Multi-session agents can switch between LLMs to balance performance and inference cost. Such switches require transferring a history for continuity, yet their effects on the recipient remain underexplored. Through controlled experiments with multi-session tasks, we uncover behavior transfer: recipients tend to adopt re...
Youngbin Choi, Sehyun Hwang, Suhyeon Jun et al.· 0 citations
This work introduces Function-Space Policy Optimization (FSPO), a single-policy framework that combines current privileged adaptation with function-space temporal consolidation, and introduces privileged disagreement correction to explicitly suppress locally overvalued actions.
Large language models (LLMs) hold broad knowledge in one set of weights, but lack interpretability and trustworthy reasoning, especially in high-stakes use cases. A neuro-symbolic model, with its interpretable architecture and System 2 reasoning capacity, is a promising alternative if built at the scale of LLMs; howeve...
Xiaocong Yang, Xuanyu Meng, Yuji Zhang et al.· 0 citations
This work reframe agentic trajectories as paths through a shared embedding space of actions and environmental observations, and introduces Precog-RM, a transformer-based model that meta-learns a representation in which outcome prediction can be performed in a few-shot setting.
Alexander Gill, Guram Gogia, F. Guzmán· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Transformers have demonstrated strong performance in long-term time series forecasting (LTSF), yet modeling non-stationary temporal dependencies remains challenging. In this paper, we interpret self-attention as a Bayesian posterior over attended positions, combining a content-based prior induced by scaled dot-product...
Xinjie Lan, Yunbo Mei, Leheng Zhou et al.· 0 citations
Temporal graph data are recorded in different representations, but whether these differences also determine the scope of learned knowledge reuse remains unclear. This study investigates whether predictive structure learned from relational histories can be reused between continuous-time dynamic graphs (CTDGs) and tempor...
Contrastive learning for time series depends on deciding which pairs of inputs should be treated as similar and dissimilar. Because few augmentations reliably preserve meaning in time series, prior methods have relied on two disjoint notions of similarity between windows: structural similarity, which relates windows wi...
Aditya Radhakrishnan, Maxwell A. Xu, Wanting Mao et al.· 0 citations
Expected-reward maximization in reinforcement learning concentrates probability mass on a few outcomes, even in tasks that require many distinct, high-quality solutions, a failure known as mode collapse. Inverse Probability Scaling (IPS) counters this in group-based policy gradients such as GRPO by dividing each reward...
Runtime policy verifiers can prevent agents from executing disallowed actions, but their decisions are typically used only for enforcement and discarded afterward. We ask whether these decisions can instead become verifiable policy rewards for training the agents they guard. We introduce Policy-Verified Self-Training (...
It is shown that even a three-token, single-layer attention-only transformer can fail to converge, and that, while each transformer has a temperature threshold, the supremum of this set is infinite, so there is no global minimal temperature that forces all transformers to converge.
Katy Blumer, Da-Cheng Juan, Jon M. Kleinberg et al.· 0 citations
On-policy distillation (OPD) provides dense token-level supervision on student rollouts, but this supervision can become unreliable when the student and teacher diverge, either because of a large initial policy gap or compounding errors in long-horizon reasoning and tool use. We introduce Divergence-Triggered Dynamic D...
Qi-Jia He, Ze-Qun Li, S.-S. Luo et al.· 0 citations
Modern machine learning models increasingly operate on variable-size structured data, such as sets and graphs. A central requirement is \emph{size generalization}: the ability of a model trained on inputs of one size to generalize to inputs of a different, potentially much larger, size. Classical statistical learning t...
