Paper Citation Record · LEDGER

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning

As of 9 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 1 inbound Pith citation observation for arXiv:2606.03113.

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

pith.paper-citation-record.v1
2606.03113 v1

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-28T10:19:02.938980Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-28T10:19:02.938980Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-02T03:06:30.308770Z

Reference resolution

38 of 38 outbound references displayed

verified exact4
verified fuzzy0
unresolved32
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3158e3aa-a440-49b4-a421-6aa0bf44699e · outbound

This paper cites an unresolved cited work.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa8e528c-d1be-4831-9b7c-ef6ea4de4dcd · outbound

This paper cites Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T03:06:30.310571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c8ec0be9-5660-40da-9c02-cd0a09ae7911 · outbound

This paper cites exit” action signals high confidence and continues the drafting process, while a “continue.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning exit” action signals high confidence and continues the drafting process, while a “continue

Reference 3

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 651a292e-1a53-4fc9-830d-0fe7ba6cde8b · outbound

This paper cites Implementaion Details Training Hyperparameters.The model is trained using the Adam optimizer [26] with a learning rate of α= 6.25×10 −5.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Implementaion Details Training Hyperparameters.The model is trained using the Adam optimizer [26] with a learning rate of α= 6.25×10 −5

Reference 4

Resolution: malformed identifier; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a03ef81-3d7a-4cfa-b01c-ca38d27b5029 · outbound

This paper cites an unresolved cited work.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e598926d-5981-4929-aa2b-1ff3845d9021 · outbound

This paper cites an unresolved cited work.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d167527d-3fe4-4996-87e3-b9ebd4351f23 · outbound

This paper cites Llama 2: Open foundation and fine-tuned chat models,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Llama 2: Open foundation and fine-tuned chat models,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ac8290a-51ca-4c85-a2da-bf2d7d8233ce · outbound

This paper cites Gpt-4 technical report,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Gpt-4 technical report,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4f567f58-aedf-4e1b-8ed1-a47a3ab53bff · outbound

This paper cites Gemini: A family of highly capable multimodal models,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Gemini: A family of highly capable multimodal models,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a97271c-5bca-4044-8884-66ea5a0b86f1 · outbound

This paper cites Draft & verify: Lossless large lan- guage model acceleration via self-speculative decoding,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Draft & verify: Lossless large lan- guage model acceleration via self-speculative decoding,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bb7faa6-cb76-49d2-b4e1-29ee1ce7b9da · outbound

This paper cites LayerSkip: Enabling early exit inference and self-speculative decoding,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning LayerSkip: Enabling early exit inference and self-speculative decoding,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0135c962-0de2-4217-9c40-8037d2f19fda · outbound

This paper cites Not all layers of llms are necessary during inference,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Not all layers of llms are necessary during inference,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b81416dd-fac9-4bc3-b858-3c21b7fe4100 · outbound

This paper cites Confident adaptive language modeling,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Confident adaptive language modeling,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f12a786-9baa-4780-81b6-e54b43f425f9 · outbound

This paper cites Dola: Decoding by contrasting layers improves factuality in large language models,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Dola: Decoding by contrasting layers improves factuality in large language models,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a7c4cc6-7ac5-49e5-bc08-2c9ae8a4f096 · outbound

This paper cites Deja vu: contextual sparsity for efficient llms at inference time,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Deja vu: contextual sparsity for efficient llms at inference time,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc1c67e1-ff32-491b-a951-6b161d6b06ed · outbound

This paper cites Draft on the fly: Adaptive self- speculative decoding using cosine similarity,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Draft on the fly: Adaptive self- speculative decoding using cosine similarity,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1f5d853-7893-4c0b-bdbb-edf2846224d5 · outbound

This paper cites Investigating acceleration of LLaMA inference by enabling intermediate layer decoding via instruction tuning with ‘LITE’,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Investigating acceleration of LLaMA inference by enabling intermediate layer decoding via instruction tuning with ‘LITE’,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 96eb19fd-7bb5-40d6-80b3-2471b441db77 · outbound

This paper cites Kangaroo: lossless self-speculative decoding for accelerating llms via double early exiting,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Kangaroo: lossless self-speculative decoding for accelerating llms via double early exiting,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6b45fec-30ec-424b-bb7e-b39f27baeb40 · outbound

