Paper Citation Record · LEDGER

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

As of 15 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 0 inbound Pith citation observations for arXiv:2608.09819.

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

pith.paper-citation-record.v1
2608.09819 v1

Coverage vector

measured 39 of 39 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T10:20:58.914022Z

measured 39 of 39 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+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

39 of 39 outbound references displayed

verified exact4
verified fuzzy3
unresolved28
parse uncertain0
malformed identifier0
metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d2157c7a-f774-426f-be39-b71d0bbfc124 · outbound

This paper cites Effective LoRA adapter routing using task representations.arXiv preprint arXiv:2601.21795,.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Effective LoRA adapter routing using task representations.arXiv preprint arXiv:2601.21795,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.769738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46626407-3a34-4706-9e7d-d7cf09f26a51 · outbound

This paper cites URLhttps://arxiv.org/abs/2601.21795.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA URLhttps://arxiv.org/abs/2601.21795

Reference 5

Resolution: verified exact; doi, observed 2026-08-11T10:20:59.291298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d8d9322c-507c-4525-9c2f-6f0259fb8d79 · outbound

This paper cites Scaling Laws for Reward Model Overoptimization.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Scaling Laws for Reward Model Overoptimization

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.777851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d688194-ab17-429b-92e5-ae0525d82015 · outbound

This paper cites When Does Continual Learning Require Learning.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA When Does Continual Learning Require Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.786739Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5f8eb12-9507-4ec7-93bc-768a35882674 · outbound

This paper cites When Does Continual Learning Require Learning.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA When Does Continual Learning Require Learning

Reference 9

Resolution: metadata mismatch; local_arxiv, observed 2026-08-11T10:20:59.213515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 5c63e113-5cf5-4a02-85b4-dbdd5066365d · outbound

This paper cites EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answering.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answering

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.794678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 184e6838-5e68-4daf-8e57-a559f1cf9c14 · outbound

This paper cites EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answering.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answering

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.798612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fd43145-7b95-4868-b00c-14f5761bf216 · outbound

This paper cites EXG: Self-Evolving Agents with Experience Graphs.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA EXG: Self-Evolving Agents with Experience Graphs

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.802585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81b30585-34cf-4cdd-90ae-407d7037cb26 · outbound

This paper cites EXG: Self-Evolving Agents with Experience Graphs.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA EXG: Self-Evolving Agents with Experience Graphs

Reference 13

Resolution: metadata mismatch; local_arxiv, observed 2026-08-11T10:20:59.180649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7fc3e9a2-d264-4047-851c-f53510a9abe3 · outbound

This paper cites Continual Harness: Online Adaptation for Self-Improving Foundation Agents.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Continual Harness: Online Adaptation for Self-Improving Foundation Agents

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.810377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9f24084-d2ea-46c7-98d5-28d7ec0db68b · outbound

This paper cites Macaron-A2UI: A model for generative UI in per- sonal agents.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Macaron-A2UI: A model for generative UI in per- sonal agents

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:20:59.864008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 688b3930-840c-4736-841f-cbb31a8a45a5 · outbound

This paper cites $\delta$-mem: Efficient Online Memory for Large Language Models.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA $\delta$-mem: Efficient Online Memory for Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.822704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7fdbc8d3-88ca-4113-b39b-d8d61a4a66cf · outbound

This paper cites Every step evolves: Scaling reinforcement learning for trillion-scale thinking model.arXiv preprint arXiv:2510.18855,.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Every step evolves: Scaling reinforcement learning for trillion-scale thinking model.arXiv preprint arXiv:2510.18855,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.830917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa387358-eac2-4fbe-bfe1-010e29d23eb8 · outbound

This paper cites LiveMem: Maintaining Memory State Continuity in Long-Running LLM Inference.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA LiveMem: Maintaining Memory State Continuity in Long-Running LLM Inference

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.835084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation acdbb1d3-cb21-462d-8f2d-4a7f30af94fd · outbound

This paper cites LiveMem: Maintaining Memory State Continuity in Long-Running LLM Inference.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA LiveMem: Maintaining Memory State Continuity in Long-Running LLM Inference

Reference 21

Resolution: metadata mismatch; local_arxiv, observed 2026-08-11T10:20:59.112463Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 982bd53c-d3da-4f94-8099-24a779ac17f4 · outbound

This paper cites Wenhan Ma, Hailin Zhang, Liang Zhao, Yifan Song, Yudong Wang, Zhifang Sui, and Fuli Luo.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Wenhan Ma, Hailin Zhang, Liang Zhao, Yifan Song, Yudong Wang, Zhifang Sui, and Fuli Luo

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.842858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7dfcc882-fb06-4793-b44c-73ab6c54f82b · outbound

This paper cites Categorizing Variants of Goodhart's Law.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Categorizing Variants of Goodhart's Law

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.846775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ff82367-442f-44e8-8dfc-de359d021188 · outbound

This paper cites Kimi K2: Open Agentic Intelligence.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Kimi K2: Open Agentic Intelligence

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.850881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f818168a-3eab-41d1-a6d6-d5391c37f4aa · outbound

This paper cites Qwen3 Technical Report.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Qwen3 Technical Report

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.855224Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2035360d-8b74-4f0f-a772-1d51d97936b6 · outbound

This paper cites AI and the Everything in the Whole Wide World Benchmark.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA AI and the Everything in the Whole Wide World Benchmark

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.859324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95607acd-422d-44a4-8ee7-573b1fda1fda · outbound

This paper cites Shrey Shah and Justin Wagle.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Shrey Shah and Justin Wagle

Reference 27

Resolution: verified exact; raw_fallback, observed 2026-08-11T10:20:59.483187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation c2092b54-9a39-487b-94a6-c9c5b9a90a79 · outbound

This paper cites URLhttps://arxiv.org/abs/2603.15965.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA URLhttps://arxiv.org/abs/2603.15965

Reference 28

Resolution: verified exact; doi, observed 2026-08-11T10:20:59.094451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation a416e684-f3f0-485a-89b1-7bf9f0d119c1 · outbound

This paper cites S-LoRA: Serving Thousands of Concurrent LoRA Adapters.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA S-LoRA: Serving Thousands of Concurrent LoRA Adapters

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.872081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cec6d5a-cdd8-4bb8-981e-2edf6b9ed06c · outbound

This paper cites Evaluating AI systems under contextual uncertainty.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Evaluating AI systems under contextual uncertainty

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:20:59.851382Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8afba3e3-21ed-4c4d-913c-ba3da103a622 · outbound

This paper cites LaMDA: Language Models for Dialog Applications.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA LaMDA: Language Models for Dialog Applications

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.880964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf6aa913-5a21-413c-860d-ca8f2df86f1e · outbound

This paper cites Multi-Agent Collaboration Mechanisms: A Survey of LLMs.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Multi-Agent Collaboration Mechanisms: A Survey of LLMs

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.885048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44362bcd-9e3e-4a14-9d36-132288a348af · outbound

This paper cites Multi-Agent Collaboration Mechanisms: A Survey of LLMs.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Multi-Agent Collaboration Mechanisms: A Survey of LLMs

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.889044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2446b99b-6161-4c20-9690-73063efb64e2 · outbound

This paper cites Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Decomposing the Basic Abilities of Large Language Models: Mitigating Cross-Task Interference in Multi-Task Instruct-Tuning

Reference 34

Resolution: metadata mismatch; local_arxiv, observed 2026-08-11T10:20:58.964669Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1eba1413-2bbd-4a3a-a858-f120a5eed352 · outbound

This paper cites Executable Code Actions Elicit Better LLM Agents.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Executable Code Actions Elicit Better LLM Agents

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.897424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 415577af-7a4e-488c-a09d-c657fd7526b5 · outbound

This paper cites Efficient LLM agents with REPL harnesses: Executable composition and validated reuse.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Efficient LLM agents with REPL harnesses: Executable composition and validated reuse

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T10:20:59.838840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 55c1c479-5e27-4c2d-888d-768bd443b47a · outbound

This paper cites Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.905636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70f38476-f930-43d6-985c-0e0a10ce613f · outbound

This paper cites LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

Reference 38

Resolution: verified exact; local_arxiv, observed 2026-08-11T10:20:59.336737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 206253d0-070e-4ad4-a5df-689771b3092e · outbound

This paper cites MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.914022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ac13e61-474e-4525-9d75-c60b6d14505e · outbound

This paper cites Beyond Static Models: An Evolving Framework for Continual Learning in Large Language Models across Training Stages.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Beyond Static Models: An Evolving Framework for Continual Learning in Large Language Models across Training Stages

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.760138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6dfd8244-7b67-4e97-a342-96b251e1d6f3 · outbound

This paper cites GLM-5: from Vibe Coding to Agentic Engineering.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA GLM-5: from Vibe Coding to Agentic Engineering

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.782536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a67aa7b5-f969-44f3-916e-078a48a74d70 · outbound

This paper cites Recursive Harness Self-Improvement.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Recursive Harness Self-Improvement

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.818598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b94b6b5-95a5-465f-b1be-3a32ee14a82a · outbound

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

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Recursive Self-Improvement in AI: From Bounded Self-Refinement to Autonomous Research Loops

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.764730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2d17029-7de0-4b96-bc3f-6df644aae589 · outbound

This paper cites Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.826813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 278c8f23-f6ca-4367-9807-70f3fc487741 · outbound

This paper cites What Will it Take to Fix Benchmarking in Natural Language Understanding?.

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA What Will it Take to Fix Benchmarking in Natural Language Understanding?

Reference 2026

Resolution: unresolved; no resolver link, observed 2026-08-11T10:20:58.755608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.