NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
81 results for “keyword:"computer use agents"” in ICLR 2027. 12 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]AlphaCUA: Scaling Safety Benchmarks for Computer-Use Agents by Discovering and Validating Risk Factors▼4.3k2.00
[PDF]Neuro-Symbolic Computer Use: Learning Reusable Policies for Reliable and Efficient Execution▼4.5k2.67
[PDF]From Clues to Closure: Benchmarking Ultra-Long-Horizon Autonomous Computer Use through Evidence-Driven Gameplay▼4.3k2.00
[PDF]How Agents Reach the Record Matters: A Parity-Controlled Study of Access Modality for Clinical EHR Agents▼1351.33
[PDF]Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps▲6.1k2.00
[PDF]Closing the Specialization Gap between Computer Use Benchmark Scores and the Real World Performance▼1351.33
[PDF]ScienceCUA: Resource-to-Skill Construction and Execution-Guided Skill Evolution for Scientific Computer Use Agents▼4.5k2.67
[PDF]PhotoArena: Benchmarking Pure-GUI Computer-Use Agents in Adobe Photoshop via Dual-Track Verification▼4.3k2.00
[PDF]PhysicianUIBench: Benchmarking Computer-Use Agents through a High-Fidelity EHR Interface▼4.5k2.25
[PDF]Hybrid Computer Use: A Unified Programmatic, Semantic, and Visual Interface for General Agents▲3.0k2.50
[PDF]CaptchaArena: A Large-Scale, Fine-Grained Dataset for Training Computer-Use Agents on Interactive CAPTCHAs▲5103.00
Withdrawn or desk rejected (12)
[PDF]ClickShield: A Firewall for Multimodal Computer-use Agents Against Dual Prompt InjectionWithdrawn1.67
[PDF]AsyPO: Asymmetric Post-Training for GUI Agents with Segment-Level Reasoning GuidanceWithdrawn1.67