Pith. sign in

Paper Citation Record · LEDGER

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering

As of 13 August 2026, this Paper Citation Record lists 69 of 69 outbound references and 0 inbound Pith citation observations for arXiv:2607.25090.

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

pith.paper-citation-record.v1
2607.25090 v1

Coverage vector

measured 69 of 69 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-07-31T01:39:50.577219Z

measured 69 of 69 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+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

69 of 69 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved68
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 5cf4e0ba-6e9b-4d5e-8f3a-83ab823e02be · outbound

This paper cites How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models

Reference 1

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:45.876972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:45.876972Z digest=sha256:08d0f25b6b47a2e5d7df279b688b6f4900acb307097abe12cfb4ee45027fe0d9

Observation 5bff7c3d-1027-4a68-b60a-8b9e3a4e30ac · outbound

This paper cites Auffarth.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Auffarth

Reference 2

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:45.915563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:45.915563Z digest=sha256:c23aa259027c88d3991a8849d6e445ea20c58f382ad1e74735d6574c4523bbbf

Observation 65950c18-b38c-4e28-bc55-32d2c1c5becb · outbound

This paper cites Exploring LLM Agents for Cleaning Tabular Machine Learning Datasets.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Exploring LLM Agents for Cleaning Tabular Machine Learning Datasets

Reference 3

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:45.979523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:45.979523Z digest=sha256:be67d19aafe76751ae603d958440576ad269e02692676378ad59eb84f8baa496

Observation 4dc59044-cd52-4c04-9385-184704d63124 · outbound

This paper cites Bettini, A.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Bettini, A

Reference 4

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:46.043128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:46.043128Z digest=sha256:73b2e611ff9826576e53edb850cbaefdef2349afb70540e6454300cab29c67ff

Observation e7789e9b-689a-4f7d-a474-fd50a1cbab1d · outbound

This paper cites Why Do Multi-Agent LLM Systems Fail?.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Why Do Multi-Agent LLM Systems Fail?

Reference 5

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:46.144408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:46.144408Z digest=sha256:33a20b1283e445cb9ffc8ae00346a3e8b9ecb67ee7db0713dfe3f398157a01ed

Observation 562d99ad-f91b-4d84-bdfc-93e6135990aa · outbound

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

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering

Reference 6

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:46.211613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:46.211613Z digest=sha256:2d69070c86096dbd50f9cccbdc49b9d62f3642d705da54f5f062ae3407b715eb

Observation 8b256110-f9e9-46f8-a3f9-9ba7386e83d7 · outbound

This paper cites AgentFlow: Resilient Adaptive Cloud-Edge Framework for Multi-Agent Coordination.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering AgentFlow: Resilient Adaptive Cloud-Edge Framework for Multi-Agent Coordination

Reference 7

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:46.248248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:46.248248Z digest=sha256:f2e428c9c8f5fa89672faed5d16ab4f65739847b1ce828cde812a1e18b29ad26

Observation bdc1d8c5-c6e9-4e05-b4b8-2ab608847e2e · outbound

This paper cites an unresolved cited work.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Unresolved cited work

Reference 8

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:46.313397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:46.313397Z digest=sha256:ed2728574c45df59edccb887041c9f8ae36684f24cc57510462aa0bbffa0e937

Observation 5365d0a5-e56c-48fc-b398-e015cdf8afd5 · outbound

This paper cites an unresolved cited work.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Unresolved cited work

Reference 9

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:46.377414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:46.377414Z digest=sha256:ac3b4ab7e6a7c48979801d205037944cdaf0fdd69a2b700c10e8abcfe614dbf7

Observation ae532849-6683-43e6-814e-893cb6476163 · outbound

This paper cites an unresolved cited work.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Unresolved cited work

Reference 10

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:46.443101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:46.443101Z digest=sha256:e8126d184c66e6fc30a4c74da15825729bdee881239aa7e8fed2e49265039638

Observation 40e11efe-9657-4742-977e-18346fee941c · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 11

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:46.509041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:46.509041Z digest=sha256:238423053b3c3b81b61cdae9a3067bae8654752fba76c624189298408a6a60ca

Observation 36987d3b-a370-49ec-9d7b-7409002be9de · outbound

This paper cites DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents

Reference 12

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:46.580060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:46.580060Z digest=sha256:82df85e2c119be7eaf67055bf9e0487112b9a702773caf52dbd3bb160c0ee914

Observation b7565a7f-ca71-4e08-9f3a-15eb3c84880e · outbound

This paper cites an unresolved cited work.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Unresolved cited work

Reference 13

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:46.678736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:46.678736Z digest=sha256:da9697c0f2b742200524e20876e396aa7b5aba3c5ed926cf315228b5a091b7e7

Observation cb3c5cb9-db31-46b1-a88f-ccc61f6b6e32 · outbound

This paper cites Errica, D.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Errica, D

Reference 14

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:46.744304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:46.744304Z digest=sha256:9d1951eeed1fb69b552d50af4cbdb70478aa51a5d8e22f5d77e968ea74d5f611

Observation 9043af6a-881e-4ff4-b319-2427ec7f6644 · outbound

This paper cites MLZero: A Multi-Agent System for End-to-end Machine Learning Automation.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering MLZero: A Multi-Agent System for End-to-end Machine Learning Automation

Reference 15

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:46.815411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:46.815411Z digest=sha256:27d67d29b483d7c4c22d793182ebbd86402c487ed75bb6efdd73cc268ab5a346

Observation 4c62d237-66f4-47e8-930c-37a9ae07b454 · outbound

This paper cites Grosnit, A.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Grosnit, A

Reference 16

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:46.881774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:46.881774Z digest=sha256:111ec79a70627abe2b59b268a3cecccfd65991a875b16cb448f2a5a1b4ec2edd

Observation f4cacc42-7757-44ac-abd0-a72cac0d4895 · outbound

This paper cites DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning

Reference 17

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:46.981119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:46.981119Z digest=sha256:fe6a7746457ac98be7952cdd6eed5d458941a87650a43419bdf6540b4f3d3159

Observation 54a1a404-3e3c-44d7-80bc-c2351528290a · outbound

This paper cites an unresolved cited work.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Unresolved cited work

Reference 18

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:47.043792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:47.043792Z digest=sha256:8fb63fff76b38ef058b0048e6807eef8be5e6a392a22963c2a790db6cfe5e043

Observation 2273c5e5-9c33-4e6b-8e1b-f6694a665b93 · outbound

This paper cites R-Zero: Self-Evolving Reasoning LLM from Zero Data.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering R-Zero: Self-Evolving Reasoning LLM from Zero Data

Reference 19

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:47.105486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:47.105486Z digest=sha256:1835d88a660ca4ca76393b0c6594051bedf95d9aeeac7e12f95d5bd17be2c0e5

Observation 668008f8-d1d1-4c27-9fb9-3c117585f4d5 · outbound

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

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation

Reference 20

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:47.207858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:47.207858Z digest=sha256:bac0ab41da8b52a14c1757ff8e8c77e2dce17952f88b22ff111563821a40184f

Observation b3e7f591-feb9-4b26-97e4-f1410e1e70fe · outbound

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

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code

Reference 21

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:47.273431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:47.273431Z digest=sha256:7f3b1ab3630bfd9fdca0f44189ab58188367333236d50e7fb0541b6846a69306

Observation 4eb5c0a1-c99f-4471-86e1-eacaa42ddc0c · outbound

This paper cites Jiang, J.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Jiang, J

Reference 22

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:47.339068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:47.339068Z digest=sha256:8e8572b8062f97dc06e36aa6918d60376d0bfc98d26945534d17087f7473d1eb

Observation 484669f9-3b08-40ed-aa54-97d11e3b37e2 · outbound

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

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering AIDE: AI-Driven Exploration in the Space of Code

Reference 23

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:47.402763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:47.402763Z digest=sha256:4077adc50d120230977730be532abd7aebb45471ea83e6477733b4c06bda3d0f

Observation 9b335ce2-d058-44f6-8d06-74991609702d · outbound

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

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

Reference 24

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:47.501092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:47.501092Z digest=sha256:127fb180b5d68ebab79ce19d0c84639aee3a0d86b7722db0e38e9c282e447121

Observation 66ebe250-73dd-4313-be8b-7aa0051acd37 · outbound

This paper cites DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?

Reference 25

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:47.560956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:47.560956Z digest=sha256:d5cac3014dedbd8f91a1a7e5fb1b1530a4a316b30953d0f4983ec4a29f0f1c41

Observation a8dd8cca-2a5f-48ec-8141-ac6ce716bbee · outbound

This paper cites an unresolved cited work.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Unresolved cited work

Reference 26

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:47.628725Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:47.628725Z digest=sha256:5501d643b9821918d29670faa08cbcb2a55dcd4c936dcaec9dd381044d5f0859

Observation e1654d27-9de8-471c-b6db-1ba5e75bf16b · outbound

This paper cites AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions

Reference 27

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:47.689559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:47.689559Z digest=sha256:0babf2f5134926e7efdd3447a9b290a2da7b1c89d4430e6067b69bb72b23db48

Observation cde98678-75b3-4d5c-b19d-db760d391139 · outbound

This paper cites Liang, Z.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Liang, Z

Reference 28

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:47.757378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:47.757378Z digest=sha256:48460714f79b6b0ad95f742fc0bfaa4fe64256d1a7bdd445bcf93beb1a33919c

Observation e92abd29-e79a-4e75-9b7a-43e31b2aba2a · outbound

This paper cites Large Language Model Agent for Hyper-Parameter Optimization.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Large Language Model Agent for Hyper-Parameter Optimization

Reference 29

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:47.851233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:47.851233Z digest=sha256:14f73ffada601e67d7c5b083a512b6ea9d3dcc81362d66bb03230ffc6aae1f51

Observation 99dcefc0-46f4-4ecc-9f88-47f3350f81cf · outbound

This paper cites Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces

Reference 30

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:47.910499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:47.910499Z digest=sha256:4fdbf05faf375c73f5c8db9882594c5d1cfb0878a39abc4cdee30b2246575629

Observation 7c2316a1-2487-4c09-b8b2-20bf3c450413 · outbound

This paper cites an unresolved cited work.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Unresolved cited work

Reference 31

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:47.972116Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:47.972116Z digest=sha256:534851eae07b4eccb6351367e59f31b5a1dd0328a8a6f7633ae8bdea8b772c8a

Observation 82085697-697f-492e-8976-fbe492b63405 · outbound

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

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement

Reference 32

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.069072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.069072Z digest=sha256:25fa420fd647dd2b81a34175eca43ec82fe7fd7b2db724c9a87f0def380b0787

Observation fbe3ca25-9898-4567-9bbc-77d51be55df5 · outbound

This paper cites Introducing openai gpt-5.OpenAI Blog, 2025.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Introducing openai gpt-5.OpenAI Blog, 2025

Reference 33

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.174480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.174480Z digest=sha256:a62053058aa4d8415c2211ab3c564c2d668a171701d0bd2b3ed7ee58fbda56b4

Observation ab31ddc7-33f3-4aaf-9638-3fc9cef2795e · outbound

This paper cites Introducing openai o3 and o4-mini.OpenAI Blog, 2025.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Introducing openai o3 and o4-mini.OpenAI Blog, 2025

Reference 34

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.210572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.210572Z digest=sha256:8f0b146c442f41cb70ff44a88de862752035e7be4a6b503e3bb9ff2763a545c4

Observation 07880117-07f1-489b-89d1-243abd7a8a73 · outbound

This paper cites an unresolved cited work.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Unresolved cited work

Reference 35

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.248851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.248851Z digest=sha256:7a1ad7218e761f4adde5c625f1e8189c481018d6a12bb5abeadece6dffdfcf5e

Observation 4d7dd1f4-ba19-4d6b-9f87-89d3edfdfb0d · outbound

This paper cites KernelBench: Can LLMs Write Efficient GPU Kernels?.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering KernelBench: Can LLMs Write Efficient GPU Kernels?

Reference 36

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.284510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.284510Z digest=sha256:da87ddd79715aff3846db116bc08aefc4528e99abb07f2ddbce688578f822595

Observation b7806e89-9db5-42cc-82d3-e938319bdd42 · outbound

This paper cites GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering GDPval: Evaluating AI Model Performance on Real-World Economically Valuable Tasks

Reference 37

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.332944Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.332944Z digest=sha256:5960014e1300d8fc86939e29e2a27f244f9b3b049a88bb3098d75712e22f6bb2

Observation f8184199-b1b0-4c94-b964-340a7718b476 · outbound

This paper cites Humanity's Last Exam.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Humanity's Last Exam

Reference 38

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.374945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.374945Z digest=sha256:034647ec206fe6486be7037b82aac2657115a679a11c09e26fea5fe9ac0f6d7b

Observation 3997331b-ae27-4dda-a97c-d4d2e363e6a3 · outbound

This paper cites Press, B.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Press, B

Reference 39

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.421606Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.421606Z digest=sha256:7afe535c92ae61aeeb76253b3895ac16380f6bb244c95768c3ae15a7bc34c8c2

Observation c21e4322-f1ba-4ff2-80b4-e53d494c83c9 · outbound

This paper cites MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering

Reference 40

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.459777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.459777Z digest=sha256:4fa398d75ed859985d99466f9308cc55cba537eb10bac7af6deb0f91e45ba192

Observation 53efcee7-34cd-412c-9c73-46adc0ba7a13 · outbound

This paper cites Qiang, Y.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Qiang, Y

Reference 41

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.534455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.534455Z digest=sha256:ae7ddc7cb4fb9caf1d3cc73ce45462793dc5472a09935c04be51d46ff435b604

Observation f20aef37-c4a5-4912-8407-8c09289de51d · outbound

This paper cites an unresolved cited work.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Unresolved cited work

Reference 42

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.567763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.567763Z digest=sha256:c66fe8a503b5e95c7c78aae6bc2d63278804b7da234bcb06cf47df5c506c3244

Observation 45c52c6b-2565-4bce-b5e0-0280ae1f636b · outbound

This paper cites Shang, Y.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Shang, Y

Reference 43

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.622754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.622754Z digest=sha256:6784ef6bd7560a16406b302877769198b117e5719af39d5c3aedf9d015580323

Observation 8b21ee08-d16c-4454-b242-05b533ac0dc2 · outbound

This paper cites PaperBench: Evaluating AI's Ability to Replicate AI Research.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering PaperBench: Evaluating AI's Ability to Replicate AI Research

Reference 44

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.664815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.664815Z digest=sha256:e635c040cad08a7a85b27c4d834b19193aae9fbe2be837f4860e4a26cfde2e58

Observation 5365ea3c-7a03-4ed2-b06b-3bd52ca636e1 · outbound

This paper cites Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents

Reference 45

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.698379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.698379Z digest=sha256:c30e5c01dddad780be0002a87086c155e3d678194c978b4674833ace5f02c50d

Observation 3e1dffac-109e-4453-9e1c-48b967604fc4 · outbound

This paper cites ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code

Reference 46

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.754483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.754483Z digest=sha256:a32fea20808728e4b8029d7d7a1034dbda09674e0d02de7063fd9d0627784976

Observation d19b1dfa-0de0-4fd0-9322-2bb55aeda36a · outbound

This paper cites an unresolved cited work.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Unresolved cited work

Reference 47

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.794155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.794155Z digest=sha256:065783116553e6765a49c4a1157f3855f1c89ccb609a8122dd8fbd209790c041

Observation b2f48f2f-c040-4a8a-a1f3-d6eb9d05a93c · outbound

This paper cites Toledo, K.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Toledo, K

Reference 48

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.835039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.835039Z digest=sha256:851edb50462343cffd89bfc5dab60dc5710895c015353f46062d20eec7ff932e

Observation f7baaac6-fa2e-41b9-8885-05e91a823a40 · outbound

This paper cites an unresolved cited work.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Unresolved cited work

Reference 49

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.870027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.870027Z digest=sha256:3c82088dda48d4de3fcdc3da976c8a0797960ff63354cdede920f78a1617d0d0

Observation 300ae76d-1246-4940-853e-c1785ad16084 · outbound

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

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering OpenHands: An Open Platform for AI Software Developers as Generalist Agents

Reference 50

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.910410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.910410Z digest=sha256:69b2a2f18545a01d813e1b4c96f7ff9c3b773e9b6f5f774843cf1588e9b3206f

Observation 102f6301-0043-4f3e-92c6-3d998a33755e · outbound

This paper cites Simulating Human-like Daily Activities with Desire-driven Autonomy.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Simulating Human-like Daily Activities with Desire-driven Autonomy

Reference 51

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.950879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.950879Z digest=sha256:65e8723c3fda2af63cd4bac6800c96acfc2ec874cbd536ed249222c9c64b2cd7

Observation 997ecc20-294c-4f87-9656-80f77c5de968 · outbound

This paper cites BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents

Reference 52

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:48.991522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:48.991522Z digest=sha256:6589bd128243e9d4a0097ad97a5c417fcfd98c5473affe07ce27a59a463ada32

Observation 736be7ab-e2d9-4522-be1b-eeb4e4383de0 · outbound

This paper cites an unresolved cited work.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Unresolved cited work

Reference 53

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:49.022541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:49.022541Z digest=sha256:5350c670e0b726c7092fc365db6656270741df11e0af5ce61e18b50b8ee59e72

Observation 3898c4ef-8cea-4e28-a263-f226e51eea35 · outbound

This paper cites an unresolved cited work.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Unresolved cited work

Reference 54

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:49.057613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:49.057613Z digest=sha256:4b47b9ed6b6e042d2847fc3d8db80180c593c53a0778d42687946b962def8e9f

Observation 107469e8-4acc-4131-8a58-d84fbfadbef1 · outbound

This paper cites an unresolved cited work.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Unresolved cited work

Reference 55

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:49.108572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:49.108572Z digest=sha256:b672e1881171a01247ebd85b4f3d4febfa7767b1a8596523ce7924edf2ae94b4

Observation b223f18e-0fb4-47d0-86b2-c12b00bf2c00 · outbound

This paper cites Reinforcement Learning for Machine Learning Engineering Agents.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Reinforcement Learning for Machine Learning Engineering Agents

Reference 56

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:49.218941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:49.218941Z digest=sha256:b7627aa140f55bba719c2f4f3bdbf0321e1bb1a097ac237326127c6cd91f5ca3

Observation d28e0a71-5e69-4c7b-a82c-79dd1f7355ab · outbound

This paper cites an unresolved cited work.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Unresolved cited work

Reference 57

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:49.298864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:49.298864Z digest=sha256:8e054e645ac0601cb311c27b18e8e7673969dff00994aca05635973ba7fda181

Observation bec55fd4-bb5d-4b1c-99b1-4982055f1a0a · outbound

This paper cites $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

Reference 58

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:49.431931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:49.431931Z digest=sha256:471947625b7588e13f6b6e66a13bf1ff1f7647caa7c5866ec858d31ec19b18d9

Observation 1e1d7ddc-847e-4a5b-bee7-5f80e8eff804 · outbound

This paper cites AutoML-GPT: Automatic Machine Learning with GPT.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering AutoML-GPT: Automatic Machine Learning with GPT

Reference 59

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:49.518675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:49.518675Z digest=sha256:813c591010bef24d4000006839a5f2d8c5172bd8716724d8c8088dc205f3bb70

Observation 1408ddfd-ee28-4dfa-8fc5-0cbb9df3d75e · outbound

This paper cites Zhang, L.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Zhang, L

Reference 60

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:49.588680Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:49.588680Z digest=sha256:5c653eac76cb74f5835d619fb85d1a56c97aa93dfcd14eb1326fee9473884bfc

Observation 07f3ec80-4d83-47df-8d06-6753530c2fd9 · outbound

This paper cites Zhang, R.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Zhang, R

Reference 61

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:49.768350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:49.768350Z digest=sha256:1dd93167837989cfe8954f723dc29df9f974d98c806579af11d5a3e4126c8061

Observation e918f3a6-097d-49d3-bf18-9ec17da754b6 · outbound

This paper cites Zhang, X.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Zhang, X

Reference 62

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:49.865472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:49.865472Z digest=sha256:021c95f8253af5f4173731e2f0b47f1a76951d66bced3bc4ccf0b960b345da23

Observation f9d301ed-02d8-4fcd-80ff-f651f6a5f3bb · outbound

This paper cites WebArena: A Realistic Web Environment for Building Autonomous Agents.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering WebArena: A Realistic Web Environment for Building Autonomous Agents

Reference 63

Resolution
malformed identifier
no resolver link, observed 2026-07-31T01:39:49.959361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:49.959361Z digest=sha256:f8cf2a565061f8cc834443827c716c370dc5a0cfaaee27db2275a2f8e5e78e1c

Observation 7663ac0e-e471-440f-abca-0ddba39ae6bf · outbound

This paper cites Combine training and testing data for consistent prepro- cessing.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Combine training and testing data for consistent prepro- cessing

Reference 64

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:50.113763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:50.113763Z digest=sha256:fb74094e54bdd696a38853296d8765d2aec44f5578df180fc3aa6b622bb724b9

Observation 37ec8327-0454-410a-bd68-e16da764f24c · outbound

This paper cites ,margin_64).

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering ,margin_64)

Reference 65

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:50.169715Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:50.169715Z digest=sha256:8132e5b3d44b3237f28574cabc2ab18cafdf067033ae157125c88f445fb85001

Observation f2f3768a-2e34-4b6c-9971-09cf53e710ff · outbound

This paper cites an unresolved cited work.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Unresolved cited work

Reference 66

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:50.229834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:50.229834Z digest=sha256:e8e2fd012708ac82e3b59a09e5acb665019ccc381f90e667d63728c59cc3d071

Observation 3b703d2c-7219-4296-887c-6928073e94e3 · outbound

This paper cites Set is_unbalance=True, n_estimators=1000, learning_rate=0.05, min_child_samples=20, subsample=0.7, colsample_bytree=0.7, reg_alpha=0.1, reg_lambda=0.1,random_state=42, andn_jobs=-1.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Set is_unbalance=True, n_estimators=1000, learning_rate=0.05, min_child_samples=20, subsample=0.7, colsample_bytree=0.7, reg_alpha=0.1, reg_lambda=0.1,random_state=42, andn_jobs=-1

Reference 67

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:50.323177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:50.323177Z digest=sha256:c7368b08b4900adb1212ec31604eabc54fc49f0490302f86bd47fac542da41ea

Observation 4d9170fa-27a3-4721-9d9f-1417dec764ad · outbound

This paper cites an unresolved cited work.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Unresolved cited work

Reference 68

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:50.508436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:50.508436Z digest=sha256:422bf74a4b21b027564333c2c4c1e5994fefff7b9e1ae2be70e8e6419dd9561c

Observation 4221d847-8702-4007-b298-167ff3cb7d4e · outbound

This paper cites Save submission.csvto theoutput_pathusing absolute paths.

Matryoshka Agent: Unfolding Sub-Agents for Long-Horizon Machine Learning Engineering Save submission.csvto theoutput_pathusing absolute paths

Reference 69

Resolution
unresolved
no resolver link, observed 2026-07-31T01:39:50.577219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T01:39:50.577219Z digest=sha256:d4f37bfc4f1c128b3948f6423fe043cf0376c390f039afdcd34651a9ff89f262

Pith citing papers

No inbound Pith citation observations are available.