Paper Citation Record · LEDGER

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents

As of 19 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2508.14751.

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

pith.paper-citation-record.v1
2508.14751 v2

Coverage vector

measured 33 of 33 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T18:24:29.852767Z

measured 33 of 33 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

33 of 33 outbound references displayed

verified exact5
verified fuzzy15
unresolved12
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8957f401-e29d-4c0f-950d-0f4fe7fd190e · outbound

This paper cites an unresolved cited work.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-05T18:24:34.691892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 37c612ad-f047-4da9-af10-6424f8929752 · outbound

This paper cites Do As I Can, Not As I Say: Grounding Language in Robotic Affordances.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T18:24:27.867540Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04f70aa2-25a4-41ff-89cd-28ff30bfb6aa · outbound

This paper cites Hierarchical reinforcement learning with natural language subgoals.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Hierarchical reinforcement learning with natural language subgoals

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-08-05T18:24:31.159289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5db288c5-12bc-4ed5-8369-4e301bdd8d41 · outbound

This paper cites Hindsight experience re- play.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Hindsight experience re- play

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T18:24:34.487501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 52ed84e6-fdd1-40e6-b9ca-24620c3c6057 · outbound

This paper cites The option-critic architecture.Proceedings of the AAAI Conference on Artiﬁcial Intelligence, 31(1), Feb.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents The option-critic architecture.Proceedings of the AAAI Conference on Artiﬁcial Intelligence, 31(1), Feb

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T18:24:28.148476Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11f7b691-e8b7-4268-8402-3358956a67d9 · outbound

This paper cites Human-Timescale Adaptation in an Open-Ended Task Space.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Human-Timescale Adaptation in an Open-Ended Task Space

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T18:24:28.233424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c06f52e2-b6c9-4f0a-9894-961853a7bac1 · outbound

This paper cites Integration of action and language knowledge: A roadmap for developmental robotics.Autonomous Mental Development, IEEE Transactions on, 2:167 – 195, 10 2010.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Integration of action and language knowledge: A roadmap for developmental robotics.Autonomous Mental Development, IEEE Transactions on, 2:167 – 195, 10 2010

Reference 7

Resolution: metadata mismatch; raw_fallback, observed 2026-08-05T18:24:30.959095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 4cd1785c-1e3f-454c-afa0-61ed412da49c · outbound

This paper cites Grounding large language models in interactive environments with online reinforcement learning.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Grounding large language models in interactive environments with online reinforcement learning

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T18:24:34.278833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation d070b60a-b4d9-40a3-8c22-f70689296e72 · outbound

This paper cites PARL: A uniﬁed framework for policy alignment in reinforcement learning from human feedback.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents PARL: A uniﬁed framework for policy alignment in reinforcement learning from human feedback

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T18:24:34.061357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation c57734bd-fbb2-4ab6-a39b-515d19c95675 · outbound

This paper cites Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T18:24:28.455014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0dbdf64a-89ca-41aa-9b98-b600d3c585ac · outbound

This paper cites Language and culture internalization for human-like autotelic ai.Nature Machine Intelligence, 4(12):1068–1076, December.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Language and culture internalization for human-like autotelic ai.Nature Machine Intelligence, 4(12):1068–1076, December

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T18:24:33.837215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation b7b6f4cf-b829-443a-8928-c3399dccac25 · outbound

This paper cites Feudal reinforcement learning.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Feudal reinforcement learning

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T18:24:33.616650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f030792c-961d-4528-ad4d-bb0cf2cf1599 · outbound

This paper cites Guiding pretraining in reinforcement learning with large language models.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Guiding pretraining in reinforcement learning with large language models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T18:24:33.434307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fd349959-749b-4ba9-9a51-2bbd164646d8 · outbound

This paper cites Intrinsically motivated open-ended multi-task learning using transfer learning to discover task hierarchy.Applied Sciences, 11(3):975, January 2021.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Intrinsically motivated open-ended multi-task learning using transfer learning to discover task hierarchy.Applied Sciences, 11(3):975, January 2021

Reference 14

Resolution: verified exact; doi, observed 2026-08-05T18:24:30.167603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 2f15fca1-a331-466a-b12c-2d2e67cab7df · outbound

This paper cites Adaptations:V(s 1;z) is not pretrained in our set up but learned during training on collected trajectories.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Adaptations:V(s 1;z) is not pretrained in our set up but learned during training on collected trajectories

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T18:24:31.958256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation fc09c98b-0b95-478e-a0e0-e44b919288e7 · outbound

This paper cites This is repeatedN times; the actual next skill is drawn from the distribution of LLM-assigned token likelihoods, encouraging diversity.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents This is repeatedN times; the actual next skill is drawn from the distribution of LLM-assigned token likelihoods, encouraging diversity

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T18:24:31.675233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 50c5439d-16b3-4fa8-a1ea-a3b512661830 · outbound

This paper cites make wood pickaxe.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents make wood pickaxe

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T18:24:31.316764Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 7a76aade-11a8-4f8d-9e20-c1939952dc90 · outbound

This paper cites Sutton, Doina Precup, and Satinder Singh.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Sutton, Doina Precup, and Satinder Singh

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T18:24:33.216084Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e9ff3b0f-bbba-4e91-a6e8-abe20a825027 · outbound

This paper cites Fundamental processes in sensorimotor learning: Reasoning, reﬁnement, and retrieval.eLife, 13:e91839, aug 2024.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Fundamental processes in sensorimotor learning: Reasoning, reﬁnement, and retrieval.eLife, 13:e91839, aug 2024

Reference 55

Resolution: verified exact; doi, observed 2026-08-05T18:24:30.015115Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a596f9e6-1e67-4c88-a3c7-5cf97fdb72bf · outbound

This paper cites an unresolved cited work.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Unresolved cited work

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-05T18:24:28.920223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64312f54-a420-402f-b57f-718fbf2c938b · outbound

This paper cites On the planning abilities of large language models (a critical investigation with a proposed benchmark),.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents On the planning abilities of large language models (a critical investigation with a proposed benchmark),

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T18:24:33.030694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 86ce88e7-53b9-48c3-ab81-bece52872142 · outbound

This paper cites FeUdal Networks for Hierarchical Reinforcement Learning.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents FeUdal Networks for Hierarchical Reinforcement Learning

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-05T18:24:29.149394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 997fcac4-34ca-4ce7-bbc4-77fa54a4521f · outbound

This paper cites Will we run out of data? Limits of LLM scaling based on human-generated data.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Will we run out of data? Limits of LLM scaling based on human-generated data

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-05T18:24:29.213666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09346e43-0eef-4d83-af17-abff70908469 · outbound

This paper cites Voyager: An Open-Ended Embodied Agent with Large Language Models.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Voyager: An Open-Ended Embodied Agent with Large Language Models

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-05T18:24:29.271710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f55a97d1-9b97-4ddc-b79b-3c9ae54ea63d · outbound

This paper cites Chinese Poetry Generation with Planning based Neural Network.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Chinese Poetry Generation with Planning based Neural Network

Reference 61

Resolution: verified exact; local_arxiv, observed 2026-08-05T18:24:30.507469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 0bc14ca0-0e9d-45ae-993e-45464931683e · outbound

This paper cites Reinforcing llm agents via policy optimization with action decomposition.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Reinforcing llm agents via policy optimization with action decomposition

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T18:24:32.852549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation da3d68e9-939e-4800-ad13-2cc3eff5748b · outbound

This paper cites Coca: Contrastive captioners are image-text foundation models, 2022.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Coca: Contrastive captioners are image-text foundation models, 2022

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T18:24:32.692151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 10ff6f78-edfb-49a9-b653-7e57db2604c4 · outbound

This paper cites Omni: Open-endedness via models of human notions of interestingness.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Omni: Open-endedness via models of human notions of interestingness

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T18:24:32.459146Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation accf1601-a565-4545-8325-f57635025843 · outbound

This paper cites Bootstrap your own skills: Learning to solve new tasks with large language model guidance.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Bootstrap your own skills: Learning to solve new tasks with large language model guidance

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T18:24:32.274478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 560cb814-90b5-43b9-850b-02631f057f85 · outbound

This paper cites Visualize Before You Write: Imagination-Guided Open-Ended Text Generation.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents Visualize Before You Write: Imagination-Guided Open-Ended Text Generation

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-05T18:24:29.664804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d26b740-1674-4893-bfb3-ec15e8982ea3 · outbound

This paper cites doi: 10.1038/s42256-022-00591-4.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents doi: 10.1038/s42256-022-00591-4

Reference 2022

Resolution: verified exact; doi, observed 2026-08-05T18:24:30.315913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 05f93942-02a6-42f4-af4a-2c03df8493c6 · outbound

This paper cites On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark).

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents On the Planning Abilities of Large Language Models (A Critical Investigation with a Proposed Benchmark)

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-05T18:24:29.091692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 387f5504-7cac-4adb-b809-fc0b7f5d7183 · outbound

This paper cites GPT-4 Technical Report.

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents GPT-4 Technical Report

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-05T18:24:27.801385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.