Progress in AI is often measured by what a single model can do on its own. Yet teams of AI agents are starting to make breakthroughs and discoveries in science, medicine, mathematics and software engineering. As AI begins to work in teams of agents and people, the ability to collaborate becomes a core part of their int...
Sean Wu, Aneesh Pappu, Jiaru Zou et al.· 0 citations
On-policy distillation (OPD) is emerging as an important paradigm for language-model post-training, combining dense teacher supervision with training on student-generated trajectories. This creates a feedback loop where each update changes the student and thereby the training distribution that generates subsequent upda...
Guan-Zhe Hong, S. Motwani, Liang-Qiang Chen et al.· 0 citations
Large language models (LLMs) are increasingly used to discover scientific equations from experimental data. Such a discovery system has two parts that must work together: a library of executable computational tools and the model's tool-use policy. The tools supply the solving capability, from diagnosing structure in th...
Peng-Ze Li, Jia-Quan Zhang, En-Cheng Su et al.· 0 citations
This work constructs TypewriterCorpus, a 54B-token historical corpus with extensive temporal filtering, proposes lexically grounded instruction tuning that constrains all responses to vocabulary from historical source documents, and introduces History-Event, a benchmark of 2,344 events for evaluating both competence an...
Xiaoxi Luo, Zachary Shinnick, Niclas Griesshaber et al.· 4 citations
This work proposes $D^2-Monitor, in which a lightweight probe runs on every sample, producing a base prediction and a hesitation estimate that decides whether to escalate the sample to a more expressive probe, and exhibits the best trade-off between effectiveness and efficiency relative to 8 baselines.
Ao Liu, Yu-Peng Chen, James Oldfield et al.· 1 citation
Whether unlearning runs exhibit exploitable structure in weight space is investigated, and it is observed that models from different runs still lie in a shared evaluation-performance basin, suggesting that stronger models may be recovered through an unlearning-tailored soup strategy, reducing the need for repeated tuni...
Using controlled corruption, this work decouple these two roles and finds a reversal: making a noisy token easier to predict reduces its damage as a target but increases it as context.
Su-Qin Yuan, Runqi Lin, Ke-Yu Lin et al.· 0 citations
Autoresearch agents are reshaping the research ecosystem, but they can also let flawed claims enter the literature at scale. Human advisors catch such issues in drafts through careful, traceable feedback, yet advisor-style assessment requires extensive manual effort and does not scale. To shift automated paper assessme...
Research Attention Prediction (RAP), a rolling benchmark covering 278 AI/ML fields and 1,390 episodes, is introduced, a rolling benchmark covering 278 AI/ML fields and 1,390 episodes for large language models to track shifts in research attention.
Ying-Qian Wu, Jingcong Liang, Si-Yuan Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.