Pith. sign in

Paper Citation Record · LEDGER

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

As of 5 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 12 inbound Pith citation observations for arXiv:2603.04474.

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

pith.paper-citation-record.v1
2603.04474 v2

Coverage vector

measured 57 of 57 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-15T16:36:43.330447Z

measured 69 of 69 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00

measured 12 of 12 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T14:21:12.213623Z

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

57 of 57 outbound references displayed

  • verified exact19
  • verified fuzzy36
  • unresolved0
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch2

External citation measurements

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

Outbound references

Observation 1b5ffedc-51c1-4ef7-9a06-c1a448e0173b · outbound

This paper cites Trustworthy agentic ai systems: A cross-layer review of architectures, threat models, and governance strategies for real-world deployment.F1000Research, 14(905):905.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Trustworthy agentic ai systems: A cross-layer review of architectures, threat models, and governance strategies for real-world deployment.F1000Research, 14(905):905

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.016901Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:2ec3e770775ab5c72942653549091082b73724c3832f7e84d7e19391a61114cc

Observation bec8269a-1c11-44b8-9d11-61d98ba68fc2 · outbound

This paper cites The orchestration of multi-agent systems: Architec- tures, protocols, and enterprise adoption.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration The orchestration of multi-agent systems: Architec- tures, protocols, and enterprise adoption

Reference 2

Resolution
verified exact
arxiv_id, observed 2026-05-15T16:40:10.670591Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:65b5f26a860e32859b678fac0569c593f328fdb43d88d646f978ce0319303d53

Observation 51c18962-df4d-41ea-900a-9ede3f1c414d · outbound

This paper cites An overview of recent advances of resilient consensus for multiagent systems under at- tacks.Computational Intelligence and Neuroscience, 2022(1):6732343.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration An overview of recent advances of resilient consensus for multiagent systems under at- tacks.Computational Intelligence and Neuroscience, 2022(1):6732343

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.012562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:d11a2803508d0cbd658f7f4af6a3242ede75d162b86ac848814396c580b35f3e

Observation fdca1db7-fafb-4e25-baf7-dbf7ef75423a · outbound

This paper cites Uci machine learning repository.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Uci machine learning repository

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.021767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:0abc98c1aa5af9d4fa2823a92adeb81f1a95be56805209722535c8c9034c6679

Observation 5e5f1a51-e2cf-4055-8704-af9fbae7416c · outbound

This paper cites Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation

Reference 5

Resolution
verified exact
arxiv_id, observed 2026-05-21T07:24:13.179886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:97656840a4556347282f9e02741ba9abb855cc79e516884802eee698fb171209

Observation c94fe53e-eeb5-4213-830a-31734474791c · outbound

This paper cites A theory of fads, fashion, custom, and cultural change as informational cascades.Journal of political Economy, 100(5):992–1026.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration A theory of fads, fashion, custom, and cultural change as informational cascades.Journal of political Economy, 100(5):992–1026

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.165217Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:a37167f92489b894acd70c38c74bb0021210ec0650b0f55c8b265446fc45a6f6

Observation cc03f118-0bb9-4df7-bdb5-359790d8dc69 · outbound

This paper cites SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration SagaLLM: Context Management, Validation, and Transaction Guarantees for Multi-Agent LLM Planning

Reference 7

Resolution
verified exact
arxiv_id, observed 2026-05-15T16:40:10.636622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:6ac403a01b2ea5b82b8eb514ec75cb3319ba15a880cb2d1565b7341466e70a70

Observation 5d63d049-d7e9-4a85-84fd-b377d13bdf82 · outbound

This paper cites A lattice model of secure informa- tion flow.Communications of the ACM, 19(5):236–243.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration A lattice model of secure informa- tion flow.Communications of the ACM, 19(5):236–243

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.026042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:0e07c228c761ea7e4ce64a42cc9c3089b9f10464434ac75a83e31d765e6fd837

Observation 950523ac-f70d-4c74-bedb-456508c30ff3 · outbound

This paper cites Improving factuality and reasoning in language models through multiagent de- bate.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Improving factuality and reasoning in language models through multiagent de- bate

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.160943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:e0f4facb63d10e99b144373e59f1c467aa8209324f41412250c851d5a646c647

