SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models | Paper Citation Record

Observation 6bc64510-d7a8-4b6b-ae97-88ed0445d7e8 · outbound

This paper cites Chain-of-Thought Prompting Elicits Reasoning in Large Language Models.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Chain-of-Thought Prompting Elicits Reasoning in Large Language Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:21.422159Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation caf57f6a-3985-4dc2-a13c-cc6f25390643 · outbound

This paper cites Brown, et al., ”Language models are few-shot learners,” Advances in neural information processing systems , vol.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Brown, et al., ”Language models are few-shot learners,” Advances in neural information processing systems , vol

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:21:26.460187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7294e69b-a06d-4971-b7a0-33b9975637f4 · outbound

This paper cites Available: https: //cloud.google.com/discover/what-is-prompt-engineering.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Available: https: //cloud.google.com/discover/what-is-prompt-engineering

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:21:26.335998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 360bc1a9-d26a-4d62-8911-fd0993a0418b · outbound

This paper cites Avail- able: https://portkey.ai/blog/the-complete-guide-to-prompt-engineering.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Avail- able: https://portkey.ai/blog/the-complete-guide-to-prompt-engineering

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:21:26.200688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 6aade15e-b022-428a-81da-8b6f419984ce · outbound

This paper cites Available: https://latitude-blog.ghost.io/blog/ common-llm-prompt-engineering-challenges-and-solutions/.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Available: https://latitude-blog.ghost.io/blog/ common-llm-prompt-engineering-challenges-and-solutions/

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:21:26.060086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation bd0449fd-ae43-409c-b0af-b657332086fc · outbound

This paper cites Prompt Engineering a Prompt Engineer.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Prompt Engineering a Prompt Engineer

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:21.671226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9422473-02a7-49a3-8f53-65ceadd15f32 · outbound

This paper cites Avail- able: https://portkey.ai/blog/what-is-automated-prompt-engineering.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Avail- able: https://portkey.ai/blog/what-is-automated-prompt-engineering

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:21:25.946407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 4b778348-061b-4f59-909d-5343130e9b39 · outbound

This paper cites Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:21.764324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fadb112-3e34-4123-acd6-4bb9ecb1bb86 · outbound

This paper cites Large Language Models Are Human-Level Prompt Engineers.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Large Language Models Are Human-Level Prompt Engineers

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:21.812199Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 688a6acd-9f61-4798-b6fe-8944716ec071 · outbound

This paper cites Large Language Models as Optimizers.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Large Language Models as Optimizers

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:21.862941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 668de9a0-8e09-4675-a8eb-4e7eed5b9a65 · outbound

This paper cites Avail- able: https://www.promptingguide.ai/techniques/ape.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Avail- able: https://www.promptingguide.ai/techniques/ape

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:21:25.848410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3303ba51-0865-49a4-8ffa-461938986927 · outbound

This paper cites Challagundla, K.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Challagundla, K

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:21.984178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fca162a-3463-441f-8eb9-a4c88a2b70b0 · outbound

This paper cites Efficient Prompting Methods for Large Language Models: A Survey.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Efficient Prompting Methods for Large Language Models: A Survey

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:21.987576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70a361e1-73fa-428d-9c08-02402c90ebd5 · outbound

This paper cites Prefix-Tuning: Optimizing Continuous Prompts for Generation.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Prefix-Tuning: Optimizing Continuous Prompts for Generation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:21.992600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 460a2989-a75d-4641-bb5e-f9a7632e2ddf · outbound

This paper cites Available: https:// learnprompting.org/docs/trainable/prefix-tuning.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Available: https:// learnprompting.org/docs/trainable/prefix-tuning

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:21:25.756318Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation fe6fb1cd-7926-46e0-9556-4034110176e4 · outbound

This paper cites P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:22.152771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba5ebd03-38c7-41a4-8d68-98c8e4a4b5a0 · outbound

This paper cites Available: https://aclanthology.org/2021.emnlp-main.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Available: https://aclanthology.org/2021.emnlp-main

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:21:25.671415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 224d88e8-ab61-4fb8-93bf-d059a9da626b · outbound

This paper cites RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:22.259301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b75e980-cfd6-4bc6-addd-eb7eb977d8a4 · outbound

This paper cites Available: https://blog.ml.cmu.edu/2023/02/24/ rlprompt-optimizing-discrete-text-prompts-with-reinforcement-learning/.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Available: https://blog.ml.cmu.edu/2023/02/24/ rlprompt-optimizing-discrete-text-prompts-with-reinforcement-learning/

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:21:25.553335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 37d7da41-bfd5-4fca-a5f9-f3015fa4cc0c · outbound

This paper cites GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt Optimizers.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models GReaTer: Gradients over Reasoning Makes Smaller Language Models Strong Prompt Optimizers

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:22.393950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4bdd5728-f601-4001-a757-c6e1e5c893f1 · outbound

This paper cites A Survey on Large Language Model based Autonomous Agents.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models A Survey on Large Language Model based Autonomous Agents

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:22.496327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0240ab5e-cc3f-4c13-b515-4e5640e144e8 · outbound

This paper cites AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:22.605249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 405beac8-e407-406f-9f83-66a100bec138 · outbound

This paper cites Available: https://microsoft.github.io/autogen/0.2/docs/Use-Cases/agent chat/.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Available: https://microsoft.github.io/autogen/0.2/docs/Use-Cases/agent chat/

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:21:25.452066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 24af02b0-806f-4345-a562-006b35e871f8 · outbound

This paper cites Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:22.819294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4324abba-b3ac-45ad-b603-d3c28b23fc40 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Constitutional AI: Harmlessness from AI Feedback

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:22.927968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47eb747a-66ef-468f-8f0a-9dbb98baa9fc · outbound

This paper cites Kojima, et al., ”Large language models are zero-shot reasoners,” Advances in neural information processing systems , vol.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Kojima, et al., ”Large language models are zero-shot reasoners,” Advances in neural information processing systems , vol

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:21:25.239189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation cfadfd24-0f40-4c42-b285-729145731039 · outbound

This paper cites Challagundla, M.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Challagundla, M

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:23.149126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dbdd6eb-760a-4e90-8e73-cd9963af6624 · outbound

This paper cites EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:23.230213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c72444b-afdf-44db-9335-3d98478778e1 · outbound

This paper cites StraGo: Harnessing Strategic Guidance for Prompt Optimization.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models StraGo: Harnessing Strategic Guidance for Prompt Optimization

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:23.296225Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c60c9bbc-260c-499f-97d2-5f75df7fd49e · outbound

This paper cites Automatic Prompt Optimization with "Gradient Descent" and Beam Search.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:23.373110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c13daac1-4acf-467d-8ca6-df58ae222450 · outbound

This paper cites Instruction Induction: From Few Examples to Natural Language Task Descriptions.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Instruction Induction: From Few Examples to Natural Language Task Descriptions

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:23.439329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f8fa664-51ce-4c1f-9bdb-d1734e328642 · outbound

This paper cites Fast Parallel Algorithms for Submodular $p$-Superseparable Maximization.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Fast Parallel Algorithms for Submodular $p$-Superseparable Maximization

Reference 33

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T20:21:24.333921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b179139d-dd08-4d4b-858e-a572b7abfa60 · outbound

This paper cites Available: https://aclanthology.org/ 2022.emnlp-main.222.pdf.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Available: https://aclanthology.org/ 2022.emnlp-main.222.pdf

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:21:25.028818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 5b4741a9-ed98-4d8e-9d05-e748a2f25b99 · outbound

This paper cites Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:23.654427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca570bb5-3e53-48d5-b8ec-3debf652c0b9 · outbound

This paper cites Available: https://openreview.net/forum?id=fWRBheSJth.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Available: https://openreview.net/forum?id=fWRBheSJth

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T20:21:24.866659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 012a4a66-8ba2-469c-a3cb-2be4e2574b66 · outbound

This paper cites Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Models.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Models

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-08-06T20:21:24.173835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 888aa557-1475-41a0-a737-f8f414a4101e · outbound

This paper cites LLM Multi-Agent Systems: Challenges and Open Problems.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models LLM Multi-Agent Systems: Challenges and Open Problems

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:23.924275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c81f267a-551c-4725-9dda-a02b928d1ecb · outbound

This paper cites AutoAgents: A Framework for Automatic Agent Generation.

SI-Agent: An Agentic Framework for Feedback-Driven Generation and Tuning of Human-Readable System Instructions for Large Language Models AutoAgents: A Framework for Automatic Agent Generation

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T20:21:24.020429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers