From 19bf5917090a3843f650d295518ec75f0876035b Mon Sep 17 00:00:00 2001 From: genitrix Date: Tue, 28 Jul 2026 21:15:48 +0800 Subject: [PATCH 1/2] docs: add related ClawBench benchmark --- README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/README.md b/README.md index 515e87d..ec1ae45 100644 --- a/README.md +++ b/README.md @@ -54,6 +54,10 @@ Current research primarily focuses on "deep" tasks. DeepSearch tackles the "I ca In sharp contrast, WideSearch tackles the "I could do it, but the sheer volume is overwhelming" problem. It requires agents to systematically find and organize large-scale information into a structured output, shifting the primary challenge from deep search to achieving exhaustiveness and fidelity at scale. +### Related Web-Agent Benchmark + +[ClawBench](https://github.com/TIGER-AI-Lab/ClawBench) is a complementary benchmark for evaluating agents on long-horizon, real-world browser tasks across live websites. It emphasizes end-to-end execution, browser actions, network traces, screenshots, and rubric-based evaluation, providing a useful contrast to WideSearch's broad information-seeking focus. See the [project homepage](https://claw-bench.com/) and [paper](https://arxiv.org/abs/2504.08523) for details. + ## Experiments We test both single-agent and multi-agent modes, and manually conducted end-to-end testing of the commercial AI system on the web interface. In addition, we randomly select 20 questions and invited human annotators to perform tests. The experiment results are as follows: ![experiments](figs/image.png) From 7a8b5a0b2b4240e23e3e007e12f5153082ffdf02 Mon Sep 17 00:00:00 2001 From: genitrix Date: Tue, 28 Jul 2026 21:16:48 +0800 Subject: [PATCH 2/2] fix: use canonical ClawBench paper link --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index ec1ae45..46a0e04 100644 --- a/README.md +++ b/README.md @@ -56,7 +56,7 @@ In sharp contrast, WideSearch tackles the "I could do it, but the sheer volume i ### Related Web-Agent Benchmark -[ClawBench](https://github.com/TIGER-AI-Lab/ClawBench) is a complementary benchmark for evaluating agents on long-horizon, real-world browser tasks across live websites. It emphasizes end-to-end execution, browser actions, network traces, screenshots, and rubric-based evaluation, providing a useful contrast to WideSearch's broad information-seeking focus. See the [project homepage](https://claw-bench.com/) and [paper](https://arxiv.org/abs/2504.08523) for details. +[ClawBench](https://github.com/TIGER-AI-Lab/ClawBench) is a complementary benchmark for evaluating agents on long-horizon, real-world browser tasks across live websites. It emphasizes end-to-end execution, browser actions, network traces, screenshots, and rubric-based evaluation, providing a useful contrast to WideSearch's broad information-seeking focus. See the [project homepage](https://claw-bench.com/) and [paper](https://arxiv.org/abs/2604.08523) for details. ## Experiments We test both single-agent and multi-agent modes, and manually conducted end-to-end testing of the commercial AI system on the web interface. In addition, we randomly select 20 questions and invited human annotators to perform tests. The experiment results are as follows: