arXiv:2512.01485v1 Announce Type: cross Abstract: Chain-of-Thought (CoT) reasoning has significantly advanced the problem-solving capabilities of Large Language Models (LLMs), yet conventional CoT often exhibits internal determinism during decoding, limiting exploration of plausible alternatives. Recent methods attempt to address this by…
arXiv:2512.00311v1 Announce Type: new Abstract: Knowledge Tracing (KT) aims to model student’s knowledge state and predict future performance to enable personalized learning in Intelligent Tutoring Systems. However, traditional KT methods face fundamental limitations in explainability, as they rely solely on…
arXiv:2512.01809v1 Announce Type: cross Abstract: Generative models, like flows and diffusions, have recently emerged as popular and efficacious policy parameterizations in robotics. There has been much speculation as to the factors underlying their successes, ranging from capturing multi-modal action distribution…
arXiv:2512.00321v1 Announce Type: new Abstract: Power consumption has become a critical aspect of modern life due to the consistent reliance on technological advancements. Reducing power consumption or following power usage predictions can lead to lower monthly costs and improved electrical…
arXiv:2305.19659v5 Announce Type: replace Abstract: Subgraph counting is a fundamental task for analyzing structural patterns in graph-structured data, with important applications in domains such as computational biology and social network analysis, where recurring motifs reveal functional and organizational properties. In…
arXiv:2512.00342v1 Announce Type: new Abstract: Real-world intelligence systems usually operate by combining offline learning and online adaptation with highly correlated and non-stationary system data or signals, which, however, has rarely been investigated theoretically in the literature. This paper initiates a…
arXiv:2501.03840v4 Announce Type: replace Abstract: Artificial intelligence and machine learning applications in archaeology have increased significantly in recent years, and these now span all subfields, geographical regions, and time periods. The prevalence and success of these applications have remained largely…
arXiv:2512.00351v1 Announce Type: new Abstract: The thriving field of multi-agent reinforcement learning (MARL) studies how a group of interacting agents make decisions autonomously in a shared dynamic environment. Existing theoretical studies in this area suffer from at least two of…
arXiv:2505.17989v4 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has been an effective approach for improving Large Language Models’ reasoning in domains such as coding and mathematics. Here, we apply RLVR methods towards forecasting future real-world events –…
arXiv:2512.00352v1 Announce Type: new Abstract: Multi-agent reinforcement learning (MARL), as a thriving field, explores how multiple agents independently make decisions in a shared dynamic environment. Due to environmental uncertainties, policies in MARL must remain robust to tackle the sim-to-real gap.…