Observation b1794681-6067-4990-ac88-a1e14d921deb · outbound

This paper cites Exploration of LLM Multi-Agent Application Implementation Based on LangGraph+CrewAI.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Exploration of LLM Multi-Agent Application Implementation Based on LangGraph+CrewAI

Reference 10

Resolution
verified exact
arxiv_id, observed 2026-05-15T16:40:10.631810Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:6593f3528a585c8cf805fce12531f481d454a0188d380bb4c04916fc4890b0ef

Observation 63c94ffe-6e36-43f9-ab11-f0807ac241cd · outbound

This paper cites PhD thesis, University of Oxford.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration PhD thesis, University of Oxford

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.030524Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:7ed42f58cc4b21a2c756232094cf73002c6003dec05b9a84cb386137e7d54c5d

Observation 1640e2ac-bdfd-4aac-ae3f-ab33b4c77eb4 · outbound

This paper cites Ragas: Automated evaluation of retrieval augmented generation.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Ragas: Automated evaluation of retrieval augmented generation

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.064231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:d32d3d821cc2775c2ad6d842ef3c70d08e72408c3bde2043c1b6cbaa54f28e41

Observation 59ecaab9-9bf8-4b11-9ed0-95d0eb4491df · outbound

This paper cites From prompt injections to pro- tocol exploits: Threats in llm-powered ai agents work- flows.ICT Express.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration From prompt injections to pro- tocol exploits: Threats in llm-powered ai agents work- flows.ICT Express

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.035199Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:d8f1d09649c2e79cd501f9c3b5aa53a42879b277f694cd8265702f76bdebcea1

Observation ced07893-2c0f-43d4-aea0-8069102adf79 · outbound

This paper cites Multi-agent frame- work for threat mitigation and resilience in ai-based systems.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Multi-agent frame- work for threat mitigation and resilience in ai-based systems

Reference 14

Resolution
verified exact
arxiv_id, observed 2026-05-15T16:40:10.610785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:7a39a0cd9b7614fa1721cf76046e08195e119d5145b729ae85496d0239b7628f

Observation a891d0ff-843f-4807-a1be-23f506063f14 · outbound

This paper cites Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injec- tion.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injec- tion

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.096927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:f16edb519119ccc0468a7bbae3b97b68f039a7ba6cd4e6a76a1328a09ca06d98

Observation 95405a5e-d8f8-4e72-8ecc-4e6882262592 · outbound

This paper cites Large Language Model based Multi-Agents: A Survey of Progress and Challenges.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Large Language Model based Multi-Agents: A Survey of Progress and Challenges

Reference 16

Resolution
verified exact
local_arxiv, observed 2026-05-15T16:40:10.620987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:bf8d5bbb24b5d67c7235a6a374bdbf5ed88bf9516d6726674f1c5b5b5e337740

Observation 22538662-b600-4e9a-8e89-bfaa84a3045e · outbound

This paper cites DeBERTa: Decoding-enhanced BERT with Disentangled Attention.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration DeBERTa: Decoding-enhanced BERT with Disentangled Attention

Reference 17

Resolution
verified exact
local_arxiv, observed 2026-05-15T16:40:10.641079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:6624730ccb07be2e44de033c0e1776fcfd61c5c75e0851c99c9cef849a45fffc

Observation bdaf8ade-94dd-4b0c-b604-d3ee454dcd5d · outbound

This paper cites Red-teaming llm multi-agent systems via communication attacks.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Red-teaming llm multi-agent systems via communication attacks

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.134713Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:b5210299114366f65a74189ee69e5e62fa58a9133424f32e6156c77706fe853d

Observation b51e21b9-26c0-4fe8-b3db-78b045d2d3cf · outbound

This paper cites SentinelAgent: Graph-based Anomaly Detection in Multi-Agent Systems.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration SentinelAgent: Graph-based Anomaly Detection in Multi-Agent Systems

Reference 19

Resolution
metadata mismatch
arxiv_id, observed 2026-05-15T16:40:10.605299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:287734835ed76215767f6333cb53940f8b4b8ac43d0da1e743ef859b18c10a56

Observation 09e6a53b-3989-4da1-80cc-cdbf3cd6aaea · outbound

This paper cites Measuring Massive Multitask Language Understanding.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Measuring Massive Multitask Language Understanding

Reference 20

Resolution
verified exact
local_arxiv, observed 2026-05-15T16:40:10.665108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:7ae397082a5ea2b9b8eda1af98eb6d19f75f60e1e5ba57f37286c264f01bb7e9

