Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Software Eng.×1AI×1HCI×1Crypto×1NLP×1
Frequent co-authors
Research Timeline
2026
Behavioral Canaries: Auditing Private Retrieved Context Usage in RL Fine-Tuning
The paper introduces Behavioral Canaries, a novel auditing mechanism that detects unauthorized use of private retrieved context data during Reinforcement Learning Fine-Tuning (RLFT) by inducing detectable stylistic behavioral changes.
How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World Sessions
This study analyzes over 20,000 real-world coding sessions to show that AI coding agents frequently fail users through subtle misalignment, requiring constant manual correction even when major system damage is avoided.
Highlighted terms show continued research focus across papers