Paper Citation Record · LEDGER

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning

As of 21 August 2026, this Paper Citation Record lists 95 of 95 outbound references and 3 inbound Pith citation observations for arXiv:2506.05109.

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

pith.paper-citation-record.v1
2506.05109 v1

Coverage vector

measured 95 of 95 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T10:28:24.695242Z

measured 98 of 98 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T01:01:38.475397Z

measured 1 of 1 external citation measurements

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

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

Reference resolution

95 of 95 outbound references displayed

verified exact0
verified fuzzy33
unresolved62
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

2
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation d5a42c6a-9ccf-4747-9c48-3453a2caed51 · outbound

This paper cites write newline.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:16.760749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e146ce08-8442-47ea-baba-77c1d7e78c41 · outbound

This paper cites ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning ReST meets ReAct: Self-Improvement for Multi-Step Reasoning LLM Agent

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:16.864213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e94ea10d-0614-4f9b-860c-ae435ececd19 · outbound

This paper cites DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:16.963397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42676b98-b535-4b3e-806e-cb062700f94d · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Constitutional AI: Harmlessness from AI Feedback

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:17.065407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9fc23d32-3abb-4533-b8b7-d752cbf6cdfd · outbound

This paper cites Human-timescale adaptation in an open-ended task space.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Human-timescale adaptation in an open-ended task space

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:17.166714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9027692-9226-49ec-a94c-162ff8aa8467 · outbound

This paper cites M., Gebru, T., McMillan-Major, A., and Shmitchell, S.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning M., Gebru, T., McMillan-Major, A., and Shmitchell, S

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:17.243242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4a7c8a1-d526-498d-ada7-ef02fb380f90 · outbound

This paper cites Curriculum learning.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Curriculum learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:17.306726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d6eabb9-39cb-45ba-8af2-c442f20bd220 · outbound

This paper cites B., Zhang, J., Oostermeijer, K., Bellagente, M., Clune, J., Stanley, K., Schott, G., and Lehman, J.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning B., Zhang, J., Oostermeijer, K., Bellagente, M., Clune, J., Stanley, K., Schott, G., and Lehman, J

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:17.380705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09013d81-5b43-452a-a558-fc3123a7320c · outbound

This paper cites Metacognition, executive control, self-regulation, and other more mysterious mechanisms.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Metacognition, executive control, self-regulation, and other more mysterious mechanisms

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:17.459026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ee11e9a-3e13-4e8e-8618-5c454426f0f7 · outbound

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

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:17.544773Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e865748-7cec-4e32-bf0a-dbb511d75b72 · outbound

This paper cites D., Edwards, A., Parker-Holder, J., Shi, Y., Hughes, E., Lai, M., Mavalankar, A., Steigerwald, R., Apps, C., et al.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning D., Edwards, A., Parker-Holder, J., Shi, Y., Hughes, E., Lai, M., Mavalankar, A., Steigerwald, R., Apps, C., et al

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:17.620825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8f435bf-9fb7-4b6c-b76f-897d41a99e53 · outbound

This paper cites Alphamath almost zero: Process supervision without process.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Alphamath almost zero: Process supervision without process

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:17.712364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb335fc1-f301-4df1-95e0-d15d1313ee77 · outbound

This paper cites Teaching large language models to self-debug.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Teaching large language models to self-debug

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:17.793828Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a47be92-21f4-4c31-be34-4591795da1d1 · outbound

This paper cites N., Li, T., Li, D., Zhu, B., Zhang, H., Jordan, M., Gonzalez, J.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning N., Li, T., Li, D., Zhu, B., Zhang, H., Jordan, M., Gonzalez, J

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:17.871805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dffe7a3b-37f3-47b6-b933-da2c3552a718 · outbound

This paper cites On the Measure of Intelligence.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning On the Measure of Intelligence

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:17.940922Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 631581fb-b26f-4552-9927-82f102ecc763 · outbound

This paper cites W., Sutton, C., Gehrmann, S., et al.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning W., Sutton, C., Gehrmann, S., et al

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:18.043043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27828ccd-c7bd-4550-9724-6e956804c27b · outbound

This paper cites W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, Y., Wang, X., Dehghani, M., Brahma, S., et al.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning W., Hou, L., Longpre, S., Zoph, B., Tay, Y., Fedus, W., Li, Y., Wang, X., Dehghani, M., Brahma, S., et al