Observation b03492af-11f6-4e58-b982-9e967ddca6fa · outbound

This paper cites Measuring Mathematical Problem Solving With the MATH Dataset.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Measuring Mathematical Problem Solving With the MATH Dataset

Reference 21

Resolution
verified exact
local_arxiv, observed 2026-05-15T16:40:10.590118Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:c80604553bc70a1cb2dac16d1008d4b881d150cbb2c470dc500c0f282cb0b99c

Observation 4e0edbf6-304f-410f-8f78-c0bb55d32bb3 · outbound

This paper cites Metagpt: Meta programming for a multi-agent collabora- tive framework.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Metagpt: Meta programming for a multi-agent collabora- tive framework

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.114137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:2b6c4b488164bd2d7ff6d3daccbde3096de1b91ac3da19b29d5145394ff79918

Observation 881cb4d5-51f3-44dd-baf6-675711c6cdc9 · outbound

This paper cites Understanding the planning of LLM agents: A survey.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Understanding the planning of LLM agents: A survey

Reference 23

Resolution
verified exact
local_arxiv, observed 2026-05-15T16:40:10.615644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:1e27ee1288940c5ddf307e41ec1b97bf52718da7bb92714bd29b0a1190585ee9

Observation 7db92c73-39e5-448c-acaf-9ca5ac6645f4 · outbound

This paper cites An overview on multi-agent consensus under adversarial attacks.An- nual Reviews in Control, 53:252–272.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration An overview on multi-agent consensus under adversarial attacks.An- nual Reviews in Control, 53:252–272

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.087313Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:d201aba6433febd91cf7e1045fa1234b34191f943e089e3b14739e8c7607f262

Observation 82826e37-c89b-414d-8af2-eff833bc6e6f · outbound

This paper cites A multi-vocal review of security orchestration.ACM Computing Surveys (CSUR), 52(2):1–45.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration A multi-vocal review of security orchestration.ACM Computing Surveys (CSUR), 52(2):1–45

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.143091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:7679831cd56186ddae41537b3a6c2e4bd1abfa7ab6e8aff020efe9233d5af786

Observation 2e92ac95-392a-48a3-8336-78267b07e7b7 · outbound

This paper cites Towards mitigating llm halluci- nation via self reflection.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Towards mitigating llm halluci- nation via self reflection

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.075266Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:4422e87de80c5e268d8ead1f1a45d887f0f8389214d2b89a26fc619900a96f58

Observation f2b76f25-546f-4d03-b21e-3908e8634f76 · outbound

This paper cites A survey on large language models for code generation.ACM Transactions on Software Engi- neering and Methodology, 35(2):1–72, January 2026.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration A survey on large language models for code generation.ACM Transactions on Software Engi- neering and Methodology, 35(2):1–72, January 2026

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.092486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:2024547afb156939d629200c499d98b8b16b5eecb5bdf1a97e25fbda154d327d

Observation 7bbf6288-6f69-4e15-9868-d4f8e99e4378 · outbound

This paper cites A survey of llm-driven ai agent communication: Protocols, security risks, and defense countermeasures.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration A survey of llm-driven ai agent communication: Protocols, security risks, and defense countermeasures

Reference 28

Resolution
verified exact
arxiv_id, observed 2026-05-15T16:40:10.624659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:f33eb400a6a34dd28fbe1948310477f6d58aaa1e8dadb2321df07be2a8c3df04

Observation 1939c595-80a5-46c6-90ce-4d1e0e58dbe2 · outbound

This paper cites Retrieval-augmented generation for knowledge- intensive nlp tasks.Advances in neural information processing systems, 33:9459–9474.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Retrieval-augmented generation for knowledge- intensive nlp tasks.Advances in neural information processing systems, 33:9459–9474

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.178363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:9de5face2f509865c782677dfbc34e6a59028eaa8646d6213510d022a8c908b8

Observation 69fd8c2f-b4bb-4230-96b3-16ee84282cb0 · outbound

This paper cites Camel: Communica- tive agents for" mind" exploration of large language model society.Advances in Neural Information Process- ing Systems, 36:51991–52008.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Camel: Communica- tive agents for" mind" exploration of large language model society.Advances in Neural Information Process- ing Systems, 36:51991–52008

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.108778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:2dd44e6c70809d92791dadb3de4447b436dac8e49c017709e43448770bc4f532

Observation 2401956d-b25d-40eb-a58a-3c03a04c3d18 · outbound

This paper cites A survey on llm-based multi-agent systems: workflow, in- frastructure, and challenges.Vicinagearth, 1(1):9.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration A survey on llm-based multi-agent systems: workflow, in- frastructure, and challenges.Vicinagearth, 1(1):9

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.044516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:61ad12aac6cfe9a5358ab6412211485f7de94013fd00dd9569528feb74804fb0

Observation 59852961-3b90-4b27-9085-d95f9c32a0fb · outbound

This paper cites Attack and defense techniques in large language models: A survey and new perspectives.Neu- ral Networks, page 108388.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Attack and defense techniques in large language models: A survey and new perspectives.Neu- ral Networks, page 108388

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.147799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:c643176029563f6dcc1f259cfa148e924c946e8d77b4c2fa3b08b9945ed69301

Observation dfefdddc-dbfe-4d1c-a9f0-49f9de60456d · outbound

This paper cites The Dark Side of LLMs: Agent-based Attack Vectors for System-level Compromise.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration The Dark Side of LLMs: Agent-based Attack Vectors for System-level Compromise

Reference 33

Resolution
verified exact
local_arxiv, observed 2026-05-15T16:40:10.570454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:1a25a82c05f08d1bcfbf2de7dd5dfd5ed5c31e7f175506ee2edae33b57cfa21e

Observation f5300bf8-8325-452a-8b1e-ae98f5229567 · outbound

This paper cites Factscore: Fine-grained atomic evaluation of factual precision in long form text generation.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Factscore: Fine-grained atomic evaluation of factual precision in long form text generation

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.058988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:ff825877b9eb81194451c162cb20064bf05bb6f4366c9b9395b4dbff275adb2b

Observation c7356909-9a9c-4fe5-8d8f-59faf2bef2c8 · outbound

This paper cites Why do multiagent systems fail? In ICLR 2025 Workshop on Building Trust in Language Models and Applications.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Why do multiagent systems fail? In ICLR 2025 Workshop on Building Trust in Language Models and Applications

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.082494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:8ecbe0ed2ab21fc7172cc53369255afbd4c124b5441904161c6025d69eab5a51

Observation 9f6b75c1-200e-4336-bf8c-a6a1c9e48091 · outbound

This paper cites Epidemic processes in complex networks.Reviews of modern physics, 87(3):925–979.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Epidemic processes in complex networks.Reviews of modern physics, 87(3):925–979

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.138641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:9095ac2e0c768c63f4a06c884a57750eb354864830c4345d53f1076b0a21ba1d

Observation ec4de774-f8c3-42f3-96f0-ce513ff2d760 · outbound

This paper cites A review on agent-to-agent pro- tocol: Concept, state-of-the-art, challenges and future directions.Authorea Preprints.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration A review on agent-to-agent pro- tocol: Concept, state-of-the-art, challenges and future directions.Authorea Preprints

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.130135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:0883d2155289008bef955628bf0f7268e2f95bbc5eb67a17d3a12fb6c1ed89e2

Observation 029affb2-7b02-417d-8be4-2db6a363537d · outbound

This paper cites Agentic AI: A Conceptual Taxonomy, Applications and Challenges.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Agentic AI: A Conceptual Taxonomy, Applications and Challenges

Reference 38

Resolution
verified exact
arxiv_id, observed 2026-05-15T16:40:10.629806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:16d1b97eb95f2c7bf52a74c98e2f2d0feae71ea3af702d30b668e4c3a3e92f3f

Observation 09a68c78-ebc7-4c3b-b54d-ae76556ab13b · outbound

This paper cites Audit-LLM: Multi-Agent Collaboration for Log-based Insider Threat Detection.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Audit-LLM: Multi-Agent Collaboration for Log-based Insider Threat Detection

Reference 39

Resolution
verified exact
arxiv_id, observed 2026-05-15T16:40:10.634987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:8d395f043428c696b8d13e179cba6da99ab46b1dfedd6fa8e007767afe955b12

Observation d265a88e-3485-408e-9b45-9f378017087e · outbound

This paper cites Towards detecting llms hallucination via markov chain-based multi-agent debate framework.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Towards detecting llms hallucination via markov chain-based multi-agent debate framework

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.124703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:b12cdd5f295c64bf052bff683d375fe42494afffe68f8b3644782bfd46df429c

