Paper Citation Record · LEDGER

Reward-Guided Speculative Decoding for Efficient LLM Reasoning

As of 10 August 2026, this Paper Citation Record lists 67 of 67 outbound references and 34 inbound Pith citation observations for arXiv:2501.19324.

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

pith.paper-citation-record.v1
2501.19324 v3

Coverage vector

measured 67 of 67 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T20:42:44.485144Z

measured 101 of 101 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 34 of 34 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:23:03.610978Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

67 of 67 outbound references displayed

verified exact1
verified fuzzy6
unresolved60
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

1
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 7c57154e-b9fa-46a7-a2f3-1212ae786b4a · outbound

This paper cites write newline.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:43.964524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21f442d9-1119-4632-925a-78a8109bf0f0 · outbound

This paper cites Claude 3.5 sonnet model card addendum.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Claude 3.5 sonnet model card addendum

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:43.975595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1766472c-2f05-4475-b9ab-dc161d5463dc · outbound

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

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:43.982848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33331469-0c8b-40c8-ac85-f16ff7f5d3a3 · outbound

This paper cites D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:43.990044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20457001-abdd-4814-8ffd-43ed7ca435e4 · outbound

This paper cites Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.000347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6252f64e-0fd0-46a2-8f2e-812491ad2b79 · outbound

This paper cites Accelerating Large Language Model Decoding with Speculative Sampling.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Accelerating Large Language Model Decoding with Speculative Sampling

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.016298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af617fc0-5954-4655-8222-a5b29688ce9e · outbound

This paper cites AlphaMath Almost Zero: Process Supervision without Process.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning AlphaMath Almost Zero: Process Supervision without Process

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.023438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bc4f55b-fcdc-4c32-a090-e565eb9668dd · outbound

This paper cites Cascade Speculative Drafting for Even Faster LLM Inference.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Cascade Speculative Drafting for Even Faster LLM Inference

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.031679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44775d27-2243-4374-b8be-bba113f3069f · outbound

This paper cites Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.038874Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f688bd6-eb15-4e4b-acf1-f7d027636715 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Training Verifiers to Solve Math Word Problems

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.053221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70fe6d90-bff1-48da-b1fb-187b7491ba83 · outbound

This paper cites RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.060352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6a60e9f-6edc-4a6c-b1e6-0c27b324570b · outbound

This paper cites RLHF Workflow: From Reward Modeling to Online RLHF.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning RLHF Workflow: From Reward Modeling to Online RLHF

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.066469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7451f83-a507-4cda-9735-8bda0461a28e · outbound

This paper cites an unresolved cited work.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Unresolved cited work

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.079172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3e2f23e-be78-4702-b332-81a9b9099ce6 · outbound

This paper cites LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.084818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16b3c45a-7ba2-4f75-938b-5ded5372334a · outbound

This paper cites GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.090452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09b45938-ff0d-42b4-a847-3a7b3579bf19 · outbound

This paper cites Break the Sequential Dependency of LLM Inference Using Lookahead Decoding.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.096964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea697bf9-2400-4e9d-bf62-128b821e5170 · outbound

This paper cites Arcee's mergekit: A toolkit for merging large language models.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Arcee's mergekit: A toolkit for merging large language models

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:42:46.128713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 034a3c22-e44b-4f95-a3b3-ef365da94d8d · outbound

This paper cites The Llama 3 Herd of Models.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning The Llama 3 Herd of Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.110085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fca8ae2d-bc2d-493c-b18f-db9a31e63317 · outbound

This paper cites OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.116312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c45b9cfd-433c-4866-87cf-19a8228acbff · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Measuring Massive Multitask Language Understanding

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.122919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 294021f5-4e61-4677-ab53-4f67cd2c0b42 · outbound

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

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Measuring Mathematical Problem Solving With the MATH Dataset

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.130145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf924908-1438-465d-af60-d03b883e0f49 · outbound

This paper cites Deep Learning Scaling is Predictable, Empirically.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Deep Learning Scaling is Predictable, Empirically

