Current AI agents can flexibly invoke tools and execute complex tasks, yet their long-term advancement is hindered by the lack of systematic accumulation and transfer of skills. Without a unified mechanism for skill consolidation, agents frequently ``reinvent the wheel'', rediscovering solutions in isolated contexts without leveraging prior strategies. To address this challenge, we introduce SkillNet, an open infrastructure for creating, evaluating, and organizing AI skills at scale. SkillNet structures skills within a unified ontology that supports creating skills from heterogeneous sources, establishing rich relational connections, and performing multi-dimensional evaluation across Safety, Completeness, Executability, Maintainability, and Cost-awareness. Our infrastructure integrates a repository of over 600,000 skills, an interactive platform, and a versatile Python toolkit. Experiments on ALFWorld, WebShop, and ScienceWorld show 40% higher average rewards and 30% fewer execution steps across multiple backbone models. Furthermore, SkillNet-Gym benchmarks skill retrieval, utilization, and composition, while SkillNet-Fabric enables task-specific skill routing through lightweight Wikis. By formalizing skills as evolving, composable assets, SkillNet provides a robust foundation for agents to move from transient experience to durable mastery.
Yuan Liang, Ruobin Zhong, Haoming Xu et al.· 0 citations
An agent must try new behaviors to explore and improve. In high-stakes environments, an agent that violates safety constraints may cause harm and must be taken offline, curtailing any future interaction. Imitating old behavior is safe, but excessive conservatism discourages exploration. How much behavior change is too much? We show how to use any safe reference policy as a probabilistic regulator for any optimized but untested policy. Conformal calibration on data from the safe policy determines how aggressively the new policy can act, while provably enforcing the user's declared risk tolerance. Unlike conservative optimization methods, we do not assume the user has identified the correct model class nor tuned any hyperparameters. Unlike previous conformal methods, our theory provides finite-sample guarantees even for non-monotonic bounded loss functions, and it introduces a new policy control setting. Our experiments on applications ranging from natural language question answering to biomolecular engineering show that safe exploration is not only possible from the first moment of deployment, but can also improve performance.
Drew Prinster, Clara Fannjiang, Ji Won Park et al.· 0 citations
Group-relative residual calibration can incorporate verifier outcomes without discarding dense token-level guidance, and demonstrates that group-relative residual calibration can incorporate verifier outcomes without discarding dense token-level guidance.
Zhu Zhang, Ji-Xun Wang, Xiaoan Xu et al.· 1 citation
A recourse method is built on a gradient-boosted ensemble that retains 58% of its validity where the strongest baseline retains 41%, a distinction the standard evaluation cannot see because it never asks whether a recommendation can be carried out.
Emanuele Luzio· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
PGFS++ is introduced, a synthesis-aware reinforcement learning framework for input-specific molecular improvement that improves target properties while preserving high output diversity, and experiments show that PGFS++ improves target properties while preserving high output diversity.
Boqiao Zhang, Godbless James, S. Gottipati et al.· 0 citations
The Masked Diffusion Time-series Imputation Model (MDTIM) is proposed, which leverages the training paradigm of masked diffusion model for imputation tasks, and introduces Stochastic Discretization, which maps continuous values to ordinal-aware tokens while preserving continuous dynamics.
Dongbin Kim, Seungyun Lee, Geonwoo Shin et al.· 0 citations
Open-MOPD, a principled framework incorporating token-share balancing, gap-aware dynamic budget allocation, and student reward refresh, systematically restore cross-domain balance, elevating headroom recovery from 35.6% to 83.4% in a single deployable student.
Huan Gao, Haohan Chi, Yong Yan et al.· 0 citations
We introduce Bernstein-Vazirani Networks (BVNs), a non-variational quantum machine learning framework that leverages quantum interference for supervised learning, demonstrated on vision and representation learning tasks. In their standard form, BVNs follow the principle of quantum Fourier sampling: labelled data are placed in superposition and interfered in the Fourier basis to extract globally informative features. We then define generalised BVNs that enable interference in problem-adapted bases, yielding more expressive models under the same measurement budget as in the standard setting. BVNs achieve universal function approximation through (over)complete interference bases, while training of BVNs is gradient-free. Experiments on synthetic and real-world classification tasks, as well as implicit image representation, show strong generalisation capabilities and competitive performance with classical and quantum baselines.
Harness Continual Learning is formulated, a new continual learning paradigm in which the harness evolves around a frozen foundation model, and the resulting loss of earlier behavior as harness-level forgetting is defined.
Borui Kang, Jinrui Gu, Junhan Lv et al.· 0 citations
This work introduces Top-K prompting as a robust training and inference paradigm to better capture diverse, plausible reaction predictions and establishes Top-K, plausibility-aware training as a practical new direction for robust future LLM-based synthesis planning.
B. Zagribelnyy, Ivan D. Ilin, N. Bondarev et al.· 1 citation
A graphical notation for designing interpretable AI architectures, adapted from Penrose tensor notation is introduced, which gives a global view of an architecture and maps one to one onto PyTorch einsum code.
The proposed Module Level Reward Evolution Framework integrates three mechanisms: reflection-based refinement, hybrid credit assignment, and a merge strategy with rollback, which together improve the effectiveness and robustness of reward optimization.
Chenglin Liu, Xun Wang, Ruishuo Chen et al.· 0 citations
A weeklong summer workshop brought higher education faculty to campus to explore how AI and machine learning materials can be adapted for their classrooms.
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
MIT News · Artificial Intelligence· news.mit.eduAug 24, 2026
