CompanyAnthropic5 recent entries20 Apr 2026AISysRev -- LLM-based Tool for Title-abstract ScreeningarXiv:2510.06708v3 Announce Type: replace-cross Abstract: Conducting systematic reviews is laborious. In the screening or study selection phase, the number of papers can be overwhelming. Recent resear→13 May 2026Procedural-skill SFT across capacity tiers: A W-Shaped pre-SFT Trajectory and Regime-Asymmetric Mechanism on 0.8B-4B Qwen3.5 ModelsarXiv:2605.11907v1 Announce Type: new Abstract: We measure procedural-skill SFT contribution across three Qwen3.5 dense scales (0.8B, 2B, 4B) on a 200-task / 40-skill holdout, with Claude Haiku 4.5 as
CompanyOpenAI3 recent entries20 Apr 2026AISysRev -- LLM-based Tool for Title-abstract ScreeningarXiv:2510.06708v3 Announce Type: replace-cross Abstract: Conducting systematic reviews is laborious. In the screening or study selection phase, the number of papers can be overwhelming. Recent resear→2 Jun 2026Dynamic Coordination Strategy Selection for Enterprise Multi-Agent SystemsarXiv:2606.00804v1 Announce Type: cross Abstract: Enterprise multi-agent systems increasingly expose multiple coordination patterns, but deployments often lack evidence for when to use consensus, deba→14 Aug 2026CAPRI: Contract-Aware Proof Repair for IsabellearXiv:2608.13459v1 Announce Type: cross Abstract: We address the use of large language models (LLMs) to help discover Isabelle proofs. An Isabelle build establishes that the submitted theory is accept
CompanyGoogle2 recent entries20 Apr 2026AISysRev -- LLM-based Tool for Title-abstract ScreeningarXiv:2510.06708v3 Announce Type: replace-cross Abstract: Conducting systematic reviews is laborious. In the screening or study selection phase, the number of papers can be overwhelming. Recent resear→2 Oct 2026Scientific Agents: Evaluating Profession-Specific System Prompts on Scientific TasksarXiv:2610.00084v1 Announce Type: new Abstract: Detailed profession-specific system prompts raise token use and estimated cost per response without a consistent accuracy gain. We evaluate Scientific A
CompanyMistral1 recent entries20 Apr 2026AISysRev -- LLM-based Tool for Title-abstract ScreeningarXiv:2510.06708v3 Announce Type: replace-cross Abstract: Conducting systematic reviews is laborious. In the screening or study selection phase, the number of papers can be overwhelming. Recent resear
CompanyDeepSeek1 recent entries7 Jul 2026JavaVulBench: A Java Vulnerability Benchmark with Realistic Splits, a Unified Multi-Backend Harness, and a Leakage-Aware Evaluation ModearXiv:2607.02825v1 Announce Type: cross Abstract: We release extsc{JavaVulBench}, a benchmark dataset and evaluation harness for Java vulnerability detection. The dataset contains sim30{,}600 Java met