Paper Citation Record · LEDGER

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement

As of 17 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 1 inbound Pith citation observation for arXiv:2504.20459.

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

pith.paper-citation-record.v1
2504.20459 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T05:34:53.520065Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T14:43:36.668353Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T14:43:40.206081Z

Reference resolution

37 of 37 outbound references displayed

verified exact0
verified fuzzy24
unresolved13
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 0562b247-d141-41db-990f-7f425f85d689 · outbound

This paper cites Hudson, Ehsan Adeli, Russ Altman, Simran Arora, Sydney von Arx, Michael S.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Hudson, Ehsan Adeli, Russ Altman, Simran Arora, Sydney von Arx, Michael S

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:54.185099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ad71f342-911a-43ca-96a7-e2e79680bea0 · outbound

This paper cites Chain-of- thought prompting elicits reasoning in large language models.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Chain-of- thought prompting elicits reasoning in large language models

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:54.165008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f292d68a-49e3-4c1e-bb88-d049e17b8fef · outbound

This paper cites Repository- level prompt generation for large language models of code.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Repository- level prompt generation for large language models of code

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:54.142559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 23ec7ddc-35e6-47e3-b62c-25a7baf527c5 · outbound

This paper cites Le, Ed H.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Le, Ed H

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:54.120197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4112668d-3859-4e7b-bd55-0a283339bf49 · outbound

This paper cites Solving quantitative reason- ing problems with language models.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Solving quantitative reason- ing problems with language models

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:54.104018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 308598f1-064b-424f-95d1-c21998dfc726 · outbound

This paper cites Large language models as general pattern machines.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Large language models as general pattern machines

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:54.086135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 55ce4fef-c0a4-456b-91be-82beb7df48ec · outbound

This paper cites Do as i can, not as i say: Grounding language in robotic affordances.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Do as i can, not as i say: Grounding language in robotic affordances

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:54.063197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 4ce1adae-2adc-40c0-95da-cb5fb4d57e74 · outbound

This paper cites Roco: Dialectic multi- robot collaboration with large language models.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Roco: Dialectic multi- robot collaboration with large language models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T05:34:53.336161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f510989-1430-4489-b957-0d8a1b5242fb · outbound

This paper cites Code as Policies: Language Model Programs for Embodied Control.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Code as Policies: Language Model Programs for Embodied Control

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T05:34:53.342378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a041ceac-5457-489a-9a3f-fb72c67ebaa4 · outbound

This paper cites an unresolved cited work.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-16T05:34:54.025119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f63d3cfb-2d87-4a16-929d-9411df7fb711 · outbound

This paper cites Policy gradient methods for robotics.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Policy gradient methods for robotics

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:53.999455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cc11aad1-7073-4acc-b987-12b56bd3aaff · outbound

This paper cites Learning robot actions based on self-organising language memory.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Learning robot actions based on self-organising language memory

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:53.979584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ff2dbf22-a8c6-4d48-9518-d11cf8f4c85a · outbound

This paper cites A holistic approach to compositional semantics: a connectionist model and robot experiments.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement A holistic approach to compositional semantics: a connectionist model and robot experiments

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:53.959017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5ebf953b-7743-4c97-9f5c-101f514baa56 · outbound

This paper cites Corrado, and Jeffrey Dean.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Corrado, and Jeffrey Dean

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T05:34:53.375269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e048091-ba7a-4a23-bb13-23450ed4974d · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Gemini: A Family of Highly Capable Multimodal Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T05:34:53.381487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdc0359f-f8dc-488c-9678-0e4e7c1732fd · outbound

This paper cites GPT-4 Technical Report.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement GPT-4 Technical Report

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T05:34:53.387959Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 491170ec-f16b-40b0-9fca-5671b8efaaea · outbound

This paper cites Language-conditioned imitation learning for robot manipulation tasks.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Language-conditioned imitation learning for robot manipulation tasks

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-16T05:34:53.393843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd0b3821-2d58-45c9-8df4-868bd3e484c7 · outbound

This paper cites Language Conditioned Imitation Learning Over Unstructured Data.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Language Conditioned Imitation Learning Over Unstructured Data

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:53.919868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 19c1b60f-b217-4c08-8f2a-81924544e848 · outbound

This paper cites Inner monologue: Embodied reasoning through planning with language models.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Inner monologue: Embodied reasoning through planning with language models

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:53.901398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fc80df36-2173-4732-a66f-bd487c0e5d83 · outbound

This paper cites Llm-planner: Few-shot grounded planning for embodied agents with large language models.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Llm-planner: Few-shot grounded planning for embodied agents with large language models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:53.884566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d2a18373-5b2a-41f5-a944-ff725f89021d · outbound

This paper cites Task and motion planning with large language models for object rearrangement.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Task and motion planning with large language models for object rearrangement

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:53.868234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2a8053a6-bdc3-447d-8321-3bcd35fd34d7 · outbound

This paper cites Eureka: Human-level reward design via coding large language models.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Eureka: Human-level reward design via coding large language models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T05:34:53.432527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40ae87d5-8966-49a1-ac7a-95c1bb380bcc · outbound

This paper cites In-Context Imitation Learning via Next-Token Prediction.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement In-Context Imitation Learning via Next-Token Prediction

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T05:34:53.438385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8038367e-087c-4f9f-87ff-734bb4bb6b3e · outbound

This paper cites Keypoint Action Tokens En- able In-Context Imitation Learning in Robotics.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Keypoint Action Tokens En- able In-Context Imitation Learning in Robotics

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:53.836123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 37a22f6c-af8a-4c67-ab7a-c45cb712cf47 · outbound

This paper cites Learning to learn faster from human feedback with language model predictive control, 2024.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Learning to learn faster from human feedback with language model predictive control, 2024

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:53.818429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation e422251e-1bba-433f-9f5c-8bc5bdd84525 · outbound

This paper cites Kumar, Emilien Dupont, Francisco Ruiz, Jordan Ellenberg, Pengming Wang, Omar Fawzi, Pushmeet Kohli, and Alhussein Fawzi.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Kumar, Emilien Dupont, Francisco Ruiz, Jordan Ellenberg, Pengming Wang, Omar Fawzi, Pushmeet Kohli, and Alhussein Fawzi

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:53.802073Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3af525e8-de1d-49ea-a333-690a0d09b84c · outbound

This paper cites Le, Denny Zhou, and Xinyun Chen.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Le, Denny Zhou, and Xinyun Chen

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:53.785499Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a53c5dd8-272d-4c22-8f7c-a8ffef1d72d4 · outbound

This paper cites Using large language models for hyperparameter opti- mization.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Using large language models for hyperparameter opti- mization

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:53.769041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b18bf4c0-fe23-4e1d-9ffa-b3b547a48f63 · outbound

This paper cites Learning to select and generalize striking movements in robot table tennis.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Learning to select and generalize striking movements in robot table tennis

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-16T05:34:53.472671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6f560a4-243b-47d3-a065-76a800bc49e7 · outbound

This paper cites Robotic Table Tennis: A Case Study into a High Speed Learning System.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Robotic Table Tennis: A Case Study into a High Speed Learning System

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:53.739313Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 57af96a3-4a26-45d6-a9e0-7e28acce2dc9 · outbound

This paper cites i-sim2real: Reinforcement learning of robotic policies in tight human-robot interaction loops.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement i-sim2real: Reinforcement learning of robotic policies in tight human-robot interaction loops

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:53.722151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 350bd471-9ec1-4f1c-aeaf-83938ec9007f · outbound

This paper cites Achieving Human Level Competitive Robot Table Tennis.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Achieving Human Level Competitive Robot Table Tennis

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-16T05:34:53.489368Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ca802ac-9b42-4f57-9e89-f2b388f0da14 · outbound

This paper cites Adam: A method for stochastic op- timization.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Adam: A method for stochastic op- timization

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:53.703622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f521c9a2-8c11-44d6-8f65-92718d8106ce · outbound

This paper cites A simplex method for function minimization.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement A simplex method for function minimization

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T05:34:53.500546Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7303d748-dc10-46bd-b9f4-a53a0f28baab · outbound

This paper cites The convergence of the random search method in the extremal control of a many parameter system.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement The convergence of the random search method in the extremal control of a many parameter system

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-16T05:34:53.506394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5b5c769-e27f-42f7-8f20-8b5cef8a2759 · outbound

This paper cites A connectionist machine for genetic hillclimbing , volume 28.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement A connectionist machine for genetic hillclimbing , volume 28

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:53.666336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 361f10c1-771d-4e5a-9a2e-cf8e98846741 · outbound

This paper cites Fancy gym.

SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement Fancy gym

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T05:34:53.648805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Pith citing papers

Observation be4a0ae4-f381-47ac-91fc-3aaf41eceecd · inbound

HITTER: A HumanoId Table TEnnis Robot via Hierarchical Planning and Learning cites this paper.

HITTER: A HumanoId Table TEnnis Robot via Hierarchical Planning and Learning SAS-Prompt: Large Language Models as Numerical Optimizers for Robot Self-Improvement

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-05T14:43:40.298447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.