Paper Citation Record · LEDGER

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search

As of 5 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 1 inbound Pith citation observation for arXiv:2603.01692.

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

pith.paper-citation-record.v1
2603.01692 v3

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-15T17:49:46.383559Z

measured 43 of 43 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-06-28T00:57:02.959467Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-02T13:46:59.819303Z

Reference resolution

42 of 42 outbound references displayed

verified exact19
verified fuzzy19
unresolved3
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2b42aabe-6b40-48f6-9be2-8c6f128f2152 · outbound

This paper cites Artificial Analysis: Independent Benchmarks and Performance Landscape of AI Models.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Artificial Analysis: Independent Benchmarks and Performance Landscape of AI Models

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:50:12.686241Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e32422cc-45d3-4768-ba82-69a10d3d56ac · outbound

This paper cites Comparative Analysis of Gradient-Based Optimization Techniques Using Multidimensional Surface 3D Visualizations and Initial Point Sensitivity.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Comparative Analysis of Gradient-Based Optimization Techniques Using Multidimensional Surface 3D Visualizations and Initial Point Sensitivity

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:50:12.242212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e006deef-3792-4eca-b631-fadc636f4e49 · outbound

This paper cites Optimization methods for large-scale machine learning.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Optimization methods for large-scale machine learning

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:50:12.681018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fc560ce5-11dd-48aa-a399-67b7b6147fd9 · outbound

This paper cites MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-15T17:50:12.253270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fd8ae382-a983-4aab-9846-7de665371c18 · outbound

This paper cites Traceisthenextautodiff: Generativeoptimization with rich feedback, execution traces, and llms.Advances in Neural Information Processing Systems, 37: 71596–71642.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Traceisthenextautodiff: Generativeoptimization with rich feedback, execution traces, and llms.Advances in Neural Information Processing Systems, 37: 71596–71642

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:50:12.670532Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fa3c3ac3-2da2-49d6-a902-f3d09918edc6 · outbound

This paper cites Introducing MAPO: Momentum-Aided Gradient Descent Prompt Optimization.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Introducing MAPO: Momentum-Aided Gradient Descent Prompt Optimization

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:50:12.248468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3bfa3821-07b9-4da1-ace5-825cfba6cb1e · outbound

This paper cites Internagent-mle: Navigating fine-grained optimization for coding agent.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Internagent-mle: Navigating fine-grained optimization for coding agent

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:50:12.665991Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a4a69550-6662-4b06-8d4c-31dda1adba60 · outbound

This paper cites Loss surfaces, mode connectivity, and fast ensembling of dnns.Advances in neural information processing systems, 31.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Loss surfaces, mode connectivity, and fast ensembling of dnns.Advances in neural information processing systems, 31

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:50:12.675713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ebd0af58-2f3a-4c18-a1bb-cd4549d9421a · outbound

This paper cites Aider LLM Leaderboards: Code Editing and Refactoring Benchmarks.https://aider.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Aider LLM Leaderboards: Code Editing and Refactoring Benchmarks.https://aider

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:50:12.661133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3cf5e1d7-b1ef-4ac2-bd90-fa5c3afde300 · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-15T17:50:12.213590Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0dafeb71-0a0e-4c7e-ae4b-d818f3348287 · outbound

This paper cites Evoprompt: Connecting llms with evolutionary algorithms yields powerful prompt optimizers.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Evoprompt: Connecting llms with evolutionary algorithms yields powerful prompt optimizers

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:50:12.644086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d2b289d4-6ea3-4b36-b315-08cd9ed0c454 · outbound

This paper cites MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:50:12.229176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dd702606-79f4-47f2-975c-db6e499ae27b · outbound

This paper cites Academic Press.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Academic Press

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:50:12.639121Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d2836d84-479d-48df-ba82-db90c9680158 · outbound

This paper cites OpenAI o1 System Card.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search OpenAI o1 System Card

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-15T17:50:12.236045Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a38e1dbc-a2c5-4607-8a7f-342d9112c06a · outbound

This paper cites AIDE: AI-Driven Exploration in the Space of Code.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search AIDE: AI-Driven Exploration in the Space of Code

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-17T18:22:30.071006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 997664c4-9e2c-419c-a512-24f3e388a755 · outbound

This paper cites SWE-bench: Can Language Models Resolve Real-World GitHub Issues?.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-05-15T17:50:12.218265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 21457aac-a06d-4a9b-bbda-fdb7d98ef398 · outbound

This paper cites KompeteAI: Accelerated Autonomous Multi-Agent System for End-to-End Pipeline Generation for Machine Learning Problems.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search KompeteAI: Accelerated Autonomous Multi-Agent System for End-to-End Pipeline Generation for Machine Learning Problems

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-05-15T17:50:12.285295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation eee33bf5-61d4-46ff-b717-29752422a941 · outbound

This paper cites The FM Agent, February 2026.https://arxiv.org/abs/2510.26144.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search The FM Agent, February 2026.https://arxiv.org/abs/2510.26144

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:50:12.256694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2a4574c1-f0aa-422b-96a7-fb020fc66d1a · outbound

This paper cites ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search ML-Master: Towards AI-for-AI via Integration of Exploration and Reasoning

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:50:12.279869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3a339b5e-2e46-46a9-9bc0-08c295a70a2f · outbound

This paper cites Self-refine: Iterative refinement with self- feedback.Advances in Neural Information Processing Systems, 36:46534–46594.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Self-refine: Iterative refinement with self- feedback.Advances in Neural Information Processing Systems, 36:46534–46594

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:50:12.598644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 78d84997-31e1-4a34-b89a-8847383e15e7 · outbound

This paper cites Guided evo- lutionary strategies: Augmenting random search with surrogate gradients.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Guided evo- lutionary strategies: Augmenting random search with surrogate gradients

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:50:12.648720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4cfcd81b-d4f2-4adf-ba7e-02617503ee1f · outbound

This paper cites MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:50:12.299130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d7a505a1-1aab-4526-9ffd-8f761124b57d · outbound

This paper cites Springer.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Springer

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:50:12.626327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bd0cd20f-91f8-4db2-8a78-7c815bbd6cc8 · outbound

This paper cites Dsgym: A holistic framework for evaluating and training data science agents.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Dsgym: A holistic framework for evaluating and training data science agents

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:50:12.246096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bfb10034-9596-459e-913c-db9e4c33a663 · outbound

This paper cites Introducing openai o3 and o4-mini.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Introducing openai o3 and o4-mini

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:50:12.630480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e988b4d7-58fc-499f-8bea-7ad2a6f5b85c · outbound

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

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Automatic Prompt Optimization with "Gradient Descent" and Beam Search

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:50:12.234658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3d1bee81-8690-4a6b-8b37-eac93e8e4c29 · outbound

This paper cites Reflexion: Language agents with verbal reinforcement learning.Advances in Neural Information Processing Systems, 36:8634–8652.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Reflexion: Language agents with verbal reinforcement learning.Advances in Neural Information Processing Systems, 36:8634–8652

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:50:12.602593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3885500f-d69c-4163-bdd9-da5a7d47b325 · outbound

This paper cites OpenAI GPT-5 System Card.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search OpenAI GPT-5 System Card

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-05-15T17:50:12.268050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1ad37891-d224-4ced-868e-e59b5b8bfe1b · outbound

This paper cites A survey of reasoning with foundation models: Concepts, methodologies, and outlook.ACM Computing Surveys, 57(11):1–43.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search A survey of reasoning with foundation models: Concepts, methodologies, and outlook.ACM Computing Surveys, 57(11):1–43

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:50:12.617201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0ce0e877-bbe7-4695-bc08-94c8cc66fb34 · outbound

This paper cites arXiv preprint arXiv:2507.02554 , year=.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search arXiv preprint arXiv:2507.02554 , year=

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-15T17:50:12.305111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 27273833-eab6-4c93-b937-b56f111959e6 · outbound

This paper cites OpenHands: An Open Platform for AI Software Developers as Generalist Agents.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search OpenHands: An Open Platform for AI Software Developers as Generalist Agents

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-05-15T17:50:12.239953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b577fd38-ccbe-40ab-8160-7ed3fe4d4c88 · outbound

This paper cites Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-15T21:20:59.729674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6305306d-5c67-474a-b389-3d917ed32398 · outbound

This paper cites Large language models as optimizers.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Large language models as optimizers

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:50:12.656577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c9a48c6b-51d6-4475-a6aa-04eb22a23448 · outbound

This paper cites TextGrad: Automatic "Differentiation" via Text.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search TextGrad: Automatic "Differentiation" via Text

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-05-15T17:50:12.251461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9eb5eb1c-92a0-4956-8562-9090a3dd596c · outbound

This paper cites Initialization with Forced Diversifi- cation.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Initialization with Forced Diversifi- cation

Reference 35

Resolution: malformed identifier; arxiv_id, observed 2026-05-15T17:50:12.262503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 00b82697-ca5f-4106-a06f-98a2903bf469 · outbound

This paper cites an unresolved cited work.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-05-15T17:50:12.593776Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 78cb3d50-3ee9-44a4-8025-04ba9d0844e4 · outbound

This paper cites an unresolved cited work.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-05-15T17:50:12.652657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ebb73b01-7424-42d2-b607-b2586791174a · outbound

This paper cites an unresolved cited work.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-05-15T17:50:12.614595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 84f370f1-67bd-4fe2-b429-de30f1e0cc62 · outbound

This paper cites These are moderately detectable, as the validator can flag suspiciously specific features by analyzing their construction logic.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search These are moderately detectable, as the validator can flag suspiciously specific features by analyzing their construction logic

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:50:12.621943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 983fcd4d-bdae-4d92-8f78-a62c3acdb8b1 · outbound

This paper cites shortcut solvability.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search shortcut solvability

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:50:12.634976Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7ae772a5-29b8-4d28-a22a-2116ccfa326f · outbound

This paper cites neural networks vs.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search neural networks vs

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:50:12.606600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 631f2466-06a0-4298-b6d2-133aa5d9c4e7 · outbound

This paper cites When one trace discovers a better region, others can adopt or adapt that hypothesis, enabling non-local transitions while preserving local refinement within each region.

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search When one trace discovers a better region, others can adopt or adapt that hypothesis, enabling non-local transitions while preserving local refinement within each region

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T17:50:12.610715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Pith citing papers

Observation 1a6316ec-f914-4ef8-9e5c-48801ceb1afa · inbound

MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery cites this paper.

MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-07-02T13:46:59.820786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.