Observation 817a75d5-b7f2-48ee-ba40-6531b5f79be3 · outbound

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

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agents

Reference 41

Resolution
verified exact
arxiv_id, observed 2026-05-15T16:40:10.626671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:d1493303655de1c22e4f4b73d0151205064825042687ab6121844a29db0ee143

Observation 2c4ea325-7518-42d9-bc05-6591f8c5b3f8 · outbound

This paper cites Creating large language model applications utilizing langchain: A primer on developing llm apps fast.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Creating large language model applications utilizing langchain: A primer on developing llm apps fast

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.053668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:e266f0081dedb132e061c0c14ac508084f1557018a87b34b3bf8373625bd45db

Observation 5e16f565-d5b9-456b-895a-d2bd684ae017 · outbound

This paper cites Multi-Agent Systems Execute Arbitrary Malicious Code.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Multi-Agent Systems Execute Arbitrary Malicious Code

Reference 43

Resolution
metadata mismatch
arxiv_id, observed 2026-05-15T16:40:10.565595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:9a14ad6daf4d7da237062cd7d95602005f420a139c01d3c958d75f763b3562ba

Observation 06d28cfa-2635-43c2-82a1-231d39a91ad7 · outbound

This paper cites The spread of true and false news online.science, 359(6380):1146– 1151.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration The spread of true and false news online.science, 359(6380):1146– 1151

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.169716Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:a381134f38603c09bd0e1e7789d1d229002a25a6f1078ded62eeecc11b6e9738

Observation cc5fb910-1e10-4733-a12f-a1a3d89e6932 · outbound

This paper cites Agent AI with LangGraph: A Modular Framework for Enhancing Machine Translation Using Large Language Models.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Agent AI with LangGraph: A Modular Framework for Enhancing Machine Translation Using Large Language Models

Reference 45

Resolution
verified exact
arxiv_id, observed 2026-05-15T16:40:10.571109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:837c672db6ac9f9dacdf40c10507af526afc3f7974f7862db835f3c294e647ba

Observation ba745369-c072-4f81-af9b-ef34dc3543b6 · outbound

This paper cites A survey on large language model based autonomous agents.Frontiers of Computer Science, 18(6):186345.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration A survey on large language model based autonomous agents.Frontiers of Computer Science, 18(6):186345

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.183658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:7c18c28280f5f7b919f466458e8d029df50016a9839223a0d18f27e22d35eb55

Observation 3443dfb4-dfb6-4f1b-b6fc-aee837d3c768 · outbound

This paper cites Security of internet of agents: Attacks and counter- measures.IEEE Open Journal of the Computer Society.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Security of internet of agents: Attacks and counter- measures.IEEE Open Journal of the Computer Society

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.174027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:37dd57e3bde57c07edeccd7ff738f81c73681c3dd1b45c047e682c72d5b2815f

Observation d9ddf7e7-fa6e-43ae-a320-b219ed26e605 · outbound

This paper cites Large model based agents: State-of-the-art, cooperation paradigms, security and privacy, and future trends.IEEE Communications Surveys & Tutorials.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Large model based agents: State-of-the-art, cooperation paradigms, security and privacy, and future trends.IEEE Communications Surveys & Tutorials

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.152337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:8eda5ff8652f7690afd67929a56927c05b8d6bbecf72161df966f2f3e338040f

Observation 26a450ba-ec93-44bd-8080-a1e1bcf9d488 · outbound

This paper cites A simple model of global cascades on random networks.Proceedings of the National Academy of Sciences, 99(9):5766–5771.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration A simple model of global cascades on random networks.Proceedings of the National Academy of Sciences, 99(9):5766–5771

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.156774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:2792a58c4d9f0686d16258406c31abea7e4d419ddb615f51df3aaa7ef02a64bc

Observation 2bc99559-e9ad-4990-ac13-b79c55fe42fc · outbound

This paper cites Autogen: Enabling next-gen llm applications via multi-agent conversations.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Autogen: Enabling next-gen llm applications via multi-agent conversations

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.049061Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:989304afd96425caecff4a4c55546869fb3792a86ad22bdf409e9bd88f635432

Observation d9920f23-a17b-4ff1-a665-357491ee2c4c · outbound

This paper cites The rise and potential of large language model based agents: A survey.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration The rise and potential of large language model based agents: A survey

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.102130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:23070ef0260149c28cf27fdae61f7ff06acd31ef6538b75ab0373cc37d63b6a5

Observation 5b14e64f-78df-419b-9fd1-7c7a130017bf · outbound

This paper cites Who’s the mole? modeling and detecting intention-hiding malicious agents in llm-based multi-agent systems.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Who’s the mole? modeling and detecting intention-hiding malicious agents in llm-based multi-agent systems

Reference 52

Resolution
verified exact
arxiv_id, observed 2026-05-15T16:40:10.659295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:a3dd1dee276cb56ead8bba257efcb71e3ef7de994268b683529b38df9dcd5426

Observation b4c5dbc2-682b-4f2d-ab28-098195bd0095 · outbound

This paper cites Minimizing hallucinations and communication costs: Adversarial debate and voting mechanisms in llm-based multi-agents.Applied Sciences, 15(7):3676.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Minimizing hallucinations and communication costs: Adversarial debate and voting mechanisms in llm-based multi-agents.Applied Sciences, 15(7):3676

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.039958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:f76b65ce00359fdc0476aa2348ba4e1abfd469b8301e8018983060585d0996a3

Observation 222fb120-d66e-418f-93fb-419a6fe8c125 · outbound

This paper cites Jailbreak Attacks and Defenses Against Large Language Models: A Survey.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Reference 54

Resolution
verified exact
local_arxiv, observed 2026-05-15T16:40:10.651710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:f0aebfdf583d8eacae3749c6c866e594c940a2cda334eb1efb9bc6ac366cf3dd

Observation 44e124b1-805a-4f33-a363-6a232cadf090 · outbound

This paper cites Blockchain for network service or- chestration: Trust and adoption in multi-domain envi- ronments.IEEE Communications Standards Magazine, 7(2):16–22.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Blockchain for network service or- chestration: Trust and adoption in multi-domain envi- ronments.IEEE Communications Standards Magazine, 7(2):16–22

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.070200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:e59db458c35e92561acd151a75ec430ad5a80af1f0f47aa0fa4752b789fadf6d

Observation e7c5c23e-e7f1-4887-9288-f5711a0115de · outbound

This paper cites Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems

Reference 56

Resolution
verified exact
arxiv_id, observed 2026-05-15T16:40:10.646859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:23374b654062a17ee85b7ac26060ea89111480f73db39de08ad65ef69f3c1477

Observation a645ee21-82d6-43ba-9aa9-a544100709b2 · outbound

This paper cites infection.

From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration infection

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-05-15T16:41:18.119975Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-15T16:36:43.330447Z digest=sha256:eec27238341b5e8af7185164678e6a5ad3bc1e240d57a0194d08b9fd7cced5ca

Pith citing papers

Observation a2ef967e-e04c-4694-a664-f48f88b64712 · inbound

Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy cites this paper.

Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

Reference 32

Resolution
verified exact
local_arxiv, observed 2026-05-14T20:07:53.702189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-14T20:04:57.638215Z digest=sha256:27fae2d921401f2d0b37ebdb650e15b8898c8371e4c65cdb4a69b6ee58d7bad8

Observation 3f48360f-0337-426f-a1df-259598e91e05 · inbound

Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy cites this paper.

Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

Reference 32

Resolution
verified exact
local_arxiv, observed 2026-05-20T21:33:46.453242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-20T21:30:30.384184Z digest=sha256:36d45f790c70b6bcca848ce78f2857170f44abbd91cb335e1d0f7df8ba113880

Observation 62f0da9f-634d-4c50-844b-3944070656c2 · inbound

CASPIAN: Online Detection and Attribution of Cascade Attacks in LLM Multi-Agent Systems via Cross-Channel Causal Monitoring cites this paper.

CASPIAN: Online Detection and Attribution of Cascade Attacks in LLM Multi-Agent Systems via Cross-Channel Causal Monitoring From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

Reference 41

Resolution
verified exact
local_arxiv, observed 2026-05-20T03:13:00.385123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-05-20T03:11:36.534055Z digest=sha256:bac5b6bc00a9598a4f8a7d06d4342079d456af2e45fccb019f077d308a3c465f

Observation b9ed889a-8efa-4a23-a9f5-9e2dc637a2ab · inbound

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation cites this paper.

