UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks | Paper Citation Record

Observation 6c75db65-7fa2-475a-abdf-7006fb8313d4 · outbound

This paper cites Pinchbench: Real-world benchmarks for ai coding agents.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Pinchbench: Real-world benchmarks for ai coding agents

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.511408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5e5f8c88-32f2-4d34-bf13-8d8979a9c982 · outbound

This paper cites Kimi k2.6: From code to creation, from one to many.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Kimi k2.6: From code to creation, from one to many

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.507307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0bb5bc2e-f13f-48ac-badb-261131da8509 · outbound

This paper cites Introducing claude opus 4.6.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Introducing claude opus 4.6

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.508998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a52ac535-84b3-4e8c-a8a8-66ce8e111aac · outbound

This paper cites Introducing claude sonnet 4.6.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Introducing claude sonnet 4.6

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.512359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c6e42378-8fa1-46d0-8deb-cbb284dd9225 · outbound

This paper cites Openclaw web-search skill.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Openclaw web-search skill

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.510676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 590bc953-51e7-4ead-8d9c-1a14212dc839 · outbound

This paper cites Openclaw edict.https://github.com/cft0808/edict, 2026.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Openclaw edict.https://github.com/cft0808/edict, 2026

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.526187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3b08ba97-47b8-4841-83d9-bfda3ce3592f · outbound

This paper cites Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:46:41.278763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b7abcdf7-07d1-46a9-9376-5fe73ec7d829 · outbound

This paper cites The BrowserGym Ecosystem for Web Agent Research.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks The BrowserGym Ecosystem for Web Agent Research

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T01:46:41.292086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation dbc15a0b-2770-4f50-99bf-26b7e77e8135 · outbound

This paper cites Duckduckgo search openclaw.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Duckduckgo search openclaw

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.537106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c12c19bd-84b0-4c53-a253-b9545d878bb7 · outbound

This paper cites WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:46:41.276240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e1cf27cf-a589-4779-baa2-70fd2da715ed · outbound

This paper cites Codeplot-cot: Mathematical visual reasoning by thinking with code-driven images.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Codeplot-cot: Mathematical visual reasoning by thinking with code-driven images

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.619052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a8f243cf-6b9e-4b5d-a013-d4545731e5d2 · outbound

This paper cites Gemini 3 flash.https://deepmind.google/models/gemini/flash/, 2025.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Gemini 3 flash.https://deepmind.google/models/gemini/flash/, 2025

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.600321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3875fa8b-1d8e-4f31-b1e1-7ad060fb0da2 · outbound

This paper cites Gemini 3.1 flash lite.https://deepmind.google/models/gemini/flash-lite/, 2026.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Gemini 3.1 flash lite.https://deepmind.google/models/gemini/flash-lite/, 2026

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.587147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 777fafe2-86a2-4a9d-9360-851717c64472 · outbound

This paper cites Gemini 3.1 pro.https://deepmind.google/models/gemini/pro/, 2026.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Gemini 3.1 pro.https://deepmind.google/models/gemini/pro/, 2026

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.594892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3140aba7-6b33-454b-a273-775ddead7673 · outbound

This paper cites Cogagent: A visual language model for gui agents.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Cogagent: A visual language model for gui agents

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.602275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9f4a6df9-a7da-477a-8229-8f46438296ae · outbound

This paper cites Macagentbench: Benchmark agents where they actually work — on macos.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Macagentbench: Benchmark agents where they actually work — on macos

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.592673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 32f20998-78e7-4833-be58-7e4c0726c600 · outbound

This paper cites Visualwebarena: Evaluating multimodal agents on realistic visual web tasks.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Visualwebarena: Evaluating multimodal agents on realistic visual web tasks

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.604342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8ec9c0f7-193f-464d-a93b-adc3a35dabcf · outbound

This paper cites Agent browser openclaw.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Agent browser openclaw

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.623013Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3d8541db-d079-4165-90d2-abedb1557172 · outbound

This paper cites SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:46:41.268069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4060cc8f-298b-47dc-a826-a7fd2f91b190 · outbound

This paper cites AgentBench: Evaluating LLMs as Agents.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks AgentBench: Evaluating LLMs as Agents

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:46:41.265553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e52b6e80-b94c-45d9-8f6b-2b2fd603de01 · outbound

This paper cites LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks LiveClawBench: Benchmarking LLM Agents on Complex, Real-World Assistant Tasks

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:46:41.281407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f8374b79-244e-4155-b7b0-50598ad4fe97 · outbound

