The Signal

Everything that matters in AI, with our take.

Updated through the day. Every headline links straight to the source. The two lines underneath are ours.

research1156 agents716 infra561 labs317 culture268 capital253 regulation233 claude175 openai149 safety103 security89 evaluation77 reasoning61 alignment52 benchmarks50 interpretability48

arXiv cs.CLPaper8d ago

PlannerForge: LLM Agents for Scenario-Based Testing of Motion Planners in Autonomous Driving

LLMs are now being applied to the full ADS testing pipeline, which is useful but still feels like a research project. The utility depends on how often teams actually use this versus point tools. For autonomous driving builders, it's worth a trial run, but it's not a foundational shift yet.

agents research autonomous-driving testing

arXiv cs.CLPaper13d ago

Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs

Test case quality is a real bottleneck in code generation evals, and automating it is useful. The two-stage approach, where the model first generates sound tests and then generates adversarial counterexamples, is sensible. But this is incremental: it improves pass@1 on existing benchmarks rather than unlocking new capability. Read if you're working on code LLMs or building eval infrastructure; otherwise, it's a solid research contribution that doesn't change what you build.

research code-generation testing