LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use Agents
LEASH escalates computer-use agents by latent uncertainty, matching Claude Opus 5 at 19% lower cost.
52
Product
OSWorld
- Mentions · 7d0
- Mentions · 30d2
- All mentions8
- First seenSep 4, 2026
- Last mentioned16d ago
Timeline
8 articles · newest firstSoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments
SoftwareGym's 182 synthetic apps lift a computer-use agent to 56.97% OSWorld Pass@3.
54
ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents
ComputerSD turns real-time GUI feedback into online self-distillation signals for computer-use agents.
42
OSWorld-Pro: Process-based Evaluation for Computer Use Agents
OSWorld-Pro adds process-level subgoals so computer-use agent failures can be diagnosed beyond final outcomes.
48
OSWorld-Pro: Process-based Evaluation for Computer Use Agents
OSWorld-Pro scores computer-use agents on over 300 tasks; Claude Opus 5 reaches 75.7%.
52
Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents
EvoSkill-GUI introduces training-free skill revision for GUI agents, boosting MobileWorld, AndroidWorld, and OSWorld success by up to 16.2%.
30
UC Berkeley Researchers Release CUA-Lite, an Open Platform Unifying Sandboxes, Data, Evaluation and RL for Computer-Use Agents
UC Berkeley's CUA-Lite is an open platform unifying computer-use agent sandboxes, datasets, evaluation and RL; Lite.OSWorld cuts OSWorld memory 4.1 GB to 0.9 GB.
45
CUA-Universe: A Scalable and Dynamic Environment for Hybrid GUI+CLI Agents
Researchers introduce CUA-Universe, a pipeline turning real desktop software into hybrid GUI+CLI agent environments, lifting a 9B model's OSWorld success rate.
38
Appears with
- Claude Opus 5ai model · 3
- OSWorld-Proproduct · 2
- Lite.OSWorldproduct · 1
- OSWorld-MCPproduct · 1
- Anthropicvendor · 1
- Qwen3-VL-2B-Instructai model · 1
- Qwen3.5-35B-A3Bai model · 1
- UC Berkeleyorganization · 1
- SoftwareGymproduct · 1
- AndroidWorldproduct · 1
- CUA-Liteproduct · 1
- Fara-7Bai model · 1
- UI-TARSai model · 1
- MobileWorldproduct · 1
- UC Berkeleyvendor · 1
- EvoCUA-8Bai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.