This paper cites Agentboard: An analytical evaluation board of multi-turn llm agents.Advances in neural information processing systems, 37:74325–74362.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Agentboard: An analytical evaluation board of multi-turn llm agents.Advances in neural information processing systems, 37:74325–74362

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.555822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5b6b4aeb-a57d-4c56-84ca-395eee9bd5d2 · outbound

This paper cites SkillClaw: Let Skills Evolve Collectively with Agentic Evolver.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks SkillClaw: Let Skills Evolve Collectively with Agentic Evolver

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:46:41.263069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6115dd1a-a17d-40f5-8398-9a1a16594027 · outbound

This paper cites Desktop control openclaw.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Desktop control openclaw

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.557817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation eade2889-5875-4bbc-859a-1e97167440ab · outbound

This paper cites ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:46:41.270682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 31120ae4-d8b3-4418-ac90-c34b1b819fcc · outbound

This paper cites Gaia: a benchmark for general ai assistants.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Gaia: a benchmark for general ai assistants

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.561797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 132fa747-b504-4874-8b9c-603606db00e1 · outbound

This paper cites Hermes agent: An agent that grows with you.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Hermes agent: An agent that grows with you

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.565323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4193270e-6905-4c75-a0af-b7f4ffe03966 · outbound

This paper cites Introducing gpt-4.1 in the api.https://openai.com/index/gpt-4-1/.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Introducing gpt-4.1 in the api.https://openai.com/index/gpt-4-1/

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.567597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a5034a0b-d1bf-4446-b644-8e1f4e875121 · outbound

This paper cites Introducing gpt-5.4.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Introducing gpt-5.4

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.544799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 23de0ac2-4aff-4a5e-a226-fd52de0e06fd · outbound

This paper cites Introducing gpt-5.4 mini and nano.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Introducing gpt-5.4 mini and nano

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.569416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 69b72fb5-e2e9-4bf1-a579-f580c9b95296 · outbound

This paper cites ART: Automatic multi-step reasoning and tool-use for large language models.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks ART: Automatic multi-step reasoning and tool-use for large language models

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:46:41.281240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation dd6d8b69-96d9-4fe2-a4b4-aa2cb8575943 · outbound

This paper cites TALM: Tool Augmented Language Models.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks TALM: Tool Augmented Language Models

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:46:41.283601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3a4f3bda-f0cc-45dc-95c4-7eac4e18ffee · outbound

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

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:46:41.289461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8ccae9c2-8b01-43d7-a3d7-40e38bb3e834 · outbound

This paper cites AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:46:41.308819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e109df51-6418-4e54-8095-0d69f4a7e2e6 · outbound

This paper cites Nanobot: The ultra-lightweight personal ai agent.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Nanobot: The ultra-lightweight personal ai agent

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.611383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e8e7db00-0875-4da1-82c5-07b1c3513ca1 · outbound

This paper cites Toolformer: Language models can teach themselves to use tools.Advances in neural information processing systems, 36: 68539–68551.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Toolformer: Language models can teach themselves to use tools.Advances in neural information processing systems, 36: 68539–68551

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.617293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9ba879b3-5ff9-4824-b6c0-06a13a1cf769 · outbound

This paper cites Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face.Advances in Neural Information Processing Systems, 36:38154–38180.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face.Advances in Neural Information Processing Systems, 36:38154–38180

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.621345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7b5a12df-b1db-42bc-ab4f-d375e240e020 · outbound

This paper cites Reflexion: Language agents with verbal reinforcement learning.Advances in neural information processing systems, 36:8634–8652.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Reflexion: Language agents with verbal reinforcement learning.Advances in neural information processing systems, 36:8634–8652

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.613328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a44b9f56-5c29-48a3-8905-d17cd65ad30b · outbound

This paper cites Openclaw.https://github.com/openclaw/openclaw, 2025.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Openclaw.https://github.com/openclaw/openclaw, 2025

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.594604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f146a63c-e274-41f0-aff1-c9df45192dc2 · outbound

This paper cites Qwen3.5-Omni Technical Report.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Qwen3.5-Omni Technical Report

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:46:41.297163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6f8d1d88-c712-495a-a00a-445ecbe775db · outbound

This paper cites From assistant to double agent: Formalizing and benchmarking attacks on OpenClaw for personalized local AI agent.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks From assistant to double agent: Formalizing and benchmarking attacks on OpenClaw for personalized local AI agent

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-07-10T01:46:41.300025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 101dd469-3a5c-4952-847f-bd48e84aac94 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Chain-of-thought prompting elicits reasoning in large language models

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.596364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 44eeddb9-e227-4cf0-9c73-55cd0b02d98c · outbound

