Paper Citation Record · LEDGER

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization

As of 10 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 1 inbound Pith citation observation for arXiv:2605.16299.

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

pith.paper-citation-record.v1
2605.16299 v2

Coverage vector

measured 18 of 18 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-22T10:14:00.478000Z

measured 19 of 19 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T19:47:59.194199Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T19:47:59.236041Z

Reference resolution

18 of 18 outbound references displayed

verified exact15
verified fuzzy1
unresolved0
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d8c0d9a5-fdb8-4227-87f6-3b4b2968f789 · outbound

This paper cites Program Synthesis with Large Language Models.

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization Program Synthesis with Large Language Models

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-22T10:14:47.158201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5b95026b-8471-4947-b8f5-b835f8e09101 · outbound

This paper cites Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models.

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-22T10:14:47.182094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a401e54e-d7a7-4713-9ef1-456be7255b4e · outbound

This paper cites KTO: Model Alignment as Prospect Theoretic Optimization.

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization KTO: Model Alignment as Prospect Theoretic Optimization

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-22T10:14:47.177224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7c9c8541-8a7c-4f82-9558-ba88218254fb · outbound

This paper cites Uagent: Adversarial co-evolution for targeted bug revelation in unit testing.

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization Uagent: Adversarial co-evolution for targeted bug revelation in unit testing

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T10:16:23.176937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation def247ec-7aef-449d-9410-14c778a72f44 · outbound

This paper cites Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications.

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:14:47.154037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 175bb3bc-4a32-4f46-b2ab-2bacddea1a6a · outbound

This paper cites LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code.

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-22T10:14:47.153039Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 637594f1-ccc5-4abf-90c9-841ee7090333 · outbound

This paper cites Reveal: Self-evolving code agents via iterative generation-verification.arXiv preprint arXiv:2506.11442.

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization Reveal: Self-evolving code agents via iterative generation-verification.arXiv preprint arXiv:2506.11442

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:14:47.141381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 624e73a3-b081-408f-b52c-d21ba0247c44 · outbound

This paper cites Atgen: Adversarial reinforcement learning for test case generation.arXiv preprint arXiv:2510.14635.

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization Atgen: Adversarial reinforcement learning for test case generation.arXiv preprint arXiv:2510.14635

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:14:47.213134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f88c8584-349c-4c2c-a259-859e9282802e · outbound

This paper cites Learning to solve and verify: A self-play framework for code and test generation.arXiv preprint arXiv:2502.14948.

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization Learning to solve and verify: A self-play framework for code and test generation.arXiv preprint arXiv:2502.14948

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:14:47.219819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0e7451d3-e1a5-4599-967e-0560a7fcbf0c · outbound

This paper cites DSTC: Direct Preference Learning with Only Self-Generated Tests and Code to Improve Code LMs.

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization DSTC: Direct Preference Learning with Only Self-Generated Tests and Code to Improve Code LMs

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:14:47.226389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3bb2077a-7bce-4725-b8c9-254ac1523c9d · outbound

This paper cites Proximal Policy Optimization Algorithms.

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization Proximal Policy Optimization Algorithms

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-22T10:14:47.207783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 126d987c-ec2a-4e42-92fe-00ef0acb999b · outbound

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

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization A Survey on Self-Evolution of Large Language Models

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-22T10:14:47.202763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c4ebb61a-68d4-4d90-aa39-ae3e1b7cb8bb · outbound

This paper cites Co-evolving llm coder and unit tester via reinforcement learning.arXiv preprint arXiv:2506.03136.

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization Co-evolving llm coder and unit tester via reinforcement learning.arXiv preprint arXiv:2506.03136

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:14:47.171840Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3c8cbbd5-f55e-460c-b272-cbc610a0774b · outbound

This paper cites Finetuned Language Models Are Zero-Shot Learners.

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization Finetuned Language Models Are Zero-Shot Learners

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-22T10:14:47.191907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f414539e-896d-4e51-bb05-6e65dc61007e · outbound

This paper cites Self-rewarding correction for mathematical reasoning.

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization Self-rewarding correction for mathematical reasoning

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-22T10:14:47.165809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 05e5500d-eea9-494e-bb91-9226d6d60b19 · outbound

This paper cites Qwen2.5 Technical Report.

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization Qwen2.5 Technical Report

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-22T10:14:47.186797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 81660150-7c15-4f64-b472-5603a1ac71d0 · outbound

This paper cites Qwen3 Technical Report.

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization Qwen3 Technical Report

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-22T10:14:47.197360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 74447e26-258e-4d15-8b95-4a13b55a34a7 · outbound

This paper cites Unless otherwise specified, all hyperparameters are fixed across experiments.

ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization Unless otherwise specified, all hyperparameters are fixed across experiments

Reference 18

Resolution: malformed identifier; raw_fallback, observed 2026-05-22T10:16:23.180109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Pith citing papers

Observation c41f216f-ebd8-4ab2-aafd-18823a1f9358 · inbound

Self-Evolving Coding Agents cites this paper.

Self-Evolving Coding Agents ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization

Reference 92

Resolution: metadata mismatch; local_arxiv, observed 2026-08-05T19:47:59.243663Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.