Pith. sign in

Paper Citation Record · LEDGER

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents

As of 13 August 2026, this Paper Citation Record lists 66 of 66 outbound references and 0 inbound Pith citation observations for arXiv:2608.09476.

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

pith.paper-citation-record.v1
2608.09476 v1

Coverage vector

measured 66 of 66 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T16:53:35.001891Z

measured 66 of 66 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

66 of 66 outbound references displayed

  • verified exact0
  • verified fuzzy43
  • unresolved18
  • parse uncertain5
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 4bbcc03d-c4f9-4026-aad7-b369bfe62fa2 · outbound

This paper cites an unresolved cited work.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Unresolved cited work

Reference 1

Resolution
unresolved
raw_fallback, observed 2026-08-11T16:53:38.684889Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.001480Z digest=sha256:2899ba34a8879ae5a35353b5df4adfa83e2b9bbaaeebd1d6553505705379efdd

Observation d0a481fa-3b57-4ba4-82c4-ed0f4a3eded1 · outbound

This paper cites Maddison and Tatsunori Hashimoto , booktitle =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Maddison and Tatsunori Hashimoto , booktitle =

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:38.596732Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.015584Z digest=sha256:bfdb9429b74c40418678b32c54dd17d695cbe923cd02496844814b9b2df32a15

Observation 5bfc78cd-6447-4427-a0de-ecdd3c564fd8 · outbound

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

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Advances in Neural Information Processing Systems , volume=

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:38.577242Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.020646Z digest=sha256:5bfdf74f95917876b5326f892824e38263da01e997cb9cefd0129e92b10300af

Observation f5f61e88-f4cc-4e5b-a367-64bc0e4fa3d4 · outbound

This paper cites an unresolved cited work.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Unresolved cited work

Reference 4

Resolution
unresolved
raw_fallback, observed 2026-08-11T16:53:38.561656Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.026734Z digest=sha256:6a5b26d3aae9aca10ec2207c07cde3b4716c084dd3bdb82f1866b3371d70d5ed

Observation b9b156d9-3f57-4727-90ed-5bc2fc6969ff · outbound

This paper cites 2026 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2026 , url =

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:38.544794Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.031664Z digest=sha256:f07aa60c6a6f524d00a3a7d946e171b711d44d3343d2f94aed2372304f5ccb83

Observation 51abb43c-8294-4fe7-8c90-4a795ab746fa · outbound

This paper cites 2024 , doi =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2024 , doi =

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:38.528555Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.036917Z digest=sha256:ded10d79d7fed69b72afb5f1edd16cd3b349b30ef4a6b74b62a6c6b81ffe9929

Observation 3968e383-0668-4d9a-909b-bea4b40db5a9 · outbound

This paper cites 2024 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2024 , url =

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:38.472513Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.041942Z digest=sha256:0d6191d6b4d30560cb42ca1961231689f432b490080809bed914f162fbf0a33a

Observation f0265b3e-698d-4fb3-b601-b9582e55ae98 · outbound

This paper cites Zico Kolter and Nicolas Flammarion and Maksym Andriushchenko , booktitle =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Zico Kolter and Nicolas Flammarion and Maksym Andriushchenko , booktitle =

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:38.415803Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.046854Z digest=sha256:7687de116ab972935c325319dc488d37a6da07696f2b9d5cb0bd860ee1edc3d7

Observation 1be46a63-9d8f-404f-9121-087dd598fd80 · outbound

This paper cites 2025 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2025 , url =

Reference 9

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:38.399948Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.052416Z digest=sha256:e737618c63cb34bfee85fe4b4fa4980b1af9fd39114f4d1ee36442151507590a

Observation 5dda2272-0caf-4848-9a71-0992ee09dcb4 · outbound

This paper cites 2025 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2025 , url =

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:38.383041Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.057589Z digest=sha256:291b090673e3aebf57244224983702dc8ebc5b580fd997a22f6c984d274835f3

Observation 64c03d0b-dcdd-4d66-bdbb-d3c3aa399c0f · outbound

This paper cites Cartagena and M.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Cartagena and M

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:38.364484Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.063535Z digest=sha256:a77f8b4afa28336a59067d28efe29eca405010f8d02844144c8664813dedeaf4

Observation f8d598cd-2230-4ec6-a96f-fa9ef31999cc · outbound

This paper cites Gringras , year =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Gringras , year =

Reference 12

Resolution
parse uncertain
raw_fallback, observed 2026-08-11T16:53:38.323643Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.068380Z digest=sha256:eb47682c760f1b1a9147d0c9fc79d4f366691885eacbf079502cdc928357f75f

Observation 681a44bb-0559-4793-9d45-328b6d3f8f79 · outbound

This paper cites 2026 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2026 , url =

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:38.210537Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.075872Z digest=sha256:a2c0c61444c034dee5ef45de9948286e1c38f186f672f0a59b60932f137beb8a

Observation 37f75a8e-dcff-4a83-a9c5-43619afa672a · outbound

This paper cites 2026 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2026 , url =

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:38.194794Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.081445Z digest=sha256:5987f9418c67b3c7514f8586580d8cc05692f2257718949db6762364082bfc7a

Observation f9b9bb5d-5a18-4906-a6cc-59e82bffbb27 · outbound

This paper cites 2026 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2026 , url =

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:38.175798Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.087900Z digest=sha256:0f5c23850b3b60f9b7242cfefcddc98446c24605d459217b3fcee37bf8955273

Observation 0e1a0fbf-0519-45a0-9fa4-01f0f4329f0c · outbound

This paper cites 2026 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2026 , url =

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:38.154411Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.092857Z digest=sha256:e20ee7b53e9eea77f1a9c166df8f0c6f254c547ce143d2755e257a2861e51678

Observation 8208fb2d-7897-4e73-8802-da69dacc092b · outbound

This paper cites 2026 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2026 , url =

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:38.052822Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.097756Z digest=sha256:aa5778130e1725efaf27e126248b63f9a4c1da6889d191f6a8c1cb3975fbdf9f

Observation 7380bed0-ea89-445b-8d62-90f4e9e39261 · outbound

This paper cites Sun and Y.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Sun and Y

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:38.004905Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.110303Z digest=sha256:37a1038e35ea4f0582e5b61c1f121cb02a401a4f22a8f8039500c7fbad199b8d

Observation 617fc7d6-790b-4ccf-9469-2a8fc2c84e7b · outbound

This paper cites Choi and J.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Choi and J

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:37.988116Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.169860Z digest=sha256:af331dd7737ba858b511632a5d116666e5a7595af8d14be49c2c27eabbbbb46f

Observation 38c709f6-e0bd-4584-a0c8-7c32eddf8d85 · outbound

This paper cites Lee and B.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Lee and B

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:37.930621Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.204041Z digest=sha256:01d7ade4359b91ab0aa891580737c1c5179c02a080db791fdb21992063fa2dde

Observation e0f3edd2-5ae7-42dc-9b1e-493e64bc49e5 · outbound

This paper cites Zhu and Z.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Zhu and Z

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:37.856014Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.253734Z digest=sha256:03cc64e20c70e78450026b42df0436b05071b6980f329e8d04557de45ea58a84

Observation 1f95c9f9-d609-49c1-984d-3202d229b7ae · outbound

This paper cites Babu and R.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Babu and R

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:37.839200Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.301760Z digest=sha256:12090cbdd75102fd3bb5f1178d4b3858080db22bc8425e817f468f9aeed87d89

Observation a60a1392-19d0-4c39-ae5f-fb68c3fd5517 · outbound

This paper cites an unresolved cited work.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Unresolved cited work

Reference 23

Resolution
unresolved
raw_fallback, observed 2026-08-11T16:53:37.821383Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.305849Z digest=sha256:2b88df8a21109d6365bd32509d904f80cc707494b84b468f3ffe3c7e560e706e

Observation 2849010e-5b32-4a14-9893-de869aeecfc9 · outbound

This paper cites Xiong and D.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Xiong and D

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:37.717680Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.310816Z digest=sha256:1ddf07b15e4c061b84053313eb084eab0f3962536a9e728c6b9e623fae17d971

Observation 8a4001ea-89f6-450b-b75d-a05b3d5f2555 · outbound

This paper cites an unresolved cited work.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Unresolved cited work

Reference 25

Resolution
unresolved
raw_fallback, observed 2026-08-11T16:53:37.631107Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.315274Z digest=sha256:4aa9a0c37ab6cf308fff33b2a5efbb5bae8c454f55c117967ad7b1799b346349

Observation b226cfa0-1e30-4b5b-9af4-13249d908d73 · outbound

This paper cites an unresolved cited work.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Unresolved cited work

Reference 26

Resolution
unresolved
raw_fallback, observed 2026-08-11T16:53:37.615929Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.320272Z digest=sha256:1136eca8d837bbb14e6cbe1ff0d0f2b23b3bddd19e9b75ec32112107efc7bbad

Observation e07c4f6c-f192-4892-a064-c8c5f80b47da · outbound

This paper cites an unresolved cited work.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Unresolved cited work

Reference 27

Resolution
unresolved
raw_fallback, observed 2026-08-11T16:53:37.599801Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.324663Z digest=sha256:6b8f3f0e8d301efc82a90abd64f08ed70b5bcf316adef3bf68a794f4f2c5887e

Observation 571858ad-8983-466d-945a-5da12b20fe38 · outbound

This paper cites an unresolved cited work.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Unresolved cited work

Reference 28

Resolution
unresolved
raw_fallback, observed 2026-08-11T16:53:37.515005Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.329844Z digest=sha256:d8ae7ef0e158a740f1ad1df9082ae2ae2ace2e210f57ac0acc4a0430c0400442

Observation 5a37ba01-9633-402f-86c5-303db788b776 · outbound

This paper cites an unresolved cited work.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Unresolved cited work

Reference 29

Resolution
unresolved
raw_fallback, observed 2026-08-11T16:53:37.458267Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.334904Z digest=sha256:d191bb410be74ce773f1d3570e3edc464ff9c03204e3da5db1c7de3d29f85770

Observation 4c528645-c3e5-49b0-af47-235700c7d988 · outbound

This paper cites an unresolved cited work.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Unresolved cited work

Reference 30

Resolution
unresolved
raw_fallback, observed 2026-08-11T16:53:37.442503Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.341148Z digest=sha256:d3f006e7b5c07f56e5b4d216d59a62393ba79c06cf0a0693bf6658d9781f13b8

Observation 8e480803-8834-40f4-a79b-5847eb3ecc0b · outbound

This paper cites InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-11T16:53:34.346231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T16:53:34.346231Z digest=sha256:ca4862f02a073e2ce4f837bc8c1383d3a7894092025e55055380ec5fae947eb2

Observation baee685e-c6a5-470f-80c9-7710bd8740b8 · outbound

This paper cites 2025 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2025 , url =

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:37.425159Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.351295Z digest=sha256:fe7da1395e0bc2bbc64491e56f2c8af038f207041c8e541503365ec2f957e7cd

Observation ab66cf88-6d6c-4f01-9fc0-b5abb087594e · outbound

This paper cites Jimenez and John Yang and Alexander Wettig and Shunyu Yao and Kexin Pei and Ofir Press and Karthik Narasimhan , year =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Jimenez and John Yang and Alexander Wettig and Shunyu Yao and Kexin Pei and Ofir Press and Karthik Narasimhan , year =

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:37.338252Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.356085Z digest=sha256:e13b550f8d90dd171f4426c55610af2d4058805dea82b3bc31096b6271ed326b

Observation 7a958c3b-414e-4667-a905-24782ac26858 · outbound

This paper cites Xu and Hao Zhu and Xuhui Zhou and Robert Lo and Abishek Sridhar and Xianyi Cheng and Tianyue Ou and Yonatan Bisk and Daniel Fried and Uri Alon and Graham Neubig , year =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Xu and Hao Zhu and Xuhui Zhou and Robert Lo and Abishek Sridhar and Xianyi Cheng and Tianyue Ou and Yonatan Bisk and Daniel Fried and Uri Alon and Graham Neubig , year =

Reference 34

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:37.295916Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.361175Z digest=sha256:8888b903fc419c56c859708898da9aff2f999ff14241eb1b5a63c0c98c271705

Observation ac5476a9-2298-4700-8335-7f9e700848f3 · outbound

This paper cites Grabowski and Yuwei Song and Zhaowei Liu and Zhengyu Ma and Ethan Dyer and Pengcheng Yin and Diyi Yang and Chien-Sheng Wu and Sanmi Koyejo , year =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Grabowski and Yuwei Song and Zhaowei Liu and Zhengyu Ma and Ethan Dyer and Pengcheng Yin and Diyi Yang and Chien-Sheng Wu and Sanmi Koyejo , year =

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:37.280592Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.365641Z digest=sha256:4b0f8e2583ffc7b75e3b1d22a91f01c497b5eee5ee938c6c52a3ff442bce2f79

Observation 0375b00e-b033-4d5b-a80e-1a797888fb52 · outbound

This paper cites 2025 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2025 , url =

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:37.196547Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.371179Z digest=sha256:94e9e6009be2c092c09b375f3458e91e612801d89bc336f6eae1dbf4cf5c8f26

Observation bc20ae38-8ee9-4d5c-98f0-d100e19eef71 · outbound

This paper cites an unresolved cited work.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Unresolved cited work

Reference 37

Resolution
unresolved
raw_fallback, observed 2026-08-11T16:53:37.144637Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.376434Z digest=sha256:b49f4cc74ce06c2b37d501bbcaf140041d20f5eeecae85c21cb5efbee7a51ffd

Observation a7dfb7c5-7bf9-4dbb-a086-c22b93289a21 · outbound

This paper cites an unresolved cited work.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Unresolved cited work

Reference 38

Resolution
unresolved
raw_fallback, observed 2026-08-11T16:53:37.125342Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.394805Z digest=sha256:44aedf074f14ca8cf1a969f02538ede1022d25cb4561e98162f6d1dd41ec7c71

Observation 7ad92ef3-3c68-4d5d-be64-b025446d9e3f · outbound

This paper cites Luan and Linkang Du , journal =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Luan and Linkang Du , journal =

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:37.053779Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.464102Z digest=sha256:c2889669dbeb9e23c037c59f85c8c7d88f2ec5bc34b779e5effa45ff74ecd3b3

Observation 942ab63b-e595-42b6-a63f-dd99057b18e6 · outbound

This paper cites an unresolved cited work.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Unresolved cited work

Reference 40

Resolution
unresolved
raw_fallback, observed 2026-08-11T16:53:36.892001Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.505383Z digest=sha256:81db96898644a228ea334e1df95c7f2b6ba7906846ffa64b8973515db09a4de3

Observation 9ae7a332-7a11-4307-bda4-cb049fb8ae35 · outbound

This paper cites 2026 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2026 , url =

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:36.873853Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.553218Z digest=sha256:7ba0640ccf26566816a5c8a489affc7e2908420c8554a4277226f3ac424427b7

Observation 8142f752-39e5-4721-9937-da551ec65837 · outbound

This paper cites an unresolved cited work.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Unresolved cited work

Reference 42

Resolution
unresolved
raw_fallback, observed 2026-08-11T16:53:36.792743Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.572350Z digest=sha256:a63e6cd85f1ea598fe9168c4f594312f8607eba0a98e6394584554a10e63cf05

Observation 701b46b7-e602-4590-9d0d-7764eefec3e4 · outbound

This paper cites an unresolved cited work.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Unresolved cited work

Reference 43

Resolution
unresolved
raw_fallback, observed 2026-08-11T16:53:36.669558Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.577347Z digest=sha256:225c54c8ec470f64c9a9554a611af8c2ca557e7ad1fc519e74d0fc699082114e

Observation 5670cd8a-da6e-4c88-b1ad-9651fb6e6b96 · outbound

This paper cites 2026 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2026 , url =

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:36.557038Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.582423Z digest=sha256:22f1d6e657bc7bfedd2a1a5785c2d7fafa740680975e6384dbd0e7832fbdbe31

Observation 53722a94-b6fa-492a-8a35-af03dd64f832 · outbound

This paper cites 2025 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2025 , url =

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:36.477677Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.587688Z digest=sha256:e402e56997a5bb258b65e03675316d0f3489abfb51e243afe6cc30b2235d621b

Observation 4aeb5744-8401-4405-ab7e-321feafe126d · outbound

This paper cites Lampert , booktitle =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Lampert , booktitle =

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:36.461769Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.591878Z digest=sha256:54e9635353b776a852e97ce55d28d8ca24c34a5206371fa3fc7c07f353fc7c86

Observation 56dfd8ba-3a9e-4592-9529-3f16836ca011 · outbound

This paper cites 2025 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2025 , url =

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:36.446140Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.596625Z digest=sha256:0d525baf97943a0e26272a42f0e68c8e581632a19aae8a18d536fbadd15eba9e

Observation 801b47a5-229c-45dc-a1ee-65b051e9c4cf · outbound

This paper cites Xiang , booktitle =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Xiang , booktitle =

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:36.425419Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.601540Z digest=sha256:d727b3a289d60f778d826e70d33b2f2560fc3cbfd551ef14814342277b403a4e

Observation b6867042-0a8a-4f4a-89bf-86da26e8c274 · outbound

This paper cites 2026 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2026 , url =

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:36.377801Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.605782Z digest=sha256:6bce75986d41384d54b74cb0336bf489ad2c214566ddf5e4e52304649de1fc71

Observation c675c3c4-bb52-4cee-a1d6-81f964d78e65 · outbound

This paper cites Bradley Knox and Kimin Lee , booktitle =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Bradley Knox and Kimin Lee , booktitle =

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:36.165772Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.611006Z digest=sha256:f82b6bcd583462897572a547b28c5c8630733826a588edc141576130a7e4bf0b

Observation d8574246-a054-4983-97f1-d1241edc5103 · outbound

This paper cites 2025 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2025 , url =

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:36.149213Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.616464Z digest=sha256:4f734d053a502da2f9f2029c4e49ff77c3215fd869d66f17846461b45b8a9eea

Observation 6aac8c28-5d85-44db-9c6a-836e5200cbd5 · outbound

This paper cites 2025 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2025 , url =

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:36.101943Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.621388Z digest=sha256:919bcc6a938f8551be6bdac405700326857b673862dc842a262ae3ac7f479a62

Observation 7d04df4e-5382-40be-9fa5-9ba4c95f62a1 · outbound

This paper cites 2025 , doi =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2025 , doi =

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:35.942854Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.626669Z digest=sha256:210ddc942fe43b863d7f6a8c61062e696531e35a4d403dba5422867e8da74dee

Observation 48b2d750-8c29-4b13-8a2e-9eece9b940d5 · outbound

This paper cites 2025 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2025 , url =

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:35.855628Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.631588Z digest=sha256:4709fe52fda5bbbbbe469cff1858ea31179680c864611e01f3ef799ff5572ec3

Observation e1c093ba-fef8-4a62-bf37-f848b7f8cd9e · outbound

This paper cites 2026 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2026 , url =

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:35.614205Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.646956Z digest=sha256:b01478bd0114268182951c680c3a7c0e6583dc87e4dd44b7cc2293176d5a5a49

Observation 25d75d8e-365a-472f-b5b3-3105429879ce · outbound

This paper cites 2026 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2026 , url =

Reference 56

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:35.505734Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.700855Z digest=sha256:40570eae42cb6c04f7b320d5f2f76126f6c37f41946c1d232780d708d849015f

Observation 3d0407bb-158a-40e5-a072-9a57de83b695 · outbound

This paper cites an unresolved cited work.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Unresolved cited work

Reference 57

Resolution
parse uncertain
no resolver link, observed 2026-08-11T16:53:34.772080Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T16:53:34.772080Z digest=sha256:af27b8cd73cd003c2a09362e5443ead69db8161ea758b6ab1c2bbde4254e19a8

Observation 440f442e-d1ea-4507-b8ab-06801ce8b927 · outbound

This paper cites an unresolved cited work.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Unresolved cited work

Reference 58

Resolution
parse uncertain
no resolver link, observed 2026-08-11T16:53:34.828335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T16:53:34.828335Z digest=sha256:ba731d5657ae061374008e24dc613c3526d2302e3b7596b676120e15aa0d121f

Observation a020c6e5-f4f0-4072-bbe5-71c23c20a439 · outbound

This paper cites an unresolved cited work.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Unresolved cited work

Reference 59

Resolution
parse uncertain
no resolver link, observed 2026-08-11T16:53:34.866832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T16:53:34.866832Z digest=sha256:5dba29855f86220fadd45c5f5196e57dc3108aed5729e2812b7edc985b72b15e

Observation 5b48f926-0b4f-445d-8c00-5e2fbf9aa01b · outbound

This paper cites 2026 , url =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 2026 , url =

Reference 60

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:35.313262Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.893860Z digest=sha256:721d6da3f76efc784197cdbc62cdf334ca82727865d97abb32fb1c2a3210176d

Observation 4de1f442-fc7c-4c95-984f-66135e812eff · outbound

This paper cites an unresolved cited work.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Unresolved cited work

Reference 61

Resolution
parse uncertain
no resolver link, observed 2026-08-11T16:53:34.899135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T16:53:34.899135Z digest=sha256:0e8d4287db3f952f5b53e5e1d41074c3ce292bd50147c7e2e807b1c990be8017

Observation 4421ef4d-860d-4007-a1c6-ca40651e6518 · outbound

This paper cites AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-11T16:53:34.903981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T16:53:34.903981Z digest=sha256:9a1d1a5a036df0f96c68ac2edf7e1ba646f5f5af663c3315349a042411451f08

Observation 5d9f3bcc-db13-4471-a733-f87c5273351b · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-11T16:53:34.909310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T16:53:34.909310Z digest=sha256:6bf8a21db90c9242f52e45cb484e4510774e714751be78e06ee26e5c3a3af060

Observation d3658c12-51eb-4f67-a5d3-d83f82c080db · outbound

This paper cites Science China Information Sciences , volume=.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Science China Information Sciences , volume=

Reference 64

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:35.257342Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.914604Z digest=sha256:bd8c1a2fefefa7333fa8d34bd63b52f0175155a1876dfda9bd2b5d96be5e8602

Observation cd906d30-9ef6-45db-b9dd-80b2db91f6ce · outbound

This paper cites 35th USENIX Security Symposium (USENIX Security 26) , year =.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents 35th USENIX Security Symposium (USENIX Security 26) , year =

Reference 65

Resolution
verified fuzzy
raw_fallback, observed 2026-08-11T16:53:35.240557Z

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.

source=arxiv_source observed=2026-08-11T16:53:34.919197Z digest=sha256:9ba199d9cac2f75b4390777855b6c56f1290c5249429576aee643c01d4bc47db

Observation 0d49999b-5bce-4f24-bd81-9d4fbb3484a4 · outbound

This paper cites Quantifying Conversation Drift in MCP via Latent Polytope.

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents Quantifying Conversation Drift in MCP via Latent Polytope

Reference 66

Resolution
unresolved
no resolver link, observed 2026-08-11T16:53:35.001891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-11T16:53:35.001891Z digest=sha256:0976ba329ce5cf7f81dd5248474332457cd95568b5861376f44a160f625b7513

Pith citing papers

No inbound Pith citation observations are available.