arXiv Artificial IntelligenceSAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?
arXiv:2609.09113v1 Announce Type: new Abstract: While research on recursive self-improvement (RSI) has…
Curated from international AI laboratories, specialist publications and technology outlets. Last update: 3 hours ago.
arXiv Artificial IntelligencearXiv:2609.09113v1 Announce Type: new Abstract: While research on recursive self-improvement (RSI) has…
arXiv Artificial IntelligencearXiv:2609.09094v1 Announce Type: new Abstract: Combining search with function approximation has driven major…
arXiv Artificial IntelligencearXiv:2609.09081v1 Announce Type: new Abstract: Mid-training, the stage between pre-training and alignment…
arXiv Artificial IntelligencearXiv:2609.09056v1 Announce Type: new Abstract: Modern science and engineering increasingly rely on…
arXiv Artificial IntelligencearXiv:2609.09030v1 Announce Type: new Abstract: Chain-of-thought reasoning provides a structured computation…
arXiv Artificial IntelligencearXiv:2609.09001v1 Announce Type: new Abstract: Multi-step LLM reasoning lacks a machine-recheckable ledger…
arXiv Artificial IntelligencearXiv:2609.08966v1 Announce Type: new Abstract: Language-model checkpoints are commonly selected by…
arXiv Artificial IntelligencearXiv:2609.08965v1 Announce Type: new Abstract: Ensuring the safety of autonomous driving is a critical…
arXiv Artificial IntelligencearXiv:2609.08944v1 Announce Type: new Abstract: Agent skills provide a lightweight way to equip frozen…
arXiv Artificial IntelligencearXiv:2609.08861v1 Announce Type: new Abstract: Benchmark scores are a central currency in model releases…
arXiv Artificial IntelligencearXiv:2609.08832v1 Announce Type: new Abstract: Large language model (LLM)-powered agents can be accurate on…
arXiv Artificial IntelligencearXiv:2609.08772v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly being…