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

Reference 211

Resolution
metadata mismatch
local_arxiv, observed 2026-06-27T13:20:56.826731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-06-27T12:55:22.831264Z digest=sha256:d92086f037e379dbaa36afaa00005720228f497bac7e13eba918c93398a07e28

Observation e695ac46-876d-48ad-8a79-4fe1f93c27a0 · inbound

NRT-Bench: Benchmarking Multi-Turn Red-Teaming of LLM Operator Agents in Safety-Critical Control Rooms cites this paper.

NRT-Bench: Benchmarking Multi-Turn Red-Teaming of LLM Operator Agents in Safety-Critical Control Rooms From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

Reference 28

Resolution
verified exact
local_arxiv, observed 2026-07-04T04:09:34.454907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-06-26T17:13:26.201462Z digest=sha256:a6fee27ce0d4472a46ec54c7d9abfbccba028f2b2220a064139c2e1b9f68294b

Observation 0d03a1b9-6302-4ea1-9be9-b715c3f19877 · inbound

Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement cites this paper.

Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

Reference 4

Resolution
verified exact
local_arxiv, observed 2026-07-01T18:55:58.653362Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=pdf_text observed=2026-06-29T01:25:53.612641Z digest=sha256:39870d76b3f3a3598fc2972c673602877543c9a87f4ad6fc651c9876262d2997

Observation 491c2103-3253-4368-b269-925a47dd9ffa · inbound

Understanding Rollout Error in Graph World Models cites this paper.

Understanding Rollout Error in Graph World Models From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

Reference 48

Resolution
metadata mismatch
local_arxiv, observed 2026-06-29T19:13:53.337311Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

source=arxiv_source observed=2026-06-29T04:49:51.445689Z digest=sha256:f720273544797f0d2f13f3e3fcf03e769d4f046152dcd5bac4efbf87cc7e1891

Observation aedf62a0-3ec1-418e-aeba-40db4d562ef3 · inbound

Diagnosis-Driven Automatic Repair for Agentic Workflow via Symbolic Inference cites this paper.

Diagnosis-Driven Automatic Repair for Agentic Workflow via Symbolic Inference From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

Reference 29

Resolution
unresolved
no resolver link, observed 2026-07-12T06:24:52.086585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-12T06:24:52.086585Z digest=sha256:98ef1ed1271665f62b43ad63435abc7e1f23b9a941a9eca66a7eec6f6d314675

Observation dc720055-5096-4c7b-9653-c5141e3b3670 · inbound

MechMath Agent Team: LLM Driven Agents for Mathematical Research cites this paper.

MechMath Agent Team: LLM Driven Agents for Mathematical Research From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

Reference 50

Resolution
unresolved
no resolver link, observed 2026-07-11T19:30:43.940487Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-11T19:30:43.940487Z digest=sha256:e897f7bb5db3ba0fa3d53c0adc2bdcdf23e97e3cb8709e3fa2cf33c39a791182

Observation 99d81090-ac32-4f72-bef2-20f30aef69ea · inbound

Faithful, Not Corrective: Message-Format Effects in Multi-Hop Agent Relays Are Tier-Dependent cites this paper.

Faithful, Not Corrective: Message-Format Effects in Multi-Hop Agent Relays Are Tier-Dependent From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

Reference 20

Resolution
unresolved
no resolver link, observed 2026-07-14T18:00:19.323220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-07-14T18:00:19.323220Z digest=sha256:cb5a8632320d41e0013418a4a57c2a7d0c9d721763c19edfdf9859581178ac11

Observation 699ade45-619b-497f-97c8-81f5b95f3c7d · inbound

Semantic Register Compression in Multi-Agent LLM Cascades cites this paper.

Semantic Register Compression in Multi-Agent LLM Cascades From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-02T14:21:12.213623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T14:21:12.213623Z digest=sha256:1e84f3d100da8fc86a3cde2ebad63fb5f411779b8f0a404f7150518d4752528b

Observation e7f7e079-a5ab-4eff-bf9d-66f83d3d7a7b · inbound

How Affect Propagates among LLM Agents: Emergent Emotional Contagion in Crowd Simulation cites this paper.

How Affect Propagates among LLM Agents: Emergent Emotional Contagion in Crowd Simulation From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

Reference 17

Resolution
unresolved
no resolver link, observed 2026-07-31T00:25:48.559457Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-07-31T00:25:48.559457Z digest=sha256:01283d0ac92431421667330c426e8255658ee7220fa5f8f7844cf91ceca2e225