This paper cites Statistical inference for prob- abilistic functions of finite state markov chains,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Statistical inference for prob- abilistic functions of finite state markov chains,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9e71b5c-5400-424e-b366-b3074327d22e · outbound

This paper cites Sutton and Andrew G.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Sutton and Andrew G

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4011fd8e-48e1-4f4d-9506-964e99e40ba5 · outbound

This paper cites Mixture-of-depths: Dynamically al- locating compute in transformer-based language models,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Mixture-of-depths: Dynamically al- locating compute in transformer-based language models,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa3d898d-3dde-4b42-91bb-e09e8818345f · outbound

This paper cites Accelerating Inference in Large Language Models with a Unified Layer Skipping Strategy.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Accelerating Inference in Large Language Models with a Unified Layer Skipping Strategy

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-07-02T03:06:30.317060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f5e452b8-ac74-46a0-9c51-baf7f07b7cef · outbound

This paper cites Admtree: Compressing lengthy context with adaptive semantic trees,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Admtree: Compressing lengthy context with adaptive semantic trees,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5af369a2-4aa7-488b-84f6-4ef18908b3ce · outbound

This paper cites DAST: Context-aware compression in LLMs via dynamic allocation of soft tokens,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning DAST: Context-aware compression in LLMs via dynamic allocation of soft tokens,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e009c82-9735-4910-b199-f1af281b0d50 · outbound

This paper cites Knn-ssd: Enabling dynamic self-speculative decoding via nearest neighbor layer set optimization,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Knn-ssd: Enabling dynamic self-speculative decoding via nearest neighbor layer set optimization,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31920af8-e213-46f2-8d9a-c850949c02ac · outbound

This paper cites Speculative decoding: Exploiting speculative execution for accelerating seq2seq generation,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Speculative decoding: Exploiting speculative execution for accelerating seq2seq generation,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0353a7ea-5673-40ed-89b8-62727d10a514 · outbound

This paper cites Specinfer: Accelerating large lan- guage model serving with tree-based speculative inference and verification,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Specinfer: Accelerating large lan- guage model serving with tree-based speculative inference and verification,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae13476b-952d-4630-b1cd-a2d31584f2cc · outbound

This paper cites Eagle: speculative sampling requires rethinking feature uncertainty,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Eagle: speculative sampling requires rethinking feature uncertainty,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f86f2519-931c-4d77-8737-411008c77762 · outbound

This paper cites Unlocking efficiency in large lan- guage model inference: A comprehensive survey of speculative decoding,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Unlocking efficiency in large lan- guage model inference: A comprehensive survey of speculative decoding,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46a9b7d7-47e7-4051-b341-1edce0215829 · outbound

This paper cites Human-level control through deep reinforcement learning,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Human-level control through deep reinforcement learning,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1168155-3b74-4aba-b135-e09988f52b36 · outbound

This paper cites Learning to predict by the methods of temporal differences,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Learning to predict by the methods of temporal differences,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcaa16f5-85e6-45e0-b219-207396d6d432 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Adam: A Method for Stochastic Optimization

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-07-02T03:06:30.313498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 64801931-7d82-44b1-bd69-435cedcb3e3f · outbound

This paper cites Noisy Networks for Exploration.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Noisy Networks for Exploration

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-07-02T03:06:30.320474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b8fc34f9-e8f3-419e-bb6f-13c47c269247 · outbound

This paper cites Alpaca: A strong, replicable instruction- following model,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Alpaca: A strong, replicable instruction- following model,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbe4cda3-565b-46d7-a2e1-e1a7a06d3408 · outbound

This paper cites Low-resource domain adaptation for compositional task-oriented semantic parsing,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Low-resource domain adaptation for compositional task-oriented semantic parsing,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c7aade8-3c7a-4ef7-b95e-55549ad3d1cd · outbound

This paper cites Abstractive text summarization using sequence-to-sequence rnns and beyond,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Abstractive text summarization using sequence-to-sequence rnns and beyond,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbc0ad88-9ceb-4d02-ab02-fd3e6f049526 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Evaluating Large Language Models Trained on Code

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-07-02T03:06:30.323809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 45c7da89-618e-4c3a-b395-254824101c17 · outbound

This paper cites Fast inference from transformers via speculative decoding,.

Experience-Driven Dynamic Exits for LLMs with Reinforcement Learning Fast inference from transformers via speculative decoding,

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-28T10:19:02.938980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation aa8e528c-d1be-4831-9b7c-ef6ea4de4dcd · inbound