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 • 24
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling Paper • 2606.18023 • Published Jun 16 • 211
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 • 20
Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code Paper • 2606.11817 • Published Jun 10 • 18
Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code Paper • 2606.11817 • Published Jun 10 • 18
DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt Paper • 2506.09353 • Published Nov 16, 2025