This paper cites Intelligent agents: Theory and practice.The knowledge engineering review, 10(2):115–152.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Intelligent agents: Theory and practice.The knowledge engineering review, 10(2):115–152

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.598482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c2004007-2095-4485-bf92-bcd7a853cbdf · outbound

This paper cites Metaclaw: Just talk–an agent that meta-learns and evolves in the wild.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Metaclaw: Just talk–an agent that meta-learns and evolves in the wild

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-07-10T01:46:41.289460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation eb67096b-0957-4e38-acbb-839d0b40cb49 · outbound

This paper cites Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments.Advances in Neural Information Processing Systems, 37:52040–52094.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments.Advances in Neural Information Processing Systems, 37:52040–52094

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.602498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 564ec014-cbcf-44b5-8908-7a5e74eb577a · outbound

This paper cites TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:46:41.306236Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1bd81118-61fd-4dc2-b119-0c22a15550c2 · outbound

This paper cites MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action

Reference 47

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:46:41.294757Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 608d9d32-0a63-478a-b4c0-ad640297fad4 · outbound

This paper cites React: Synergizing reasoning and acting in language models.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks React: Synergizing reasoning and acting in language models

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.600044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bbdf3c80-57ef-4372-8541-1520e89b8f76 · outbound

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

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

Reference 49

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:46:41.271151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 910fb33c-8da5-4d85-aede-bbea6563372f · outbound

This paper cites Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:46:41.278931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 117fa3a6-179a-472e-90a1-f63767464268 · outbound

This paper cites Appagent: Multimodal agents as smartphone users.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Appagent: Multimodal agents as smartphone users

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.575188Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0f998663-473f-4ec5-9072-19fa3d96ce85 · outbound

This paper cites ClawBench: Can AI Agents Complete Everyday Online Tasks?.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks ClawBench: Can AI Agents Complete Everyday Online Tasks?

Reference 52

Resolution: verified exact; local_arxiv, observed 2026-07-10T01:46:41.303337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4fcd13aa-bf9d-48cd-a05f-0fe6200f4998 · outbound

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

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks WebArena: A Realistic Web Environment for Building Autonomous Agents

Reference 53

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T01:46:41.260658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7c5c15e3-cd75-4fbc-bce9-2c9064ee3fa5 · outbound

This paper cites an unresolved cited work.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Unresolved cited work

Reference 54

Resolution: unresolved; raw_fallback, observed 2026-07-10T02:06:42.581046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 15b0f5f7-0578-4d11-b649-e2c9649c9dae · outbound

This paper cites an unresolved cited work.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Unresolved cited work

Reference 55

Resolution: unresolved; raw_fallback, observed 2026-07-10T02:06:42.582963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 039ceaf8-1e2f-45dd-b0be-c3bd739d3388 · outbound

This paper cites draw the chart, compare it with the original, then revise.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks draw the chart, compare it with the original, then revise

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.590768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 47175f3d-8b84-47b2-8adb-0ade9f2a3aa5 · outbound

This paper cites an unresolved cited work.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Unresolved cited work

Reference 57

Resolution: unresolved; raw_fallback, observed 2026-07-10T02:06:42.588817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 99b7afe3-6a5e-4ae0-adc0-1e24ecfbad58 · outbound

This paper cites an unresolved cited work.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Unresolved cited work

Reference 58

Resolution: unresolved; raw_fallback, observed 2026-07-10T02:06:42.606031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fb6427ec-5041-4602-b259-13466066a9e1 · outbound

This paper cites an unresolved cited work.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Unresolved cited work

Reference 59

Resolution: unresolved; raw_fallback, observed 2026-07-10T02:06:42.575942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6db9b2c6-0cb3-4d99-bf11-26893eceb094 · outbound

This paper cites an unresolved cited work.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Unresolved cited work

Reference 60

Resolution: unresolved; raw_fallback, observed 2026-07-10T02:06:42.565609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4e09c213-a100-4345-8b6f-dd515a25be54 · outbound

This paper cites If a single screenshot cannot fit both, save an additional supplemental screenshot for the same artwork and mark that clearly in the filename or notes.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks If a single screenshot cannot fit both, save an additional supplemental screenshot for the same artwork and mark that clearly in the filename or notes

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.561630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 41257383-2bec-4324-a968-2dd77f3f558c · outbound

This paper cites an unresolved cited work.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Unresolved cited work

Reference 62

Resolution: unresolved; raw_fallback, observed 2026-07-10T02:06:42.550924Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c725f40c-62a1-4fca-8d9c-64e5afa1245d · outbound

This paper cites an unresolved cited work.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Unresolved cited work

Reference 63

Resolution: unresolved; raw_fallback, observed 2026-07-10T02:06:42.547178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5b4959b6-8f2e-4ec9-b6a9-0d36af619937 · outbound

This paper cites an unresolved cited work.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Unresolved cited work

Reference 64

Resolution: unresolved; raw_fallback, observed 2026-07-10T02:06:42.518733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4c4f8707-01db-4c75-9304-693d942e30df · outbound

This paper cites The title must include `Rust Global: Tokyo`.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks The title must include `Rust Global: Tokyo`

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.612229Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 541c0032-91f1-49ea-9bd8-5f8fe5aad012 · outbound

This paper cites an unresolved cited work.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Unresolved cited work

Reference 66

Resolution: unresolved; raw_fallback, observed 2026-07-10T02:06:42.557519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d69fed6b-c5f9-4a9e-b353-37429e9257a0 · outbound

This paper cites an unresolved cited work.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-07-10T02:06:42.538813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4b00de40-ef5d-471f-8be9-664dec6ca316 · outbound

This paper cites An ICS import preview, a screen where no calendar has been selected, or a dialog where import/save has not been clicked does not count as a created event.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks An ICS import preview, a screen where no calendar has been selected, or a dialog where import/save has not been clicked does not count as a created event

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.563489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ff4c3b34-8b7a-4349-9177-f9dcf2f1f927 · outbound

This paper cites Record the calendar application used, event title, start/end time, timezone, venue, registration link, and evidence file paths.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Record the calendar application used, event title, start/end time, timezone, venue, registration link, and evidence file paths

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.597673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 35478cb7-e60a-4814-97ea-99fb26d5eb98 · outbound

This paper cites Available Images.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Available Images

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.571205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 0f646519-a7c1-47ef-b6aa-be4435c210bd · outbound

This paper cites an unresolved cited work.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Unresolved cited work

Reference 71

Resolution: unresolved; raw_fallback, observed 2026-07-10T02:06:42.615190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 889b95a1-e0ae-46ff-9e05-fefdfe75cda8 · outbound

This paper cites an unresolved cited work.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Unresolved cited work

Reference 72

Resolution: unresolved; raw_fallback, observed 2026-07-10T02:06:42.530037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6980910e-4299-4a7c-b7ee-0ec65b24d42b · outbound

This paper cites could be more thorough.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks could be more thorough

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.531746Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4748ebd5-3f18-47b0-b6a1-0488db74c865 · outbound

This paper cites an unresolved cited work.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Unresolved cited work

Reference 74

Resolution: unresolved; raw_fallback, observed 2026-07-10T02:06:42.535469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9118fe76-f7e1-4b25-9879-fb85c0d7393d · outbound

This paper cites an unresolved cited work.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Unresolved cited work

Reference 75

Resolution: unresolved; raw_fallback, observed 2026-07-10T02:06:42.528172Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 23b65796-e30f-4da1-85a2-089a29880450 · outbound

This paper cites an unresolved cited work.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Unresolved cited work

Reference 76

Resolution: unresolved; raw_fallback, observed 2026-07-10T02:06:42.522549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7f11fd08-e904-4376-9311-a2f651548a23 · outbound

This paper cites an unresolved cited work.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Unresolved cited work

Reference 77

Resolution: unresolved; raw_fallback, observed 2026-07-10T02:06:42.524366Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8eb27709-4fd5-41ef-9305-c5adacff5b04 · outbound

This paper cites Now let me research the LOC API to understand how to find items with clear rights and accessible images.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Now let me research the LOC API to understand how to find items with clear rights and accessible images

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.520711Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fdc6f7fd-a875-4d4d-99a2-20e111748664 · outbound

This paper cites Cycle 1 has the right pipeline and the right data; only the selection rigor and the exclusion-file consistency are insufficient.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Cycle 1 has the right pipeline and the right data; only the selection rigor and the exclusion-file consistency are insufficient

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.516466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 958a5f1d-7180-48d7-93a4-562ed717ed6e · outbound

This paper cites Hidden judging assets are never mounted into the user simulator’s workspace, and a deterministic rewriter further sanitizes the simulator’s candidate text.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks Hidden judging assets are never mounted into the user simulator’s workspace, and a deterministic rewriter further sanitizes the simulator’s candidate text

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.533698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 60910144-a8b9-470e-8e4f-26fa6f2bb1dd · outbound

This paper cites UniClawBench scores reflect both the model’s first-pass and its recovery capabilities.

UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks UniClawBench scores reflect both the model’s first-pass and its recovery capabilities

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T02:06:42.514373Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers