Paper Citation Record · LEDGER

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training

As of 14 August 2026, this Paper Citation Record lists 45 of 45 outbound references and 1 inbound Pith citation observation for arXiv:2607.04574.

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

pith.paper-citation-record.v1
2607.04574 v1

Coverage vector

measured 45 of 45 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-11T17:03:13.686066Z

measured 46 of 46 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T12:47:38.487160Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

45 of 45 outbound references displayed

verified exact0
verified fuzzy0
unresolved44
parse uncertain1
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a4a6f1aa-9e60-421f-ac85-9843ab7cbd3c · outbound

This paper cites Intelligence per Watt: Measuring Intelligence Efficiency of Local AI.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Intelligence per Watt: Measuring Intelligence Efficiency of Local AI

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8007d496-32b3-4591-9926-e6da7ea2e3b4 · outbound

This paper cites and Zipser, David , journal=.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training and Zipser, David , journal=

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88a0abcf-61af-430d-8a42-75041dbfcbf4 · outbound

This paper cites an unresolved cited work.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Unresolved cited work

Reference 3

Resolution: parse uncertain; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de0143eb-3404-4753-b9ef-b992d7665222 · outbound

This paper cites an unresolved cited work.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Unresolved cited work

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fa9354c-facb-4729-935e-d860104701c5 · outbound

This paper cites an unresolved cited work.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02d6f244-0343-4cbd-a70c-83666b5ff433 · outbound

This paper cites Revisiting DAgger in the Era of LLM-Agents.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Revisiting DAgger in the Era of LLM-Agents

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7b4f5be-d21c-4bb6-9bb3-2a82f49e70c9 · outbound

This paper cites Reinforcement and Imitation Learning via Interactive No-Regret Learning.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Reinforcement and Imitation Learning via Interactive No-Regret Learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 503ce140-825b-4954-a783-06d5cebd2ade · outbound

This paper cites Decoupling.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Decoupling

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57fbe80e-f47c-450f-99f0-4207c8bb0187 · outbound

This paper cites ReAct: Synergizing Reasoning and Acting in Language Models.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training ReAct: Synergizing Reasoning and Acting in Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1516430-12f0-4d32-85f5-a58d3e592763 · outbound

This paper cites Artificial Intelligence , volume=.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Artificial Intelligence , volume=

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4cb4d53-42b6-423b-8fdf-d7055807ff9a · outbound

This paper cites Operations Research , volume=.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Operations Research , volume=

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c85966e-e71f-43a4-9a14-5db49b224ac5 · outbound

This paper cites Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS) , pages=.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS) , pages=

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b2f55a6-dc5f-4a99-bd2c-f6059e8492ad · outbound

This paper cites Proceedings of the Twentieth European Conference on Computer Systems , pages=.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Proceedings of the Twentieth European Conference on Computer Systems , pages=

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 853ef247-2c29-4387-9220-961243b26dcd · outbound

This paper cites Second Conference on Language Modeling , year=.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Second Conference on Language Modeling , year=

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0472669e-6763-4ff9-95eb-19038e9afd55 · outbound

This paper cites 2019 International Conference on Robotics and Automation (ICRA) , pages=.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training 2019 International Conference on Robotics and Automation (ICRA) , pages=

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 588f8a8e-d5b2-4120-9478-fa66f9ffd247 · outbound

This paper cites Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics , pages=.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics , pages=

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d07c2bb6-61dc-4a3f-914b-16cde9dc33bb · outbound

This paper cites Findings of the Association for Computational Linguistics: EMNLP 2023 , pages=.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Findings of the Association for Computational Linguistics: EMNLP 2023 , pages=

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb3d2ddf-bffe-4685-8983-a26f6cd09e2f · outbound

This paper cites Understanding R1-Zero-Like Training: A Critical Perspective.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Understanding R1-Zero-Like Training: A Critical Perspective

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a225ac26-aac3-4622-83d2-e868b72d787c · outbound

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

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9a07e87-650f-462e-82a2-7644e02e69cd · outbound

This paper cites Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: Long papers) , pages=.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Proceedings of the 61st annual meeting of the association for computational linguistics (volume 1: Long papers) , pages=

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aeaca245-5a14-49a8-b05b-a12418aa4150 · outbound

This paper cites Transactions of the Association for Computational Linguistics , volume=.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Transactions of the Association for Computational Linguistics , volume=

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 248d78b7-0775-4a04-97a5-d4f1c87411ee · outbound

This paper cites Proceedings of the 28th International Conference on Computational Linguistics , pages=.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Proceedings of the 28th International Conference on Computational Linguistics , pages=

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a5aa2f9-40a9-43ea-b933-e5fdaada0a3d · outbound

This paper cites , booktitle =.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training , booktitle =

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1636ccea-4aba-48e6-8343-5fdf78133542 · outbound

This paper cites International Conference on Learning Representations , year =.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training International Conference on Learning Representations , year =

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09314f96-f9dd-4848-895b-6b7cc54ef882 · outbound

This paper cites 2024 , journal =.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training 2024 , journal =

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3f41295-1951-4ec3-8171-08b844327783 · outbound

This paper cites Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics , series =.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics , series =

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e907ab96-05b5-4dcf-91c1-32fa797487d2 · outbound

This paper cites NeurIPS 2024 Workshop on Open-World Agents , year =.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training NeurIPS 2024 Workshop on Open-World Agents , year =

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47f6c88c-8c9f-4753-b4ff-868fb9103e9d · outbound

This paper cites Better than Your Teacher:.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Better than Your Teacher:

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1aa0584e-d499-4442-89e9-c32061890140 · outbound

This paper cites Imitation Learning for Multi-turn.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Imitation Learning for Multi-turn

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5e889cd-5754-4c01-930d-a39b34d02dd7 · outbound

This paper cites arXiv preprint arXiv:2509.14257 , year =.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training arXiv preprint arXiv:2509.14257 , year =

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7566ed59-c623-4f54-a6e2-63510dd04df1 · outbound

This paper cites Training.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Training

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8887fa81-7399-464e-9b82-1e1030f2cfef · outbound

This paper cites Embodied Multi-Modal Agent trained by an.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Embodied Multi-Modal Agent trained by an

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c12213ec-23f7-4cf3-a4ae-86a95516436e · outbound

This paper cites 2025 , url =.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training 2025 , url =

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a7b871b0-ba42-4796-bc99-7bd3c9962462 · outbound

This paper cites an unresolved cited work.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2a8967d-58be-4095-805c-67f9ddc5b2e2 · outbound

This paper cites 2025 , url =.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training 2025 , url =

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b55981c8-268b-4ea0-9946-f82fc2f18af4 · outbound

This paper cites Exploring Expert Failures Improves.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Exploring Expert Failures Improves

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a77dc542-0136-4b45-a7e5-72b153350cd4 · outbound

This paper cites International Conference on Learning Representations , year =.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training International Conference on Learning Representations , year =

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3df3476-918e-41df-b903-4bfb0dda6760 · outbound

This paper cites 2024 , url =.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training 2024 , url =

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ce9c6f4-a653-4776-9a20-937823b2a816 · outbound

This paper cites On-Policy Context Distillation for Language Models.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training On-Policy Context Distillation for Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0602a50-ce15-414b-93b8-a369437ef6fd · outbound

This paper cites Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fd401ac-c066-45cc-8213-88020f972d53 · outbound

This paper cites 2026 , url =.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training 2026 , url =

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c18eead2-63eb-4b81-a884-24cc6190f3c9 · outbound

This paper cites arXiv preprint arXiv:2511.10643 , year =.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training arXiv preprint arXiv:2511.10643 , year =

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cedad13-6618-49ef-875e-d3d4b4adc21c · outbound

This paper cites NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f73cbfe-8871-4aba-ac4b-c7fe3dfa51cf · outbound

This paper cites 2023 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2023) , year=.

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training 2023 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2023) , year=

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f56a063-4987-42b8-8411-20189f8b2049 · outbound

This paper cites Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved).

A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training Supervised Fine Tuning on Curated Data is Reinforcement Learning (and can be improved)

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-11T17:03:13.686066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 8a7730c7-d11b-4168-b77c-e229d5970a63 · inbound

CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents cites this paper.

CodeRescue: Budget-Calibrated Recovery Routing for Coding Agents A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T12:47:38.487160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.