Paper Citation Record · LEDGER

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox

As of 13 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2605.10787.

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

pith.paper-citation-record.v1
2605.10787 v2

Coverage vector

measured 38 of 38 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-21T08:08:04.544564Z

measured 38 of 38 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

38 of 38 outbound references displayed

verified exact4
verified fuzzy10
unresolved2
parse uncertain2
malformed identifier0
metadata mismatch20

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 64829d28-c0bf-4662-8da1-cf5fa8c0bc5d · outbound

This paper cites Langley , title =.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox Langley , title =

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T08:09:52.262763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation cde92c6f-1628-40dc-a59e-254b2b28a3ea · outbound

This paper cites Search-o1: Agentic Search-Enhanced Large Reasoning Models.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox Search-o1: Agentic Search-Enhanced Large Reasoning Models

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T08:09:51.277152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 79c3f095-27f5-47bd-a486-a748dc63da7c · outbound

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

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T08:09:51.263706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e38e9970-45c9-415f-8c2f-b14b8d94550d · outbound

This paper cites ToRL: Scaling Tool-Integrated RL.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox ToRL: Scaling Tool-Integrated RL

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-21T08:09:51.260787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f10d98d3-0f6f-4ebe-a265-d7a461bc024e · outbound

This paper cites WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T08:09:51.292643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a81eed18-1f81-4064-b2f5-061c1b1665d4 · outbound

This paper cites Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T08:09:52.260736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a3a65ebf-aaa3-4fa0-ab86-fcb87b296a1d · outbound

This paper cites The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery

Reference 7

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T08:09:51.235176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation b7a7f456-3f3b-44a2-81e4-ce4f2dac55c3 · outbound

This paper cites The eleventh international conference on learning representations , year=.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox The eleventh international conference on learning representations , year=

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T08:09:52.253984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 513919e0-0d67-48c0-88ab-19c52268634e · outbound

This paper cites Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations , pages=.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations , pages=

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T08:09:52.256309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 7fbcf87d-e43d-4bf5-b616-d1fef4bc1c42 · outbound

This paper cites MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T08:09:51.241818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 7f410ef5-934d-4d6d-b6a9-715c15005dd7 · outbound

This paper cites ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T08:09:51.250993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5d401bf6-8419-4056-be90-c17f0a3d8fbb · outbound

This paper cites AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T08:09:51.238549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 82b16947-7659-4df3-9f41-177646597bc8 · outbound

This paper cites Forty-second International Conference on Machine Learning , year=.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox Forty-second International Conference on Machine Learning , year=

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T08:09:52.258302Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ad999b72-c1c3-47a4-9317-1ba63e77e731 · outbound

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

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

Reference 14

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T08:09:51.301730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 8d04b207-e7ed-43b9-b1a4-137e5418517d · outbound

This paper cites $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T08:09:51.244823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 4dc23ab0-a685-4d08-9947-d2f5293ba476 · outbound

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

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox WebArena: A Realistic Web Environment for Building Autonomous Agents

Reference 16

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T08:09:51.289844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation a8cc783b-7c09-4cea-9dfc-453c40d3ddb2 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox Advances in Neural Information Processing Systems , volume=

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T08:09:52.249748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5714d66f-93c4-41c6-bb92-e6be0a2fc0f0 · outbound

This paper cites Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions

Reference 18

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T08:09:51.305160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f49e1e44-bb4c-4f36-a2b7-306019a8585a · outbound

This paper cites MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-21T08:09:51.280527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 9f082c99-b21c-4773-a3cb-650ce9c4645e · outbound

This paper cites Mo et al.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox Mo et al

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T08:09:51.254538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 635c1359-2c31-4fd9-abe1-9c24191f4f41 · outbound

This paper cites arXiv preprint arXiv:2510.04550 , year=.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox arXiv preprint arXiv:2510.04550 , year=

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-21T08:09:51.286787Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f5c2bfcc-0cc2-4ba1-a130-03f7dd0f8b2e · outbound

This paper cites Survey on Evaluation of LLM-based Agents.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox Survey on Evaluation of LLM-based Agents

Reference 22

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T08:09:51.295381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation fbc60668-9b9d-4912-ad01-1fcdc08bccf4 · outbound

This paper cites GPT-4o System Card.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox GPT-4o System Card

Reference 23

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T08:09:51.270067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f8063380-a8ff-4886-9352-728eda06d431 · outbound

This paper cites 2025 , eprint=.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox 2025 , eprint=

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T08:09:52.266412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5e535fe2-22ff-4651-8d18-26bebd4650f0 · outbound

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

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 25

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T08:09:51.231660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation ca7f54d7-6815-4902-beea-5e4326153a06 · outbound

This paper cites an unresolved cited work.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox Unresolved cited work

Reference 26

Resolution: parse uncertain; raw_fallback, observed 2026-05-21T08:09:52.264583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 248e9ac4-a198-4c77-9614-510932d6bfa5 · outbound

This paper cites an unresolved cited work.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox Unresolved cited work

Reference 27

Resolution: parse uncertain; raw_fallback, observed 2026-05-21T08:09:52.268552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0e19e981-dd63-4493-8dc7-9a7c6ea43314 · outbound

This paper cites an unresolved cited work.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-05-21T08:09:52.272740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e0cf5376-ea12-45ef-af1b-a9ad8ca0aa95 · outbound

This paper cites an unresolved cited work.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-05-21T08:09:52.251873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 596b6a9f-f569-4013-b486-f38b1b7c088a · outbound

This paper cites Qwen3 Technical Report.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox Qwen3 Technical Report

Reference 30

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T08:09:51.257757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation f9f2b629-6d8f-41ce-a081-f76a95080418 · outbound

This paper cites DeepSeek-V3 Technical Report.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox DeepSeek-V3 Technical Report

Reference 31

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T08:09:51.274127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e63900fd-f256-4bfe-87ea-dd5cda1dfc48 · outbound

This paper cites Kimi K2: Open Agentic Intelligence.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox Kimi K2: Open Agentic Intelligence

Reference 32

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T08:09:51.267150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation e1a18eb0-4d23-49a0-9b31-0735b5a81d0d · outbound

This paper cites GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

Reference 33

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T08:09:51.283396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation c972d9c0-4c5a-47a6-9ff0-4754b88ff3d7 · outbound

This paper cites arXiv e-prints , pages=.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox arXiv e-prints , pages=

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T08:09:52.274659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 5088c91c-ab89-47fe-9a66-82df53a5aea6 · outbound

This paper cites RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-05-21T08:09:51.298758Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 0f768033-6540-4c06-8272-8e96a16a5553 · outbound

This paper cites Scholarpedia , volume=.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox Scholarpedia , volume=

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T08:09:52.247571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation 95cd9562-e425-4992-8bb9-e0e2b4045e3f · outbound

This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Reference 37

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T08:09:51.248018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Observation aa6e7445-c326-4e75-9621-b15f7d8f3c92 · outbound

This paper cites 2024 , eprint=.

ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox 2024 , eprint=

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T08:09:52.270713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

Pith citing papers

No inbound Pith citation observations are available.