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.136644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a4ce8fd-c225-44ca-8ca6-a13cb908d185 · outbound

This paper cites Training Compute-Optimal Large Language Models.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Training Compute-Optimal Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.144341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a8bf702-4455-4fb0-83a3-6c2f5260842a · outbound

This paper cites The curious case of neural text degeneration.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning The curious case of neural text degeneration

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.150908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a9bf614-f949-4dcb-b71f-8a2c2b47877b · outbound

This paper cites GPT-4o System Card.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning GPT-4o System Card

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.156789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba44915f-09b0-4659-b8d0-c9f2045e1e4e · outbound

This paper cites MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Time.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning MindStar: Enhancing Math Reasoning in Pre-trained LLMs at Inference Time

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.162517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5e6f325-4651-43d4-bb87-cb9cbfb2c9ee · outbound

This paper cites Scaling Laws for Neural Language Models.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Scaling Laws for Neural Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.168357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b10a533-dc69-42eb-a020-9ce9b3988a8d · outbound

This paper cites H., Gonzalez, J., Zhang, H., and Stoica, I.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning H., Gonzalez, J., Zhang, H., and Stoica, I

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.173811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f8361c1-3841-490f-88a5-23a22c4bcae9 · outbound

This paper cites Fast inference from transformers via speculative decoding.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Fast inference from transformers via speculative decoding

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.179626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7890918e-caaf-4cf6-b430-bca9f6162af8 · outbound

This paper cites V., Slone, A., Anil, C., Schlag, I., Gutman - Solo, T., Wu, Y., Neyshabur, B., Gur - Ari, G., and Misra, V.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning V., Slone, A., Anil, C., Schlag, I., Gutman - Solo, T., Wu, Y., Neyshabur, B., Gur - Ari, G., and Misra, V

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:42:46.068396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation aaae243e-3fa8-489b-b733-e5e6419876bf · outbound

This paper cites an unresolved cited work.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.199802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37154e07-8711-46fd-8ce9-3a7606eed1a6 · outbound

This paper cites SnapKV: LLM Knows What You are Looking for Before Generation.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning SnapKV: LLM Knows What You are Looking for Before Generation

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.207816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ba03539-c786-4ab2-86b7-3e11edf2d45b · outbound

This paper cites EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.215750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6c5d164-233c-4de2-b146-8b1f9a3bf2ed · outbound

This paper cites 3-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning 3-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-08-09T20:42:44.570676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c88f4ff8-826a-40e8-9d58-2afecb657ab0 · outbound

This paper cites MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.228570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5272d4cf-a94a-4bc4-9fac-c9b81664380d · outbound

This paper cites Let's Verify Step by Step.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Let's Verify Step by Step

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.234941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 806e61ad-878d-4c21-8a33-b118f93b95e9 · outbound

This paper cites Awq: Activation-aware weight quantization for on-device llm compression and acceleration.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Awq: Activation-aware weight quantization for on-device llm compression and acceleration

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.241668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 259d1ad3-0597-4ee6-a5ff-9af1e849bba6 · outbound

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

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.251912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7665727-c85a-4025-b2ee-498f7361fd6d · outbound

This paper cites an unresolved cited work.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Unresolved cited work

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.258159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d04ec9e-89c5-4e7e-900d-537f67887d17 · outbound

This paper cites Skywork-o1 open series.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Skywork-o1 open series

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.263839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1801d9b3-fd31-4a80-b40c-201c127abba8 · outbound

This paper cites Learning to reason with llms, 2024.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Learning to reason with llms, 2024

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.272726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d01e379-b894-410f-92a7-9a121291dfa8 · outbound

This paper cites Carbon Emissions and Large Neural Network Training.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Carbon Emissions and Large Neural Network Training

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.280816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7af0daca-458b-4d09-bdab-3bd5a8633d16 · outbound

This paper cites Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.286290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1882eb5d-2c89-42a5-91e4-91d8c98e94e8 · outbound

This paper cites GPQA: A Graduate-Level Google-Proof Q&A Benchmark.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.292259Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9790a47a-a798-41f8-9841-2c0039784b25 · outbound

This paper cites Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.299119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 460091e8-bb92-4268-92d0-d340a5a8ba69 · outbound

This paper cites Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.308717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ffd8a92-6085-4617-8bca-d5105949050a · outbound

This paper cites Blockwise parallel decoding for deep autoregressive models.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Blockwise parallel decoding for deep autoregressive models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.316584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca42c7bf-7a16-4c9a-9880-30bb22f15db9 · outbound

This paper cites TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.326192Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9f81045-d925-4f46-8b77-0632616fb7b2 · outbound

This paper cites A Simple and Effective Pruning Approach for Large Language Models.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning A Simple and Effective Pruning Approach for Large Language Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.340013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 949f76bd-36b3-4259-aed6-51136094ed54 · outbound

This paper cites T., Ro, J.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning T., Ro, J

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:42:45.957902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f9e9c874-d97f-4d90-8736-71cf62e774c3 · outbound

This paper cites Mathscale: Scaling instruction tuning for mathematical reasoning.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Mathscale: Scaling instruction tuning for mathematical reasoning

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:42:45.932348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e5b55482-202e-445e-9856-66c7ba8342c7 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.368701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bdd4c00-a5d2-4cf6-bcae-7eca24c93b5a · outbound

This paper cites N., Kaiser, L., and Polosukhin, I.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning N., Kaiser, L., and Polosukhin, I

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:42:45.912643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 627a8fc0-d445-45d1-bb99-665028e04d2d · outbound

This paper cites Math-shepherd: Verify and reinforce llms step-by-step without human annotations.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Math-shepherd: Verify and reinforce llms step-by-step without human annotations

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T20:42:45.894536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d4d370f4-c46f-424b-98f5-db247d902e32 · outbound

This paper cites Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.390745Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57a1196a-9508-4ac8-8f35-504f2110c370 · outbound

This paper cites QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.396702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 259cc8dc-bee7-487a-8a9a-8d6126e9d80b · outbound

This paper cites ThinK: Thinner Key Cache by Query-Driven Pruning.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning ThinK: Thinner Key Cache by Query-Driven Pruning

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.405709Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bb10878-8b67-4146-9962-38cf55ce3c7d · outbound

This paper cites What Matters for Model Merging at Scale?.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning What Matters for Model Merging at Scale?

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.413356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3893f11d-fad5-4fe8-a75e-64f520860562 · outbound

This paper cites Qwen2.5 Technical Report.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Qwen2.5 Technical Report

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.425099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a701c5d-f690-42eb-b5ce-eb0c4b4e7d75 · outbound

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

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.433332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac747d20-58d0-4e16-9744-e5bf63d89c1d · outbound

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

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Tree of thoughts: Deliberate problem solving with large language models

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.442735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation deb6154c-f8e9-43c0-b3a3-4d8d2e812720 · outbound

This paper cites OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning OVM, Outcome-supervised Value Models for Planning in Mathematical Reasoning

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.448540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c801eed3-7e36-479b-94ce-f91b886d7a0c · outbound

This paper cites Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.456802Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61de3e2e-1767-48a4-a500-7a1fae3b4be5 · outbound

This paper cites H2o: Heavy-hitter oracle for efficient generative inference of large language models.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning H2o: Heavy-hitter oracle for efficient generative inference of large language models

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.463803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e32c95fe-10d1-4937-a910-9a0b37dbe291 · outbound

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

Reward-Guided Speculative Decoding for Efficient LLM Reasoning The Lessons of Developing Process Reward Models in Mathematical Reasoning

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.472297Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60007197-a309-43ee-b7cf-157f0fdc42e9 · outbound

This paper cites ProcessBench: Identifying Process Errors in Mathematical Reasoning.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning ProcessBench: Identifying Process Errors in Mathematical Reasoning

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.478833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97823314-e74b-498a-8f40-6686fe05f016 · outbound

This paper cites P., Wang, K., Chang, J., Gao, Z., Kallus, N., Weinberger, K.

Reward-Guided Speculative Decoding for Efficient LLM Reasoning P., Wang, K., Chang, J., Gao, Z., Kallus, N., Weinberger, K

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-09T20:42:44.485144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation bcec02f8-e6ff-473a-8f3b-0cbd1a804409 · inbound

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

Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 100

Resolution: verified exact; arxiv_id, observed 2026-05-14T01:29:57.246050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 611322b8-23fc-4a20-81c5-a72412382bc8 · inbound

When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning cites this paper.

When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T15:23:03.610978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7ed6251-5e1d-4de9-a306-712159e8ad51 · inbound

Adaptive Chain-of-Focus Reasoning via Dynamic Visual Search and Zooming for Efficient VLMs cites this paper.

Adaptive Chain-of-Focus Reasoning via Dynamic Visual Search and Zooming for Efficient VLMs Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-17T05:35:13.236480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 32740862-8c87-4e4b-861e-6b4eee0e0851 · inbound

VeriThinker: Learning to Verify Makes Reasoning Model Efficient cites this paper.

VeriThinker: Learning to Verify Makes Reasoning Model Efficient Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T14:42:12.665171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 038d5e65-a888-4af9-9498-e1d5a6d4bae4 · inbound

Think Before You Accept: Semantic Reflective Verification for Faster Speculative Decoding cites this paper.

Think Before You Accept: Semantic Reflective Verification for Faster Speculative Decoding Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:32:41.836423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0ce5cfc-5745-4f52-bb92-fee9490dc8af · inbound

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding cites this paper.

What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T05:52:18.444052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a1662d7-9fd7-4836-a74c-7d216dbed935 · inbound

How Far Are We from Optimal Reasoning Efficiency? cites this paper.

How Far Are We from Optimal Reasoning Efficiency? Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T05:49:36.717578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7301252-0f20-4fba-a57c-29f0ce93276f · inbound

Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency cites this paper.

Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:16.691688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 388b0d75-619c-4211-984d-b25b88b294e2 · inbound

PREMISE: Scalable and Strategic Prompt Optimization for Efficient Mathematical Reasoning in Large Models cites this paper.

PREMISE: Scalable and Strategic Prompt Optimization for Efficient Mathematical Reasoning in Large Models Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T04:26:29.108342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35cbcd96-7426-4654-aa51-2ea55b5f6645 · inbound

Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models cites this paper.

Efficient Reasoning Through Suppression of Self-Affirmation Reflections in Large Reasoning Models Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T00:57:01.524906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87c8092e-3e82-4317-b042-40fe4076d637 · inbound

AALC: Large Language Model Efficient Reasoning via Adaptive Accuracy-Length Control cites this paper.

AALC: Large Language Model Efficient Reasoning via Adaptive Accuracy-Length Control Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T23:00:45.946584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed7eaab6-c0a9-410b-84ce-95380584986d · inbound

CoRE: Enhancing Metacognition with Label-free Self-evaluation in LRMs cites this paper.

CoRE: Enhancing Metacognition with Label-free Self-evaluation in LRMs Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T19:16:31.326240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7e65240-89f6-420b-8825-cc760c589dcf · inbound

Logit Arithmetic Elicits Long Reasoning Capabilities Without Training cites this paper.

Logit Arithmetic Elicits Long Reasoning Capabilities Without Training Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T16:45:58.173827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbf519a6-9680-4607-8070-a3251649d9d9 · inbound

Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities cites this paper.

Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T16:34:25.083207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b879e10c-fcb3-4518-83f2-40c8eacad096 · inbound

Collaborative Inference and Learning between Edge SLMs and Cloud LLMs: A Survey of Algorithms, Execution, and Open Challenges cites this paper.

Collaborative Inference and Learning between Edge SLMs and Cloud LLMs: A Survey of Algorithms, Execution, and Open Challenges Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T15:06:47.952749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea256494-2030-4bbb-ba13-a7d696c27044 · inbound

From Long to Short: LLMs Excel at Trimming Own Reasoning Chains cites this paper.

From Long to Short: LLMs Excel at Trimming Own Reasoning Chains Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-05T00:04:00.084214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0e449cb-e897-4b6a-9b53-f4b6d1e66884 · inbound

Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance cites this paper.

Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:13.834755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b28f02d8-d9ba-475a-8e33-0fd3b860cb39 · inbound

Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards cites this paper.

Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T13:15:44.660507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fcb612f-1c20-47a5-96de-8b4e4f5eda65 · inbound

MixReasoning: Switching Modes to Think cites this paper.

MixReasoning: Switching Modes to Think Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T11:16:36.269089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a082f96-ef59-4865-b01f-3914f9c8a059 · inbound

Policy-Guided Stepwise Model Routing for Cost-Effective Reasoning cites this paper.

Policy-Guided Stepwise Model Routing for Cost-Effective Reasoning Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:01:11.844961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation beb4d729-6445-4488-a429-aa9471f96554 · inbound

Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost cites this paper.

Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 115

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T20:06:09.780452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b1bc2428-7e1f-4d2d-a8f2-886b8997ceac · inbound

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration cites this paper.

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:51:30.110828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b9aa2bb9-de64-4d15-9a03-810c6695c4bd · inbound

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration cites this paper.

Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-15T05:15:03.414244Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6b4b70f5-f254-4976-8fd3-020ac22a6c20 · inbound

Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning cites this paper.

Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T02:23:31.576800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6528dc9d-a31c-44d6-937c-719ad32bb994 · inbound

Performance-Driven Policy Optimization for Speculative Decoding with Adaptive Windowing cites this paper.

Performance-Driven Policy Optimization for Speculative Decoding with Adaptive Windowing Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-19T16:42:39.750479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8c66803d-ef90-423c-94bd-8205ca26b35d · inbound

ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning cites this paper.

ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-02T03:26:28.717883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0486a096-6862-4eef-87df-9433fe9830e1 · inbound

KCSAT-ML: Probing Reasoning Models with Nationwide-Cohort Human Difficulty cites this paper.

KCSAT-ML: Probing Reasoning Models with Nationwide-Cohort Human Difficulty Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-06-27T13:10:55.947824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d2fb637d-0b15-42bd-9b2f-e1d868ee854d · inbound

The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes cites this paper.

The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 145

Resolution: verified exact; arxiv_id, observed 2026-07-03T05:57:41.512993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c7a64538-8131-4f38-9c2b-110847bc4108 · inbound

Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing cites this paper.

Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-07-04T19:20:06.711514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation aac4b144-e9fe-4ae3-a728-0a9b1dbe4f9d · inbound

Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing cites this paper.

Efficient and Trainable Language Model Test-Time Scaling via Local Branch Routing Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-07-01T06:35:29.567228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 928758a2-7325-4ee5-a6b3-a370bab1e0a7 · inbound

Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning cites this paper.

Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual Reasoning Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 23

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T13:34:41.134711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 84169b7c-5669-40d0-9f03-9c4d03678213 · inbound

Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making cites this paper.

Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T02:42:03.779702Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ba2f2ae-deba-4dbb-a4f7-8e2ef50281cd · inbound

When to Plan: Learning to Select Between Reactive Control and Deliberative Planning cites this paper.

When to Plan: Learning to Select Between Reactive Control and Deliberative Planning Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T21:04:09.724503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14bc6ab4-22d8-4176-9126-858b46c5137c · inbound

Is Your Model Thinking or Just Stagnating? PUMA: Diagnosing Reasoning Pathology via Phase-Momentum Alignment cites this paper.

Is Your Model Thinking or Just Stagnating? PUMA: Diagnosing Reasoning Pathology via Phase-Momentum Alignment Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T18:49:28.872386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.