Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-17T21:44:18.744201Z
Paper Citation Record · LEDGER
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
As of 7 August 2026, this Paper Citation Record lists 53 of 53 outbound references and 27 inbound Pith citation observations for arXiv:2511.11793.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-04T18:27:16.675981Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-07-05T15:11:10.874321Z
Reference resolution
53 of 53 outbound references displayed
- verified exact33
- verified fuzzy19
- unresolved0
- parse uncertain0
- malformed identifier0
- metadata mismatch1
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation 553ee84b-1b34-4a22-952c-792ae931a2d3 · outbound
This paper cites Introducing gpt-5.https://openai.com/index/introducing-gpt-5/.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Introducing gpt-5.https://openai.com/index/introducing-gpt-5/
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T21:45:18.451966Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 3aa6d195-9439-4f5f-a967-946ec3d2fde5 · outbound
This paper cites Kimi K2: Open Agentic Intelligence.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Kimi K2: Open Agentic Intelligence
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T21:45:17.789067Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 1612546f-98b4-401e-8459-88f18b5e88ae · outbound
This paper cites Minimax m2 & agent: Ingenious in simplicity.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Minimax m2 & agent: Ingenious in simplicity
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T21:45:18.447955Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 52d65ed6-e1f9-4041-a34f-b5febbfb4bbb · outbound
This paper cites GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models
Reference 4
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T21:45:17.796525Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e6fe7634-6b7e-4c1a-b72d-f9d547f8c1a8 · outbound
This paper cites DeepSeek-V3 Technical Report.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling DeepSeek-V3 Technical Report
Reference 5
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T21:45:17.792860Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 41c7016a-f22c-47be-a9a0-c0011be61859 · outbound
This paper cites Qwen3 Technical Report.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Qwen3 Technical Report
Reference 6
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T21:45:17.774102Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 9104b7ae-2be0-4016-bcd9-1ea21d9c7424 · outbound
This paper cites Introducing claude sonnet 4.5.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Introducing claude sonnet 4.5
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T21:45:18.458910Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation f1ac9d37-cfac-4cf7-b96a-dffd00720201 · outbound
This paper cites Introducing chatgpt agent: bridging research and action.https://openai.com/index/ introducing-chatgpt-agent/.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Introducing chatgpt agent: bridging research and action.https://openai.com/index/ introducing-chatgpt-agent/
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T21:45:18.462113Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e4a5c41f-ed35-4233-9eea-7476c7b1cdf2 · outbound
This paper cites Claude takes research to new places.https://claude.com/blog/research.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Claude takes research to new places.https://claude.com/blog/research
Reference 9
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T21:45:18.455564Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 796941e5-5969-4802-a8cb-4a0c51ff159d · outbound
This paper cites Longcat-flash technical report.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Longcat-flash technical report
Reference 10
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T21:45:17.784483Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 609b6926-a73f-4056-a915-358677818f03 · outbound
This paper cites Tongyi DeepResearch Technical Report.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Tongyi DeepResearch Technical Report
Reference 11
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T21:45:17.779821Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 1e9243f1-5b59-4c35-a2ae-80bb5c9c36a8 · outbound
This paper cites WebThinker: Empowering Large Reasoning Models with Deep Research Capability.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling WebThinker: Empowering Large Reasoning Models with Deep Research Capability
Reference 12
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T21:45:17.928218Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 2fb723df-50f2-444c-b905-0106968e877f · outbound
This paper cites WebSailor: Navigating Super-human Reasoning for Web Agent.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling WebSailor: Navigating Super-human Reasoning for Web Agent
Reference 13
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T21:45:17.817282Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 59975af9-9c76-41be-b0ce-7c09d07d8ad5 · outbound
This paper cites WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization
Reference 14
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T21:45:17.920068Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation edb9d248-4885-4172-8f73-4a7c93ccd786 · outbound
This paper cites Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training
Reference 15
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T21:45:17.809219Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e54dbf78-fc94-44f5-8dbc-82d62a9e7f40 · outbound
This paper cites Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL
Reference 16
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T21:45:17.898438Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 12d04ec9-e06c-4105-a375-617c97cb941a · outbound
This paper cites Beyond turn limits: Training deep search agents with dynamic context window.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Beyond turn limits: Training deep search agents with dynamic context window
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T21:45:17.850451Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation fce44f7a-14b2-42e2-aad8-36f767442317 · outbound
This paper cites WebDancer: Towards Autonomous Information Seeking Agency.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling WebDancer: Towards Autonomous Information Seeking Agency
Reference 18
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T21:45:17.924421Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation acbb61e5-d05e-4b91-854a-862df110c6b7 · outbound
This paper cites DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments
Reference 19
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T21:45:17.800472Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation c32495a0-899f-4246-9081-76e7c8781086 · outbound
This paper cites R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
Reference 20
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T21:45:17.884480Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 691f8b68-c759-4231-959b-5e9286a991ef · outbound
This paper cites Webexplorer: Exploreandevolvefortraininglong-horizonwebagents.arXivpreprint.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Webexplorer: Exploreandevolvefortraininglong-horizonwebagents.arXivpreprint
Reference 21
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T21:45:17.840636Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 6bdb5c6b-38b3-4658-953e-9c9ae9f08e7e · outbound
This paper cites Infoagent: Advancing autonomous information-seeking agents.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Infoagent: Advancing autonomous information-seeking agents
Reference 22
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T21:45:17.830851Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation a8ecf3bc-1ec8-463a-96e4-71e5e5221a87 · outbound
This paper cites Kimi-researcher: End-to-end rl training for emerging agentic capabilities.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Kimi-researcher: End-to-end rl training for emerging agentic capabilities
Reference 23
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T21:45:18.488254Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 46e89dcf-264e-43a1-8eeb-9d6f04a4b5b9 · outbound
This paper cites Introducing deep research.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Introducing deep research
Reference 24
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T21:45:18.473962Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 0ee09f8d-558b-4186-9312-29f992a97f85 · outbound
This paper cites BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents
Reference 25
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T21:45:17.813468Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation fec5f9e6-6d20-4da8-99c8-f99e9d4772eb · outbound
This paper cites BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinese
Reference 26
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T22:04:50.009871Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation d750ec29-25e5-4091-89f5-59367f5ebebf · outbound
This paper cites Humanity's Last Exam.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Humanity's Last Exam
Reference 27
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T21:45:17.911735Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 87f76407-4e3c-4b7d-857d-3f22cac950fa · outbound
This paper cites Gaia: a benchmark for general ai assistants.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Gaia: a benchmark for general ai assistants
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T21:45:18.493583Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation aaf52ea2-a057-44da-b233-fe5720387354 · outbound
This paper cites Grok 3 beta — the age of reasoning agents.https://x.ai/news/grok-3.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Grok 3 beta — the age of reasoning agents.https://x.ai/news/grok-3
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T21:45:18.499761Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation f1dce10c-0e2a-4558-8b93-d135929fc9bd · outbound
This paper cites React: Synergizing reasoning and acting in language models.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling React: Synergizing reasoning and acting in language models
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T21:45:18.477025Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 70b2691b-c100-4d3f-adba-c068794c707c · outbound
This paper cites Miroflow: A high-performance open-source research agent framework.https: //github.com/MiroMindAI/MiroFlow.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Miroflow: A high-performance open-source research agent framework.https: //github.com/MiroMindAI/MiroFlow
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T21:45:18.471373Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 95f3b03c-8188-4ca1-8408-d26e8c764bcc · outbound
This paper cites gpt-oss-120b & gpt-oss-20b Model Card.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling gpt-oss-120b & gpt-oss-20b Model Card
Reference 32
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T21:45:17.893410Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 124758d7-aa50-47ff-a609-03584cbe1a15 · outbound
This paper cites Musique: Multihop questions via single-hop question composition.Transactions of the Association for Computational Linguistics, 10:539–554.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Musique: Multihop questions via single-hop question composition.Transactions of the Association for Computational Linguistics, 10:539–554
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T21:45:18.496536Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e54ca631-b030-4160-9a8f-00f2b6ceddea · outbound
This paper cites Hotpotqa: A dataset for diverse, explainable multi-hop question answering.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Hotpotqa: A dataset for diverse, explainable multi-hop question answering
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T21:45:18.465766Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e31a7e2e-05c8-4923-842f-0e992185d5c1 · outbound
This paper cites WebWalker: Benchmarking LLMs in Web Traversal.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling WebWalker: Benchmarking LLMs in Web Traversal
Reference 35
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-17T21:45:17.854810Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 2e2f4f03-8f8b-4b6f-b0c3-84c36bd41509 · outbound
This paper cites MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning
Reference 36
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T21:45:17.874005Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 439ebd56-dfa5-4e22-9f97-fec2df288628 · outbound
This paper cites TaskCraft: Automated Generation of Agentic Tasks.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling TaskCraft: Automated Generation of Agentic Tasks
Reference 37
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T21:45:17.863344Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation cc8f0641-aff7-467f-a5cf-4ceaf3eb3e17 · outbound
This paper cites Qa-expert-multi-hop-qa-v1.0.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Qa-expert-multi-hop-qa-v1.0
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T21:45:18.482256Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 5e881f25-8eae-4ed6-a7e2-a9e9aa750e14 · outbound
This paper cites Onegen-traindataset-multihopqa.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Onegen-traindataset-multihopqa
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T21:45:18.479676Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 0e924b27-a3d9-4b1d-961a-a6bb325df8f7 · outbound
This paper cites Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps
Reference 40
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T07:39:58.458269Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation c643d6e0-6bce-4ea1-b6bd-ac6a351e307e · outbound
This paper cites Open-WikiTable: Dataset for Open Domain Question Answering with Complex Reasoning over Table.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Open-WikiTable: Dataset for Open Domain Question Answering with Complex Reasoning over Table
Reference 41
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T21:45:17.804974Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 7c0f95cc-72dd-4a28-ba51-236ce043dc1d · outbound
This paper cites Toucan: Synthesizing 1.5 m tool-agentic data from real- world mcp environments.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Toucan: Synthesizing 1.5 m tool-agentic data from real- world mcp environments
Reference 42
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T21:45:17.821833Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 037fdc72-2fb5-4fbc-b84a-ffb57f891837 · outbound
This paper cites Not All Correct Answers Are Equal: Why Your Distillation Source Matters.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Not All Correct Answers Are Equal: Why Your Distillation Source Matters
Reference 43
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T21:45:17.859616Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 1cd05432-0e8e-40b6-928a-cf6eadd7817a · outbound
This paper cites NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model
Reference 44
- Resolution
- verified exact
- arxiv_id, observed 2026-05-18T11:02:08.433616Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation b8f730e6-e6fc-4e26-be0f-99fd0430c810 · outbound
This paper cites Direct preference optimization: Your language model is secretly a reward model.Advances in Neural Information Processing Systems, 36:53728–53741.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Direct preference optimization: Your language model is secretly a reward model.Advances in Neural Information Processing Systems, 36:53728–53741
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T21:45:18.468707Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 9d69bd40-a87b-4286-b0a6-208d9fe8e6bf · outbound
This paper cites Provably mitigating overoptimization in rlhf: Your sft loss is implicitly an adversarial regularizer.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Provably mitigating overoptimization in rlhf: Your sft loss is implicitly an adversarial regularizer
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T21:45:18.485426Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 1722dcdd-246e-40d6-b312-884cdc246248 · outbound
This paper cites Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization
Reference 47
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T21:45:17.915724Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 4bb355e0-337e-4677-9e2c-6bc05e3c12fc · outbound
This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Reference 48
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T21:45:17.834894Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 0c7da94d-891c-47fe-bd64-904f5ac1a662 · outbound
This paper cites Introducing openai o3 and o4-mini.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Introducing openai o3 and o4-mini
Reference 49
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T21:45:18.490692Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation c64481b9-d429-4109-a892-fac6de8f8057 · outbound
This paper cites SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents
Reference 50
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T21:45:17.902577Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 4346518e-5d9e-4d0a-bd68-56eb4a2478e8 · outbound
This paper cites xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations
Reference 51
- Resolution
- verified exact
- arxiv_id, observed 2026-05-17T21:45:17.889821Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 55c2db7c-7900-4c50-b754-a91c6b8718b6 · outbound
This paper cites Fact, fetch, and reason: A unified evaluation of retrieval-augmented generation.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling Fact, fetch, and reason: A unified evaluation of retrieval-augmented generation
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-17T21:45:18.502500Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 39768ef1-a47b-4949-984c-da2ce9ac7840 · outbound
This paper cites SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models.
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models
Reference 53
- Resolution
- verified exact
- local_arxiv, observed 2026-05-17T21:45:17.845325Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Pith citing papers
Observation 5d71a7df-409b-4a1e-914b-e07ad43a8b3e · inbound
Toward Efficient Agents: Memory, Tool learning, and Planning cites this paper.
Toward Efficient Agents: Memory, Tool learning, and Planning MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 120
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T09:21:42.225908Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5a46c427-01a3-47a9-bdb9-25836e78438e · inbound
AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments cites this paper.
AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 15
- Resolution
- verified exact
- local_arxiv, observed 2026-05-10T23:30:49.422913Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation db387ea2-6ec8-4ba2-a619-789d58abd7c3 · inbound
PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory cites this paper.
PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 22
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T05:30:59.816110Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 1ab548fe-9384-42bb-8c32-9da0acce8b46 · inbound
Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges cites this paper.
Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 210
- Resolution
- verified exact
- local_arxiv, observed 2026-05-10T14:00:28.578014Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 790bcf5f-d1d5-4490-b8ef-39f186e9c71f · inbound
Mind DeepResearch Technical Report cites this paper.
Mind DeepResearch Technical Report MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 35
- Resolution
- verified exact
- local_arxiv, observed 2026-05-10T11:50:20.542098Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 38100c72-ed79-4be9-920c-210969625855 · inbound
LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent cites this paper.
LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 33
- Resolution
- verified exact
- local_arxiv, observed 2026-07-05T15:11:10.875942Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 2e71131b-67cd-4098-b621-c7628c362277 · inbound
DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data cites this paper.
DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 11
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T13:01:03.102377Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 85e57462-6a05-4d69-b733-abdade7ecb0a · inbound
SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning cites this paper.
SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 38
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T17:01:08.112396Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation e67ce3a3-c48b-4b94-92db-9a9709ebb7da · inbound
HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents cites this paper.
HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 34
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T01:45:52.331707Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 9a4a3095-ea40-41e8-8fc7-496dff322ab4 · inbound
HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents cites this paper.
HyperEyes: Dual-Grained Efficiency-Aware Reinforcement Learning for Parallel Multimodal Search Agents MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 34
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T03:21:19.047261Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 4eba06b8-cb36-41a2-9b1b-95952c36f966 · inbound
CellScientist: Dual-Space Hierarchical Orchestration for Closed-Loop Refinement of Virtual Cell Models cites this paper.
CellScientist: Dual-Space Hierarchical Orchestration for Closed-Loop Refinement of Virtual Cell Models MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 24
- Resolution
- verified exact
- local_arxiv, observed 2026-05-11T04:45:56.555500Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 8fd823c4-268d-4501-b8c4-8c7a7620e65b · inbound
PiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning cites this paper.
PiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 34
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T06:06:26.724561Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 4bf5d2b7-5197-450c-810b-49e40112cccc · inbound
PiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning cites this paper.
PiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 34
- Resolution
- verified exact
- local_arxiv, observed 2026-05-13T07:37:29.696072Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 775717b3-b5f3-41bf-a29a-1f627dfae528 · inbound
Efficient Agentic Reasoning Through Self-Regulated Simulative Planning cites this paper.
Efficient Agentic Reasoning Through Self-Regulated Simulative Planning MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 101
- Resolution
- verified exact
- local_arxiv, observed 2026-05-22T06:34:40.950557Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ebb1281f-bdd8-480f-8a58-ef7bc327d1ee · inbound
Hide to Guide: Learning via Semantic Masking cites this paper.
Hide to Guide: Learning via Semantic Masking MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 34
- Resolution
- verified exact
- local_arxiv, observed 2026-06-30T12:24:40.019270Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 33b6ab0a-0fa6-44c0-8078-9432b1919293 · inbound
Beyond Trajectory Rewards: Step-level Credit Assignment for Agentic Search via Graph Modeling cites this paper.
Beyond Trajectory Rewards: Step-level Credit Assignment for Agentic Search via Graph Modeling MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 26
- Resolution
- verified exact
- local_arxiv, observed 2026-06-29T08:03:14.233391Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ba98636a-f40f-460d-9f26-62e930f4d6d6 · inbound
TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation cites this paper.
TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 2
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T23:06:19.802596Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation ddbe4b47-6817-45c7-bee9-db926870d4ef · inbound
Benchmark Everything Everywhere All at Once cites this paper.
Benchmark Everything Everywhere All at Once MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 26
- Resolution
- verified exact
- local_arxiv, observed 2026-07-02T13:46:59.075462Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 10d8af0f-b706-4a88-b0fd-d61ecc44ca42 · inbound
DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning cites this paper.
DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 20
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-02T17:27:14.715479Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation cfa821bc-444f-4185-a80d-3618112bb6f4 · inbound
PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment cites this paper.
PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 28
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T00:17:28.913077Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation f6fd1f05-858b-4506-967e-3d4fcd0c2ded · inbound
PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment cites this paper.
PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 28
- Resolution
- unresolved
- no resolver link, observed 2026-07-12T14:37:28.660097Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9c82d9fd-5601-45d5-b880-dfaaa03cea0b · inbound
FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents cites this paper.
FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 31
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-03T10:27:56.411071Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 91e8512c-18ab-465c-b221-f4d425cf9f3b · inbound
ICBCBench: An Industry Consortium Benchmark for Financial Deep Research cites this paper.
ICBCBench: An Industry Consortium Benchmark for Financial Deep Research MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 37
- Resolution
- verified exact
- local_arxiv, observed 2026-07-03T23:19:04.117824Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 25311456-7b66-4219-9271-04a3c0c33246 · inbound
SimpleSearch-VL: A Simple Recipe for Multimodal Agentic Deep Search cites this paper.
SimpleSearch-VL: A Simple Recipe for Multimodal Agentic Deep Search MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 105
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-07-01T09:55:41.018125Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.
Observation 01959657-28d5-487d-9656-bb8cf7fe90ae · inbound
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration cites this paper.
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 132
- Resolution
- unresolved
- no resolver link, observed 2026-08-01T23:46:29.557575Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8de9a0fe-ec57-4711-8393-7a2230232f87 · inbound
Diagnosing Search Behavior and Failure Modes in Long-Horizon Search Agents cites this paper.
Diagnosing Search Behavior and Failure Modes in Long-Horizon Search Agents MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T18:27:16.675981Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cd5fa419-8447-448c-aab3-9cb3c2779912 · inbound
Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents cites this paper.
Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
Reference 214
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T15:12:56.086292Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.