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:18.112668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62529be3-2c24-43ca-b538-79c462921deb · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Training Verifiers to Solve Math Word Problems

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:18.211427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a08b2ae-80c5-4ce0-971d-567f9e5dbde8 · outbound

This paper cites an unresolved cited work.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:18.283310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66b7c29f-e2fe-409e-9379-724d0af430c3 · outbound

This paper cites Meta-rules: Reasoning about control.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Meta-rules: Reasoning about control

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:18.356818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bf443c0-3679-4e42-87b2-eea0fb618d92 · outbound

This paper cites Emergent complexity and zero-shot transfer via unsupervised environment design.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Emergent complexity and zero-shot transfer via unsupervised environment design

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:34.064823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 21ae20e8-1966-4d87-a94f-1e426f679340 · outbound

This paper cites Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:18.501424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d56e7b4-087a-4ddc-a7e9-86f30a67f08c · outbound

This paper cites F., Lan, Q., Rahman, P., Mahmood, A.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning F., Lan, Q., Rahman, P., Mahmood, A

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:18.582485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2f7922e-b28a-4a07-af18-4cceb61e88e6 · outbound

This paper cites RAFT : Reward ranked finetuning for generative foundation model alignment.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning RAFT : Reward ranked finetuning for generative foundation model alignment

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:18.670347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6225795-fd3d-4425-aa41-bb93d186e8cc · outbound

This paper cites OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:18.762189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fe51d09-b95f-4a68-91b9-485fa1565199 · outbound

This paper cites an unresolved cited work.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:28:33.821225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 40115d67-a1fa-496d-b6ad-69fd02f1ae4c · outbound

This paper cites S., Bredeweg, B., and van den Bos, W.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning S., Bredeweg, B., and van den Bos, W

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:33.573085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8ca6eb6f-9fff-4bca-91d4-20e5637d4d50 · outbound

This paper cites an unresolved cited work.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:28:33.299726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5516b231-b978-414d-84aa-af0238a9044d · outbound

This paper cites Auto-gpt: An autonomous gpt-4 experiment, 2023.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Auto-gpt: An autonomous gpt-4 experiment, 2023

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:33.062588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1b64439d-31d9-4c67-8bb2-151b1333ffdf · outbound

This paper cites Connecting large language models with evolutionary algorithms yields powerful prompt optimizers.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Connecting large language models with evolutionary algorithms yields powerful prompt optimizers

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:19.218992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4dfa4d5-baa4-4f18-b9dd-9f474cf778d3 · outbound

This paper cites V., Safdari, M., Matsuo, Y., Eck, D., and Faust, A.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning V., Safdari, M., Matsuo, Y., Eck, D., and Faust, A

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:32.899862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e7d02b9a-2cd2-4860-a31b-43f333446651 · outbound

This paper cites J., Wang, Z., Wang, D.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning J., Wang, Z., Wang, D

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:32.617602Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a53a291c-66f3-4219-8f0f-dc8fd58cf89f · outbound

This paper cites Teaching Large Language Models to Reason with Reinforcement Learning.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Teaching Large Language Models to Reason with Reinforcement Learning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:19.442762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0204f75-9542-43a9-b767-fc3e4bfcc5e0 · outbound

This paper cites Measuring massive multitask language understanding.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Measuring massive multitask language understanding

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:19.521152Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae3e674f-e94f-4f6b-8863-07c8d8f3b981 · outbound

This paper cites an unresolved cited work.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:28:32.390166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation cf752242-d7b8-446a-af39-b098f6a75ce8 · outbound

This paper cites D., Parker-Holder, J., Behbahani, F., Mavalankar, A., Shi, Y., Schaul, T., and Rockt\" a schel, T.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning D., Parker-Holder, J., Behbahani, F., Mavalankar, A., Shi, Y., Schaul, T., and Rockt\" a schel, T

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:32.170040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation fd7f6e70-1b1b-4e15-9bdc-ada83a9c63d2 · outbound

This paper cites Prioritized level replay.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Prioritized level replay

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:19.727240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b4168f6-d3d7-4e17-b2da-398db35c9093 · outbound

This paper cites SelfEvolve: A Code Evolution Framework via Large Language Models.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning SelfEvolve: A Code Evolution Framework via Large Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:19.784378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 483af8bf-ca6b-47c4-985c-d011d718f506 · outbound

This paper cites G., Karimi, A.-H., Bengio, Y., Chater, N., Gerstenberg, T., Larson, K., Levine, S., Mitchell, M., Rahwan, I., Sch \"o lkopf, B., et al.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning G., Karimi, A.-H., Bengio, Y., Chater, N., Gerstenberg, T., Larson, K., Levine, S., Mitchell, M., Rahwan, I., Sch \"o lkopf, B., et al

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:19.854733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66444608-831f-4293-83e9-155342fc7419 · outbound

This paper cites Language Models (Mostly) Know What They Know.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Language Models (Mostly) Know What They Know

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:19.943318Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba02476b-bd30-4c52-b294-8734a5c49572 · outbound

This paper cites V., Haq, S., Sharma, A., Joshi, T.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning V., Haq, S., Sharma, A., Joshi, T

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:31.893092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 51757441-9150-431e-aa24-fd0d10aebad6 · outbound

This paper cites an unresolved cited work.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:28:31.716688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2bb84647-02cd-47b7-9ed1-5021916bf16c · outbound

This paper cites and Bjork, R.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning and Bjork, R

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:31.456959Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 51fc9f4b-bfae-4297-b83d-c53da0e89c7a · outbound

This paper cites Specification gaming: the flip side of ai ingenuity.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Specification gaming: the flip side of ai ingenuity

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:31.222136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ac17182f-6518-44fd-a519-b0d881fcda3d · outbound

This paper cites M., Ullman, T.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning M., Ullman, T

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:20.404733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60791e4c-a5a6-4082-aaa2-f021a86eb949 · outbound

This paper cites u ttler, H., Lewis, M., Yih, W.-t., Rockt \.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning u ttler, H., Lewis, M., Yih, W.-t., Rockt \

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:20.489962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73c32ec4-069d-401c-8c87-252cb280e432 · outbound

This paper cites From quantity to quality: Boosting llm performance with self-guided data selection for instruction tuning.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning From quantity to quality: Boosting llm performance with self-guided data selection for instruction tuning

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:31.039020Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ba3a48cd-c8d5-4c2c-a5b6-45fde16add6b · outbound

This paper cites I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBench.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBench

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:20.658807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b43ef41f-fa84-4658-9ea7-de02a61f1389 · outbound

This paper cites The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:20.727797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40d65aee-ce1b-4bc5-b4b8-ea89df7cf338 · outbound

This paper cites J., Liang, W., Wang, G., Huang, D.-A., Bastani, O., Jayaraman, D., Zhu, Y., Fan, L., and Anandkumar, A.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning J., Liang, W., Wang, G., Huang, D.-A., Bastani, O., Jayaraman, D., Zhu, Y., Fan, L., and Anandkumar, A

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:30.860012Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c615e20f-bd51-4cea-aff0-54e1317ede47 · outbound

This paper cites Self-refine: Iterative refinement with self-feedback.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Self-refine: Iterative refinement with self-feedback

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:30.684549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ad6c4fc7-72ad-4f03-a28a-250c701d527a · outbound

This paper cites WebGPT: Browser-assisted question-answering with human feedback.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning WebGPT: Browser-assisted question-answering with human feedback

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:20.990171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2a9e057-9368-4e74-8220-df685b85f6c8 · outbound

This paper cites Superintelligence: Paths, dangers, strategies.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Superintelligence: Paths, dangers, strategies

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:30.509798Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 09207605-cc07-4509-aea2-c76672548ac3 · outbound

This paper cites Training language models to follow instructions with human feedback.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Training language models to follow instructions with human feedback

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:21.105201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df850d23-ee5a-4659-8ce3-27779a4d418c · outbound

This paper cites S., O'Brien, J., Cai, C.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning S., O'Brien, J., Cai, C

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:21.216381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2df7fb13-680e-46e2-8e24-f348bcf72c1b · outbound

This paper cites an unresolved cited work.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Unresolved cited work

Reference 56

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:28:30.313778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7498d1e4-28c7-4c4e-bd30-e41f5108b9a1 · outbound

This paper cites WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:21.810260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30502117-d889-4cb3-a595-72b0f13334f8 · outbound

This paper cites Vision-language models are zero-shot reward models for reinforcement learning.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Vision-language models are zero-shot reward models for reinforcement learning

