Paper Citation Record · LEDGER

A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

As of 6 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 22 inbound Pith citation observations for arXiv:2508.05668.

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

pith.paper-citation-record.v1
2508.05668 v3

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 22 of 22 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 22 of 22 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T17:26:29.063843Z

measured 1 of 1 external citation measurements

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

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation fd40398d-4e15-4daf-b7ab-e6fe59d0ebb1 · inbound

AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications cites this paper.

AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 108

Resolution: unresolved; no resolver link, observed 2026-08-05T17:26:29.063843Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4266b1db-1aad-4bdb-b26b-791ebcb31019 · inbound

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs cites this paper.

Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-18T11:11:18.254256Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 43344374-0792-4759-a849-971fb36ac07d · inbound

ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling cites this paper.

ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-18T06:30:59.569559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 464da0e5-f8a2-4f4c-984f-9ba853564ee0 · inbound

Rerank Before You Reason: Analyzing Reranking Tradeoffs through Effective Token Cost in Deep Search Agents cites this paper.

Rerank Before You Reason: Analyzing Reranking Tradeoffs through Effective Token Cost in Deep Search Agents A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T09:22:24.031110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e94120d-74fc-466b-9d30-21a16f45df08 · inbound

Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions cites this paper.

Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 108

Resolution: unresolved; no resolver link, observed 2026-08-02T23:04:38.875335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16a6bc5d-085b-44a9-a6b6-d22fd7bc0982 · inbound

Learning to Retrieve from Agent Trajectories cites this paper.

Learning to Retrieve from Agent Trajectories A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-14T01:48:36.104459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7b690d0e-3f97-4e57-9427-fc43f264d21b · inbound

Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration cites this paper.

Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:35:52.035835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4d2b283c-6527-4909-becf-3e922f46bb7f · inbound

Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering cites this paper.

Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 162

Resolution: verified exact; arxiv_id, observed 2026-05-11T06:20:59.186406Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 58b40efd-2edb-4470-ae4d-18b47fd8c12a · inbound

Towards Long-horizon Agentic Multimodal Search cites this paper.

Towards Long-horizon Agentic Multimodal Search A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:06:00.211792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5b7e3d95-3900-4719-ad00-bca5dc1e4e81 · inbound

Rethinking Agentic Reinforcement Learning In Large Language Models cites this paper.

Rethinking Agentic Reinforcement Learning In Large Language Models A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 103

Resolution: verified exact; arxiv_id, observed 2026-05-12T10:21:29.997032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bd0760be-d400-46b0-b4ac-ce327f4be458 · inbound

Rethinking Agentic Reinforcement Learning In Large Language Models cites this paper.

Rethinking Agentic Reinforcement Learning In Large Language Models A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 103

Resolution: verified exact; arxiv_id, observed 2026-05-11T22:11:16.875985Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9182d4be-c741-47a6-916e-8ea4bc9cb1b3 · inbound

Rethinking Agentic Reinforcement Learning In Large Language Models cites this paper.

Rethinking Agentic Reinforcement Learning In Large Language Models A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 103

Resolution: verified exact; arxiv_id, observed 2026-05-19T17:02:40.673324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e643a8d9-d12c-470b-8146-91e666ad5a8f · inbound

SiriusHelper: An LLM Agent-Based Operations Assistant for Big Data Platforms cites this paper.

SiriusHelper: An LLM Agent-Based Operations Assistant for Big Data Platforms A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-11T14:46:23.671715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation fc4ccc06-6b43-46a3-ac8d-8a1b2ba9acd6 · inbound

Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific Agents cites this paper.

Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific Agents A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-12T05:41:26.150940Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a91df4ae-4735-48a0-a27d-6d0410558fc8 · inbound

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning cites this paper.

DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:26:23.574460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4034df69-f88c-4012-9025-af2ea420a97f · inbound

Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging cites this paper.

Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-14T18:57:50.400199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 637a08b8-a3b0-456a-ac68-5b0e52449469 · inbound

Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents cites this paper.

Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-19T20:33:13.107489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c202f943-1dbc-4855-80a8-3da4ea0bf596 · inbound

From Blind Guess to Informed Judgment: Teaching LLMs to Evaluate Materials by Building Knowledge-Augmented Preference Signals cites this paper.

From Blind Guess to Informed Judgment: Teaching LLMs to Evaluate Materials by Building Knowledge-Augmented Preference Signals A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-06-29T07:33:13.358551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4cfc8b1b-d6f0-408f-8f1a-c8ee0900f7f6 · inbound

Toward Generalist Autonomous Research via Hypothesis-Tree Refinement cites this paper.

Toward Generalist Autonomous Research via Hypothesis-Tree Refinement A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-06-27T09:40:47.128809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 27adf1d2-70cc-4dd5-995a-a2c887028ec8 · inbound

VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery cites this paper.

VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 16

Resolution: metadata mismatch; local_arxiv, observed 2026-07-08T08:04:47.982149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4bc0d0a2-02c0-49a2-8efa-63e0404f1ed7 · 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 A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T18:27:16.707483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc91d440-2d38-4afb-a2b5-7fa12697bdef · 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 A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges

Reference 216

Resolution: unresolved; no resolver link, observed 2026-08-04T15:12:56.091613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.