ScaleVLA: Scaling Vision-Language-Action Models to 552 Billion Parameters Paper • 2611.21607 • Published 2 days ago • 43
CoACT: Action-Preserving Observation Compression for Coding Agents Paper • 2607.02911 • Published Jul 3
Environmental Injection Attacks against GUI Agents in Realistic Dynamic Environments Paper • 2509.11250 • Published Jan 31 • 1
SWE-Touch: Benchmarking Coding Agents When Users Touch the Code Paper • 2608.02499 • Published Aug 3 • 20
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling Paper • 2606.18023 • Published Jun 16 • 151
Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code Paper • 2606.11817 • Published Jun 10 • 18 • 5
Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code Paper • 2606.11817 • Published Jun 10 • 18 • 5
UCoder: Unsupervised Code Generation by Internal Probing of Large Language Models Paper • 2512.17385 • Published Dec 19, 2025 • 19