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:30.103119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 11fd6b50-2753-46a7-9216-7e01d06c192d · outbound

This paper cites Human-compatible artificial intelligence., 2022.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Human-compatible artificial intelligence., 2022

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:29.909495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation cdb1ccfa-6327-4cb3-b2c3-92f5a888b56b · outbound

This paper cites and Wefald, E.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning and Wefald, E

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:29.623871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation baf9518d-8283-4d8e-9693-627a73a6bf4c · outbound

This paper cites How to Train Data-Efficient LLMs.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning How to Train Data-Efficient LLMs

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:22.198008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab7052d9-503e-499e-87d6-7bd2c7654320 · outbound

This paper cites Toolformer: Language models can teach themselves to use tools.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Toolformer: Language models can teach themselves to use tools

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:22.274561Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 443bb5cb-4018-490b-b9b9-18ac5afe28b8 · outbound

This paper cites an unresolved cited work.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Unresolved cited work

Reference 63

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:28:29.420717Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 93f1d9a9-a8ef-4323-bd4a-7a621876368d · outbound

This paper cites Reflexion: Language agents with verbal reinforcement learning.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Reflexion: Language agents with verbal reinforcement learning

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:29.283609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 40856bd1-7d7e-4c60-a168-2e8075a191a3 · outbound

This paper cites J., Guez, A., Sifre, L., Van Den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning J., Guez, A., Sifre, L., Van Den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:22.627881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdcfe909-8341-4704-a609-08fa553736ad · outbound

This paper cites D., Agarwal, R., Anand, A., Patil, P., Garcia, X., Liu, P.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning D., Agarwal, R., Anand, A., Patil, P., Garcia, X., Liu, P

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:29.098415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e61b5bbf-b799-4ccf-ab58-29688b857d9b · outbound

This paper cites Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:22.812009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 820c7bdb-02f5-48c3-96ed-324ac61af2ef · outbound

This paper cites an unresolved cited work.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:28:28.915071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 323dc2fc-943f-4f59-ad20-d2d20ad8219d · outbound

This paper cites Cognitive architectures for language agents.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Cognitive architectures for language agents

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:28.732086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b2dffad8-29b1-4541-a89c-38c105103b2b · outbound

This paper cites an unresolved cited work.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Unresolved cited work

Reference 70

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:28:28.586189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a67b8b24-e232-4bcd-b90b-120a90925c11 · outbound

This paper cites E., Sarkar, A., Sellen, A., and Rintel, S.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning E., Sarkar, A., Sellen, A., and Rintel, S

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:28.383657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 70fdfd3d-505d-474c-a5e4-c203e2f899ba · outbound

This paper cites A Survey on Self-Evolution of Large Language Models.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning A Survey on Self-Evolution of Large Language Models

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:23.089533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d6ff0b8-97c5-4fc3-bfc1-4512b44c9322 · outbound

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

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Voyager: An Open-Ended Embodied Agent with Large Language Models

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:23.137247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 629e8220-685f-4277-a032-089cd9067781 · outbound

This paper cites A survey on large language model based autonomous agents.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning A survey on large language model based autonomous agents

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:23.177586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4016d8fb-0416-4ee8-b916-2a432988204a · outbound

This paper cites Emotional intelligence of large language models.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Emotional intelligence of large language models

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:28.205033Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1479d99f-2c4b-44c6-99bf-8dc5754350bf · outbound

This paper cites A., Khashabi, D., and Hajishirzi, H.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning A., Khashabi, D., and Hajishirzi, H

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:28.047808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation afc6906f-b03c-4154-afbe-f1a097ba562b · outbound

This paper cites Metacognitive ai: Framework and the case for a neurosymbolic approach.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Metacognitive ai: Framework and the case for a neurosymbolic approach

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:27.910261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 81814fb6-e247-44eb-a405-d2462cf588e7 · outbound

This paper cites an unresolved cited work.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Unresolved cited work

Reference 78

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:28:27.667495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8c3c78bd-e0b5-4bf6-b3c9-d6638188751c · outbound

This paper cites OS-Copilot: Towards Generalist Computer Agents with Self-Improvement.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning OS-Copilot: Towards Generalist Computer Agents with Self-Improvement

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:23.486683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2643ba2a-11b2-4363-93a8-c3af68948a40 · outbound

This paper cites The Rise and Potential of Large Language Model Based Agents: A Survey.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning The Rise and Potential of Large Language Model Based Agents: A Survey

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:23.548433Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44e9f224-5fcb-4450-aa4d-9914b7b83ca8 · outbound

This paper cites J., Cheng, Z., Shin, D., Lei, F., Liu, Y., Xu, Y., Zhou, S., Savarese, S., Xiong, C., Zhong, V., and Yu, T.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning J., Cheng, Z., Shin, D., Lei, F., Liu, Y., Xu, Y., Zhou, S., Savarese, S., Xiong, C., Zhong, V., and Yu, T

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:27.400891Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b0f540aa-993d-4aa0-9589-bd3ba0804f5c · outbound

This paper cites V., Zhou, D., and Chen, X.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning V., Zhou, D., and Chen, X

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:27.170574Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 7e3049ec-fa99-4f67-91a4-5748dc1390b0 · outbound

This paper cites an unresolved cited work.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Unresolved cited work

Reference 83

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:28:26.951792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation bc5afa07-cc54-4c53-ab1e-7bd5f0de81bc · outbound

This paper cites Failures pave the way: Enhancing large language models through tuning-free rule accumulation.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Failures pave the way: Enhancing large language models through tuning-free rule accumulation

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:26.707251Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 57f0e311-d0bc-43f9-9515-511447d82332 · outbound

This paper cites R., and Cao, Y.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning R., and Cao, Y

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:26.549263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 45ab5fba-cc3c-4747-850f-0e62de2600f7 · outbound

This paper cites Star: Bootstrapping reasoning with reasoning.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Star: Bootstrapping reasoning with reasoning

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:26.379100Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e0761761-8e2d-4193-a640-865a86194ce8 · outbound

This paper cites Large language models are semi-parametric reinforcement learning agents.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Large language models are semi-parametric reinforcement learning agents

Reference 87

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:26.190985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a6e1580c-d7a3-4dea-9374-2b80f795498a · outbound

This paper cites AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:24.108717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 748cf989-85bc-4426-8237-273a1c18150f · outbound

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

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning OMNI : Open-endedness via models of human notions of interestingness

Reference 89

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:26.008245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 333dd0ed-4f18-4a42-bf3f-c123bf8e197a · outbound

This paper cites Expel: Llm agents are experiential learners.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Expel: Llm agents are experiential learners

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:24.270265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53795e59-98ae-4552-9f91-01f1dcf8c4ae · outbound

This paper cites Empowering Large Language Model Agents through Action Learning.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Empowering Large Language Model Agents through Action Learning

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:24.359078Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4a8b815d-0033-4f99-bf35-198c76937523 · outbound

This paper cites E., and Stoica, I.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning E., and Stoica, I

Reference 92

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:25.826078Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation c915e8ba-3de0-4194-add4-072dee8df19d · outbound

This paper cites and Hadfield-Menell, D.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning and Hadfield-Menell, D

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:25.618435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation dad5cf41-3360-4ff9-a46e-8e52d69b4ef8 · outbound

This paper cites GPTS warm: Language agents as optimizable graphs.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning GPTS warm: Language agents as optimizable graphs

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:25.415949Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 29c2ecbb-7d46-4643-a6eb-7b204d76a3f5 · outbound

This paper cites an unresolved cited work.

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning Unresolved cited work

Reference 95

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:28:25.213666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Pith citing papers

Observation 62023054-4f59-4d22-a34e-161cd3d1902c · inbound

Galaxy: A Cognition-Centered Framework for Proactive, Privacy-Preserving, and Self-Evolving LLM Agents cites this paper.

Galaxy: A Cognition-Centered Framework for Proactive, Privacy-Preserving, and Self-Evolving LLM Agents Truly Self-Improving Agents Require Intrinsic Metacognitive Learning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T01:01:38.475397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c14027cb-b536-4031-babb-0b38c0958ac8 · inbound

Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation cites this paper.

Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation Truly Self-Improving Agents Require Intrinsic Metacognitive Learning

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-06-26T08:49:15.256236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1e3ff57d-18da-485b-b977-6daeef297033 · inbound

Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops cites this paper.

Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops Truly Self-Improving Agents Require Intrinsic Metacognitive Learning

Reference 61

Resolution: verified exact; local_arxiv, observed 2026-07-09T03:45:55.365517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.