Paper Citation Record · LEDGER

Memory Reward Inflation in Self-Improving LLM Agents

As of 8 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2608.00017.

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

pith.paper-citation-record.v1
2608.00017 v1

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-04T02:16:43.153818Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

37 of 37 outbound references displayed

verified exact0
verified fuzzy0
unresolved37
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation fd057453-96b2-4df1-a1ab-376a65485ac9 · outbound

This paper cites Sutton and Andrew G.

Memory Reward Inflation in Self-Improving LLM Agents Sutton and Andrew G

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:40.747999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 447acec5-3a1d-4f99-958d-76c0f90fe96f · outbound

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

Memory Reward Inflation in Self-Improving LLM Agents Reflexion: Language agents with verbal reinforcement learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:40.856553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6f4abcf-f05e-4d6c-bce7-1f0790d49458 · outbound

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

Memory Reward Inflation in Self-Improving LLM Agents Self-refine: Iterative refinement with self-feedback

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:40.977158Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3eae2184-c78d-4153-b98b-ae7922e7dc3b · outbound

This paper cites Memento: Fine-tuning LLM Agents without Fine-tuning LLMs.

Memory Reward Inflation in Self-Improving LLM Agents Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:41.032797Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7930bc81-c268-43a0-9e0b-f5d687120db2 · outbound

This paper cites Christiano, Jan Leike, Tom B.

Memory Reward Inflation in Self-Improving LLM Agents Christiano, Jan Leike, Tom B

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:41.161168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5786c519-f5b3-41e4-842d-710903a365b2 · outbound

This paper cites an unresolved cited work.

Memory Reward Inflation in Self-Improving LLM Agents Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:41.274957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6c6b4a9-8649-4919-83f0-a8c63062c1aa · outbound

This paper cites Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena.

Memory Reward Inflation in Self-Improving LLM Agents Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:41.355262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e747de1-a639-4923-9c64-bc7ae891cec7 · outbound

This paper cites Spontaneous Reward Hacking in Iterative Self-Refinement.

Memory Reward Inflation in Self-Improving LLM Agents Spontaneous Reward Hacking in Iterative Self-Refinement

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:41.453612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35b6a77f-a2ce-47d1-bcad-4aa26abeec89 · outbound

This paper cites ReAct: Synergizing reasoning and acting in language models.

Memory Reward Inflation in Self-Improving LLM Agents ReAct: Synergizing reasoning and acting in language models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:41.531771Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efce4652-528d-4fbf-b651-7b5ec098f964 · outbound

This paper cites Le, and Denny Zhou.

Memory Reward Inflation in Self-Improving LLM Agents Le, and Denny Zhou

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:41.585883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9f74aae-e796-4c1a-a602-ca878731518f · outbound

This paper cites Retrieval-augmented generation for knowledge-intensive NLP tasks.

Memory Reward Inflation in Self-Improving LLM Agents Retrieval-augmented generation for knowledge-intensive NLP tasks

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:41.640511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6f0ec12-58c4-472a-acd2-36a4f878530d · outbound

This paper cites O’Brien, Carrie J.

Memory Reward Inflation in Self-Improving LLM Agents O’Brien, Carrie J

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:41.697684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f525c53-dfb7-4ca9-bea7-94f9b8ef7b97 · outbound

This paper cites ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory.

Memory Reward Inflation in Self-Improving LLM Agents ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:41.810687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3908e104-b9e0-4dac-8be4-f7b14aeb47bd · outbound

This paper cites MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory.

Memory Reward Inflation in Self-Improving LLM Agents MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:41.870358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3ce45e0-ef31-4735-8a5e-1e9c439c1224 · outbound

This paper cites Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning.

Memory Reward Inflation in Self-Improving LLM Agents Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:41.921304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16ca1f9d-4d80-4d02-9ffe-3b8d22a1f76f · outbound

This paper cites Mem-{\alpha}: Learning Memory Construction via Reinforcement Learning.

Memory Reward Inflation in Self-Improving LLM Agents Mem-{\alpha}: Learning Memory Construction via Reinforcement Learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:41.975585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c472d61b-1dc4-45c2-841a-9b957d0c94ef · outbound

This paper cites Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents.

Memory Reward Inflation in Self-Improving LLM Agents Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:42.052502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f38068a7-e067-42f2-8516-ed08db3d8f06 · outbound

This paper cites Learning When to Remember: Risk-Sensitive Contextual Bandits for Abstention-Aware Memory Retrieval in LLM-Based Coding Agents.

Memory Reward Inflation in Self-Improving LLM Agents Learning When to Remember: Risk-Sensitive Contextual Bandits for Abstention-Aware Memory Retrieval in LLM-Based Coding Agents

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:42.111892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53f58fce-b58a-4ba1-b605-2a8acaf8246a · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

Memory Reward Inflation in Self-Improving LLM Agents Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:42.170552Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82440356-8ab7-48d8-9169-ed5612ca0019 · outbound

This paper cites Process reward models that think.arXiv preprint arXiv:2504.16828, 2025.

Memory Reward Inflation in Self-Improving LLM Agents Process reward models that think.arXiv preprint arXiv:2504.16828, 2025

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:42.225662Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a4080ab-d542-4623-b6fc-f8b558591d70 · outbound

This paper cites Self-Preference Bias in LLM-as-a-Judge.

Memory Reward Inflation in Self-Improving LLM Agents Self-Preference Bias in LLM-as-a-Judge

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:42.284063Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4352c5a-0e5b-440b-af5c-2a8cb2ba9922 · outbound

This paper cites Beyond the Surface: Measuring Self-Preference in LLM Judgments.

Memory Reward Inflation in Self-Improving LLM Agents Beyond the Surface: Measuring Self-Preference in LLM Judgments

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:42.324571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd5bacfb-663a-450b-a497-04c25024b9a9 · outbound

This paper cites Nine Judges, Two Effective Votes: Correlated Errors Undermine LLM Evaluation Panels.

Memory Reward Inflation in Self-Improving LLM Agents Nine Judges, Two Effective Votes: Correlated Errors Undermine LLM Evaluation Panels

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:42.387470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93271f3e-459c-4d8a-a4a1-31539340c8a6 · outbound

This paper cites QuickCheck: A lightweight tool for random testing of Haskell programs.

Memory Reward Inflation in Self-Improving LLM Agents QuickCheck: A lightweight tool for random testing of Haskell programs

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:42.432525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af03401f-98e5-498a-a261-110f4ce576aa · outbound

This paper cites Finding and understanding bugs in C compilers.

Memory Reward Inflation in Self-Improving LLM Agents Finding and understanding bugs in C compilers

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:42.487271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46ef34c9-c955-4cc7-b7c5-511c74ad8216 · outbound

This paper cites Metamorphic testing: A new approach for generating next test cases.

Memory Reward Inflation in Self-Improving LLM Agents Metamorphic testing: A new approach for generating next test cases

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:42.553548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 007d0614-1a62-46dc-a84f-6dcd08ccd8f5 · outbound

This paper cites Sanchez, and Antonio Ruiz-Cortés.

Memory Reward Inflation in Self-Improving LLM Agents Sanchez, and Antonio Ruiz-Cortés

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:42.599839Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 627f7534-db2a-4faf-84b4-54f9f4c36b80 · outbound

This paper cites CodeT: Code Generation with Generated Tests.

Memory Reward Inflation in Self-Improving LLM Agents CodeT: Code Generation with Generated Tests

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:42.650963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 789a2fc0-204f-4784-9c26-0b7f2f84402e · outbound

This paper cites SEDM: Scalable self-evolving distributed memory for agents.arXiv preprint arXiv:2509.09498, 2025.

Memory Reward Inflation in Self-Improving LLM Agents SEDM: Scalable self-evolving distributed memory for agents.arXiv preprint arXiv:2509.09498, 2025

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:42.696928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c92c542c-80b1-4a3c-93e5-ed051c3adf30 · outbound

This paper cites A-MemGuard: A proactive defense framework for LLM-based agent memory.arXiv preprint arXiv:2510.02373, 2025.

Memory Reward Inflation in Self-Improving LLM Agents A-MemGuard: A proactive defense framework for LLM-based agent memory.arXiv preprint arXiv:2510.02373, 2025

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:42.741781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6697af4e-3474-45b7-880a-d8c1346fca88 · outbound

This paper cites MemMA: Coordinating the memory cycle through multi-agent reasoning and in-situ self-evolution.arXiv preprint arXiv:2603.18718, 2026.

Memory Reward Inflation in Self-Improving LLM Agents MemMA: Coordinating the memory cycle through multi-agent reasoning and in-situ self-evolution.arXiv preprint arXiv:2603.18718, 2026

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:42.796735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 513546c6-3ba1-4884-aca6-dd24b0455df1 · outbound

This paper cites Useful Memories Become Faulty When Continuously Updated by LLMs.

Memory Reward Inflation in Self-Improving LLM Agents Useful Memories Become Faulty When Continuously Updated by LLMs

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:42.847936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 982f9154-3941-4ad3-9d34-9ddeabfc1b34 · outbound

This paper cites Large Language Models Cannot Self-Correct Reasoning Yet.

Memory Reward Inflation in Self-Improving LLM Agents Large Language Models Cannot Self-Correct Reasoning Yet

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:42.906699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5ca1904-22a6-4d15-8504-7dec3c645ce7 · outbound

This paper cites Estimating the Accuracies of Multiple Classifiers Without Labeled Data.

Memory Reward Inflation in Self-Improving LLM Agents Estimating the Accuracies of Multiple Classifiers Without Labeled Data

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:42.955345Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db240d47-19ca-4da0-8977-24a1072d9624 · outbound

This paper cites The logic of NTQR evaluations of noisy AI agents: Complete postulates and logically consistent error correlations.

Memory Reward Inflation in Self-Improving LLM Agents The logic of NTQR evaluations of noisy AI agents: Complete postulates and logically consistent error correlations

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:43.009324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 972e9bf5-95b7-4051-8b8c-e970ef6b557d · outbound

This paper cites Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs.

Memory Reward Inflation in Self-Improving LLM Agents Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:43.096931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4f5eede-59ea-405a-adce-2633ee73e701 · outbound

This paper cites SimCSE: Simple contrastive learning of sentence embeddings.

Memory Reward Inflation in Self-Improving LLM Agents SimCSE: Simple contrastive learning of sentence embeddings

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T02:16:43.153818Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.