Tracked topic
…Using only 0.05% of the EditReward preference data, RewardHarness achieves 47.4% average accuracy on image-editing evaluation benchmarks, surpassing GPT-5 by 5.3 points. When used as a reward…
…Extensive evaluations on 20 LLMs across 7 families (including frontier models such as GPT-5.4, Gemini-3.1-Pro, and Claude-Opus-4.7) demonstrate unsatisfactory performance, with scores below 60…
…On SCOUT-450 , a safety-oriented operating point reduces attack-success rate by 46% and total wall-clock by 40% relative to an always-on GPT-4o judge , at a 5.1…
…Fine-tuning a 4-billion-parameter LLM on BioTool yields substantial improvements in biomedical tool-calling performance, outperforming cutting-edge commercial LLMs such as GPT-5.1. Furthermore, human expert evaluations demonstrate…
…An 8B model trained with DCRL hits 70.5 F1 and beats GPT-5-mini on ReasonMatch-Bench—nice evidence that geometric supervision + RL can unlock spatial reasoning without CoT labels. This…
…safety-critical details into longer final answers; and (iv) safety-violation rates reshuffle the leaderboard -- GPT-5.4 climbs from rank 6 to rank 3 after SV adjustment, while Kimi-k2.5…
…Across AFTraj-2K and an external Who\&When benchmark, AgentForesight-7B outperforms leading proprietary models, including GPT-4.1 and DeepSeek-V4-Pro , achieving up to +19.9% performance gain and 3times…
…On five tasks under a shared GPT-5.5 backbone, AI CFD Scientist autonomously discovers a Spalart-Allmaras runtime correction that reduces lower-wall Cf RMSE against DNS by 7.89% on…
…On interleaved generation benchmarks, it achieves performance comparable to Nano Banana and GPT-5. Surprisingly, it also significantly enhances the base model on reasoning-based benchmarks; for example, on 4-step FLUX…
…In pairwise speaker-listener experiments with GPT-OSS-120b and Qwen3.5, we show these languages can be learned in-context from a short description alone, with oversight-evasion grammars no harder…