| 2026-11-19 | 2611.26590 | Probing the "Conscious" Mind: Selective Access and Global Workspace in Vision-Language Models | Jiahao Huang et al. | arXiv | 40 | |
| 2026-11-11 | W4410835161 | Non-halogen aqueous electrolytes for four-electron iodine conversion | Guanjie He et al. | Nature | |  |
| 2026-11-03 | 2611.01460 | Can Large Language Model Agents Learn by Watching Tutorial Videos? | Haoyu Zhao et al. | arXiv | 5 | |
| 2026-11-02 | W3210772527 | Anterior cingulate neurons perform parallel processing of fixated and peripheral information to guide information sampling and choice | James L. Butler et al. | Nature Communications | | |
| 2026-10-27 | 2610.34238 | Δτ-Bench: Pushing Agents Toward a Moving Capability | Shuofei Qiao et al. | arXiv | 24 | |
| 2026-10-25 | 2610.33956 | Continual Learning Exam: Benchmarking Long-Horizon RSI and Experiential Learning in LLM Agents | Haoyu Zhao et al. | arXiv | 54 | |
| 2026-10-14 | W7221752215 | Revisiting the Claim for a Direct-collapse Black Hole in UHZ1 at z = 10.05 | Fan Zou et al. | The Astrophysical Journal | | |
| 2026-10-09 | 2610.11794 | Memento 3: Model-Based Recursive Self-Improvement through Reflective Rulebooks | Haoyu Zhao et al. | arXiv | 43 | |
| 2026-09-22 | 2609.11063 | The information geometry of large language models is shared, learned, and controllable | Dario Picozzi | arXiv | 6 | |