From 039319e53cb31c0c961ee8dae86e63989a5c8795 Mon Sep 17 00:00:00 2001 From: reacher-z Date: Tue, 28 Jul 2026 16:32:45 +0800 Subject: [PATCH] Add ClawBench paper entry --- resources/Autonomous_Agents_Research_Papers_2026_2.md | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/resources/Autonomous_Agents_Research_Papers_2026_2.md b/resources/Autonomous_Agents_Research_Papers_2026_2.md index 2e62b95a..360c0903 100644 --- a/resources/Autonomous_Agents_Research_Papers_2026_2.md +++ b/resources/Autonomous_Agents_Research_Papers_2026_2.md @@ -53,6 +53,17 @@ Chronological order. +#### 9th April 2026 + +[ClawBench: Can AI Agents Complete Everyday Online Tasks?](http://arxiv.org/abs/2604.08523) + +- ClawBench: introduces an evaluation framework for AI browser agents with 153 everyday tasks spanning 144 live websites across 15 categories. +- The benchmark runs agents in isolated containers and safely intercepts final submission requests while recording session replay, screenshots, HTTP traffic, browser actions, and agent messages for traceable evaluation. +- [Project page](https://claw-bench.com) · [GitHub repository](https://github.com/TIGER-AI-Lab/ClawBench) + +--- + + #### 8th April 2026 [Rhizome OS-1: Rhizome’s Semi-Autonomous Operating System for Small Molecule Drug Discovery](http://arxiv.org/abs/2604.07512)