reasoning on the Edge Know What You Don't Know: Unanswerable Questions for SQuAD

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e63a581c-c5a3-4bb0-8532-cd832533d1ec · outbound

This paper cites Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies.

Efficient Reasoning on the Edge Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91906a3d-5b09-4321-affd-48cc2bb02609 · outbound

This paper cites When reasoning meets its laws.

Efficient Reasoning on the Edge When reasoning meets its laws

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8c8e6f9-4d5d-497e-9c1a-6247b8595bf0 · outbound

This paper cites Chain of Draft: Thinking Faster by Writing Less.

Efficient Reasoning on the Edge Chain of Draft: Thinking Faster by Writing Less

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4c2649e-1462-4acb-a940-a5eba97eabb4 · outbound

This paper cites The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models.

Efficient Reasoning on the Edge The Benefits of a Concise Chain of Thought on Problem-Solving in Large Language Models

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8eb4aff5-af2e-4da2-9bb5-3ccdc82e88e7 · outbound

This paper cites Think or not? selective reasoning via reinforcement learning for vision-language models.

Efficient Reasoning on the Edge Think or not? selective reasoning via reinforcement learning for vision-language models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5df31b0a-db6a-4e66-bcf7-844a07bb6c8c · outbound

This paper cites Hapo: Training language models to reason concisely via history-aware policy optimization.

Efficient Reasoning on the Edge Hapo: Training language models to reason concisely via history-aware policy optimization

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c860a27-a842-400f-b339-ab2fce5648d3 · outbound

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

Efficient Reasoning on the Edge L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d028423-1037-4878-940d-f3655809889b · outbound

This paper cites Dler: Doing length penalty right-incentivizing more intelligence per token via reinforcement learning.

Efficient Reasoning on the Edge Dler: Doing length penalty right-incentivizing more intelligence per token via reinforcement learning

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f3970d3-a399-407e-a1ab-abdda6a3d876 · outbound

This paper cites Deepscaler: Surpassing o1-preview with a 1.5 b model by scaling rl.

Efficient Reasoning on the Edge Deepscaler: Surpassing o1-preview with a 1.5 b model by scaling rl

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a4e8277-cb1e-43cf-b151-8c494d4815f2 · outbound

This paper cites TRL: Transformers Reinforcement Learning, 2020.

Efficient Reasoning on the Edge TRL: Transformers Reinforcement Learning, 2020

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f1734c6-e0b5-4ad0-9728-b31d55a9274e · outbound

This paper cites Let’s verify step by step.

Efficient Reasoning on the Edge Let’s verify step by step

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cc111fa-a85f-4eab-8929-d1b76fb8db91 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Efficient Reasoning on the Edge Training Verifiers to Solve Math Word Problems

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 890d3489-79a1-448c-b367-45138775f34e · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

Efficient Reasoning on the Edge Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28f36b6c-47a4-484a-8758-80322b7c40bb · outbound

This paper cites Large Language Monkeys: Scaling Inference Compute with Repeated Sampling.

Efficient Reasoning on the Edge Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78bdc90a-6a8e-4c01-b608-e6dfdff2c3e7 · outbound

This paper cites Inference scaling laws: An empirical analysis of compute-optimal inference for llm problem-solving.

Efficient Reasoning on the Edge Inference scaling laws: An empirical analysis of compute-optimal inference for llm problem-solving

Reference 64

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a21caa80-883c-4f89-88b1-af74688f7381 · outbound

This paper cites Scaling llm test-time compute optimally can be more effective than scaling model parameters.

Efficient Reasoning on the Edge Scaling llm test-time compute optimally can be more effective than scaling model parameters

Reference 65

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 653bcf11-d0c6-439f-aeec-05dd36f3fc49 · outbound

This paper cites The effect of sampling temperature on problem solving in large language models.

Efficient Reasoning on the Edge The effect of sampling temperature on problem solving in large language models

Reference 66

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a019654-f2fe-416c-b407-61425f831e0a · outbound

This paper cites Group Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularity.

Efficient Reasoning on the Edge Group Think: Multiple Concurrent Reasoning Agents Collaborating at Token Level Granularity

Reference 67

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bb5e1b6-5395-473f-8513-d23079c4eccd · outbound

This paper cites Learning Adaptive Parallel Reasoning with Language Models.

Efficient Reasoning on the Edge Learning Adaptive Parallel Reasoning with Language Models

Reference 68

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43dfcd84-07b1-4546-bcad-f90e32d8abf9 · outbound

This paper cites Hogwild! inference: Parallel llm generation via concurrent attention.

Efficient Reasoning on the Edge Hogwild! inference: Parallel llm generation via concurrent attention

Reference 69

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0050ce8a-a01e-4356-bc8e-2e84d34e485d · outbound

This paper cites Parallel-R1: Towards Parallel Thinking via Reinforcement Learning.

Efficient Reasoning on the Edge Parallel-R1: Towards Parallel Thinking via Reinforcement Learning

Reference 70

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af23d762-111f-4c8b-88cd-38e87e82533b · outbound

This paper cites Tree of thoughts: Deliberate problem solving with large language models.

Efficient Reasoning on the Edge Tree of thoughts: Deliberate problem solving with large language models

Reference 71

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0b158dd-92e1-40bf-b462-cac9a5412099 · outbound

This paper cites Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation.

Efficient Reasoning on the Edge Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation

Reference 72

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d112cfe-7240-4bba-8276-a021b17a72c6 · outbound

This paper cites Enhancing Reasoning through Process Supervision with Monte Carlo Tree Search.

Efficient Reasoning on the Edge Enhancing Reasoning through Process Supervision with Monte Carlo Tree Search

Reference 73

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c4f3d44-97bf-4f48-a071-66c4657fdfe6 · outbound

This paper cites Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs.

Efficient Reasoning on the Edge Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs

Reference 74

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cffc8c92-0fa5-4bd2-b4a0-b69de0e0c4e8 · outbound

This paper cites Helpsteer 2: Open-source dataset for training top-performing reward mod- els, 2024.

Efficient Reasoning on the Edge Helpsteer 2: Open-source dataset for training top-performing reward mod- els, 2024

Reference 75

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d26e2556-e31d-4142-be99-e1970e870d10 · outbound

This paper cites Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations.

Efficient Reasoning on the Edge Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations

Reference 76

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dbbc7d3-1efe-4d43-8cfc-7879358682da · outbound

This paper cites The Lessons of Developing Process Reward Models in Mathematical Reasoning.

Efficient Reasoning on the Edge The Lessons of Developing Process Reward Models in Mathematical Reasoning

Reference 77

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c3e535a-9a59-44c7-bd86-6e64cb14c995 · outbound

This paper cites Inference-time scaling for generalist reward modeling.

Efficient Reasoning on the Edge Inference-time scaling for generalist reward modeling

Reference 78

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb3854e8-5c6d-46b5-89ba-91beba9debe1 · outbound

This paper cites Web-shepherd: Advancing prms for reinforcing web agents.

Efficient Reasoning on the Edge Web-shepherd: Advancing prms for reinforcing web agents

Reference 79

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07822275-97af-4142-bdd4-eb905c7359f1 · outbound

This paper cites Scaling Autonomous Agents via Automatic Reward Modeling And Planning.

Efficient Reasoning on the Edge Scaling Autonomous Agents via Automatic Reward Modeling And Planning

Reference 80

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 491ccb90-2d2a-4ef4-b76a-80cba5656485 · outbound

This paper cites Making, not taking, the best of n.

Efficient Reasoning on the Edge Making, not taking, the best of n

Reference 81

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5042fc9-5c2b-4edf-9eef-47b7a1dc899c · outbound

This paper cites From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning.

Efficient Reasoning on the Edge From Drafts to Answers: Unlocking LLM Potential via Aggregation Fine-Tuning

Reference 82

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0181e7f1-cfbc-4fac-88ba-d29e1fa36b47 · outbound

This paper cites Learning to reason across parallel samples for llm reasoning.

Efficient Reasoning on the Edge Learning to reason across parallel samples for llm reasoning

Reference 83

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddb9fb00-fec4-4199-aca8-14bcbad2a379 · outbound

This paper cites The Majority is not always right: RL training for solution aggregation.

Efficient Reasoning on the Edge The Majority is not always right: RL training for solution aggregation

Reference 84

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9c4c203-9902-46cf-8560-c90541c73bae · outbound

This paper cites Scaling llm test-time compute with mobile npu on smartphones.

Efficient Reasoning on the Edge Scaling llm test-time compute with mobile npu on smartphones

Reference 85

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7351712a-8cd3-48e9-bbba-2dd588160040 · outbound

This paper cites Fast best-of-n decoding via speculative rejection.

Efficient Reasoning on the Edge Fast best-of-n decoding via speculative rejection

Reference 86

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd1d5b12-f903-4037-9b86-3ab0bb2e3fe5 · outbound

This paper cites ETS: Efficient Tree Search for Inference-Time Scaling.

Efficient Reasoning on the Edge ETS: Efficient Tree Search for Inference-Time Scaling

Reference 87

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b73203f1-7699-4386-a6be-f1adeebd2e62 · outbound

This paper cites Generative verifiers: Reward modeling as next-token prediction.

Efficient Reasoning on the Edge Generative verifiers: Reward modeling as next-token prediction

Reference 88

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad940002-949c-4e9c-a54a-955c988afce0 · outbound

This paper cites Quantizing deep convolutional networks for efficient inference: A whitepaper.

Efficient Reasoning on the Edge Quantizing deep convolutional networks for efficient inference: A whitepaper

Reference 89

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec2e3b21-9140-4034-8804-1397f2bb97be · outbound

This paper cites A White Paper on Neural Network Quantization.

Efficient Reasoning on the Edge A White Paper on Neural Network Quantization

Reference 90

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dd8ba84-4151-4aff-9e06-134981008b83 · outbound

This paper cites Horowitz.

Efficient Reasoning on the Edge Horowitz

Reference 91

Resolution: malformed identifier; doi_truncated, observed 2026-07-13T23:30:04.176644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9a97f3a7-1a19-4d57-8491-c933e366f7f1 · outbound

This paper cites Quantized neural net- works: Training neural networks with low precision weights and activations.The Journal of Machine Learning Research, 18(1):6869–6898, 2017.

Efficient Reasoning on the Edge Quantized neural net- works: Training neural networks with low precision weights and activations.The Journal of Machine Learning Research, 18(1):6869–6898, 2017

Reference 92

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66a2169b-c494-4265-bd04-813697149cc1 · outbound

This paper cites DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients.

Efficient Reasoning on the Edge DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients

Reference 93

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0aaf7fb7-37b4-4d9b-ae67-2e7c939c4e53 · outbound

This paper cites Post-training 4-bit quantization of convolution networks for rapid-deployment.

Efficient Reasoning on the Edge Post-training 4-bit quantization of convolution networks for rapid-deployment

Reference 94

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5e25081-515a-4547-bee6-cac4b2625573 · outbound

This paper cites Zeroq: A novel zero shot quantization framework.

Efficient Reasoning on the Edge Zeroq: A novel zero shot quantization framework

Reference 95

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fce9ce7a-3e1c-4831-ab00-1a61918b6700 · outbound

This paper cites Low-bit quantization of neural networks for efficient inference.

Efficient Reasoning on the Edge Low-bit quantization of neural networks for efficient inference

Reference 96

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cddf0d51-aea2-4801-a1d0-e2d0603ba883 · outbound

This paper cites Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming.

Efficient Reasoning on the Edge Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming

Reference 97

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d8a4a23-0a8b-4e2d-8df1-ef0a0c3f8093 · outbound

This paper cites Same, same but different: Recover- ing neural network quantization error through weight factorization.

Efficient Reasoning on the Edge Same, same but different: Recover- ing neural network quantization error through weight factorization

Reference 98

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19a68a84-dbcc-4e0b-be3f-2e84106d09b4 · outbound

This paper cites Improving neural network quantization without retraining using outlier channel splitting.

Efficient Reasoning on the Edge Improving neural network quantization without retraining using outlier channel splitting

Reference 99

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44e6df82-5957-42e6-aa8a-76089d9a8021 · outbound

This paper cites Data-free quantization through weight equalization and bias correction.

Efficient Reasoning on the Edge Data-free quantization through weight equalization and bias correction

Reference 100

Resolution: unresolved; no resolver link, observed 2026-07-13T23:28:12.790404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers