Paper Citation Record · LEDGER

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG

As of 5 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 1 inbound Pith citation observation for arXiv:2605.11611.

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

pith.paper-citation-record.v1
2605.11611 v2

Coverage vector

measured 24 of 24 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-15T06:08:43.974278Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T15:12:55.650270Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

24 of 24 outbound references displayed

verified exact18
verified fuzzy5
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 26bc6b66-167f-453e-b929-c741b31e6719 · outbound

This paper cites Learning to reason with search for llms via reinforcement learning.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG Learning to reason with search for llms via reinforcement learning

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-15T06:09:49.739729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5ecd1a49-90b0-4eb9-a0c6-6a7fcf412ec1 · outbound

This paper cites Actor-curator: Co-adaptive curriculum learning via policy-improvement bandits for rl post-training.arXiv preprint arXiv:2602.20532.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG Actor-curator: Co-adaptive curriculum learning via policy-improvement bandits for rl post-training.arXiv preprint arXiv:2602.20532

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-15T06:09:49.776333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e7106ea8-494d-49bb-8fdf-1a12f429d16c · outbound

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

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-05-15T06:09:49.763704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bfd0bed1-4d81-4f27-89d5-002fd9eb3c9a · outbound

This paper cites Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-15T06:09:49.757886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9d532962-b741-4d2c-b1c2-0671b6d37d5c · outbound

This paper cites V., Jeon, M., Vu, K., Lai, V., and Yang, E.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG V., Jeon, M., Vu, K., Lai, V., and Yang, E

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T06:09:49.770086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 238ab7c0-aaf2-44dc-bf48-28140a50f69c · outbound

This paper cites Explore data left behind in reinforcement learning for reasoning language models.arXiv preprint arXiv:2511.04800.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG Explore data left behind in reinforcement learning for reasoning language models.arXiv preprint arXiv:2511.04800

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-15T06:09:49.745970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 96ffb480-635d-4ada-abf7-021147b38620 · outbound

This paper cites The Llama 3 Herd of Models.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG The Llama 3 Herd of Models

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-15T06:09:49.752234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ff431206-325c-4828-80d1-450402210dbe · outbound

This paper cites WebGPT: Browser-assisted question-answering with human feedback.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG WebGPT: Browser-assisted question-answering with human feedback

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-15T06:09:49.782515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 87489695-aef1-4a61-9417-2f57c18eb392 · outbound

This paper cites Measuring and narrowing the compositionality gap in language models.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG Measuring and narrowing the compositionality gap in language models

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:10:07.278695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 88372b56-b367-4627-ae4e-d827292e43ec · outbound

This paper cites Qwen2.5 Technical Report.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG Qwen2.5 Technical Report

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-15T06:09:49.788478Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b906492c-335e-40c7-92df-d13617ebf43b · outbound

This paper cites Proximal Policy Optimization Algorithms.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG Proximal Policy Optimization Algorithms

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-15T06:09:49.842364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 1442abfb-c6ea-42f8-b4e4-b79eee167cb3 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-15T06:09:49.805605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6a62b3c8-3891-4ba4-b016-ebfaff0899f0 · outbound

This paper cites Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-15T06:09:49.830454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a6e1aa3e-ff72-4d8e-ba9e-55b831b99139 · outbound

This paper cites R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-15T06:09:49.794354Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b710c942-97ec-45a3-af78-98468e34fed5 · outbound

This paper cites ZeroSearch: Incentivize the Search Capability of LLMs without Searching.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG ZeroSearch: Incentivize the Search Capability of LLMs without Searching

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-17T17:44:13.577137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation debcb10e-d190-4736-96e1-d4fe35852053 · outbound

This paper cites Tongyi DeepResearch Technical Report.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG Tongyi DeepResearch Technical Report

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-15T08:56:57.433092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c65f60ab-09d4-4830-87ec-5ab8986cccef · outbound

This paper cites HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-07-10T01:18:57.797234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c725002f-10c0-40d7-a59e-db449e214563 · outbound

This paper cites Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-15T06:09:49.812523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3fa79f97-8ce9-4cab-909f-7d99f3bf6811 · outbound

This paper cites Hotpotqa: A dataset for diverse, explainable multi-hop question answering.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG Hotpotqa: A dataset for diverse, explainable multi-hop question answering

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:10:07.297032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c02d55de-c638-4865-8a95-918dce019109 · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-15T06:09:49.836332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3e81b313-9f77-4be0-ac71-bdaadb413ee0 · outbound

This paper cites Initialization with Forced Diversifi- cation.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG Initialization with Forced Diversifi- cation

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-15T06:09:49.824208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 361f14fb-2d51-4df5-ba59-11e497c7c69a · outbound

This paper cites In contrast, GRPO-Full averages informative and weakly informative trajectories uniformly at every step, diluting the retrieval-specific supervision signal.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG In contrast, GRPO-Full averages informative and weakly informative trajectories uniformly at every step, diluting the retrieval-specific supervision signal

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:10:07.308192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d978da45-1846-4d96-a5d2-f8833ba30398 · outbound

This paper cites Al Janub Stadium, January </information> <think> Now, I find the answer to the question.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG Al Janub Stadium, January </information> <think> Now, I find the answer to the question

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:10:07.302500Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 00f7d21c-513b-4625-ac66-c722626094b5 · outbound

This paper cites Al Shaikh Stadium.

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG Al Shaikh Stadium

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-15T06:10:07.270862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

Observation 0453123b-599d-4f3f-bc63-6c90c7460976 · 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 CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-04T15:12:55.650270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.