Related papers: Investigate-Consolidate-Exploit: A General Strateg…
Artificial Intelligence (AI) is accelerating the transformation of scientific research paradigms, not only enhancing research efficiency but also driving innovation. We introduce InternAgent, a unified closed-loop multi-agent framework to…
We propose a federated learning-like framework, Federation over Text (FoT), that enables multiple clients solving different tasks to collectively generate a shared library of metacognitive insights by iteratively federating their local…
Progress in scientific discovery is rarely the result of a single "Eureka" moment, but is rather the product of hundreds of scientists incrementally working together toward a common goal. While existing agent workflows are capable of…
Self-evolution is indispensable to realize full autonomous driving. This paper presents a self-evolving decision-making system based on the Integrated Decision and Control (IDC), an advanced framework built on reinforcement learning (RL).…
Achieving high efficiency on AI operators demands precise control over computation and data movement. However, existing scheduling languages are locked into specific compiler ecosystems, preventing fair comparison, reuse, and evaluation…
Large language models (LLMs) are increasingly deployed in teams, yet existing coordination approaches often occupy two extremes. Highly structured methods rely on fixed roles, pipelines, or task decompositions assigned a priori. In…
The evolution of Retrieval-Augmented Generation (RAG) has shifted from static retrieval pipelines to dynamic, agentic workflows where a central planner orchestrates multi-turn reasoning. However, existing paradigms face a critical…
This technical white paper introduces the Interactive Agents Call Tree (IACT), a computational model designed to address the limitations of static, hard-coded agent workflows. Unlike traditional systems that require pre-defined graphs or…
In the rapidly evolving field of artificial intelligence, the ability to harness and integrate knowledge across various domains stands as a paramount challenge and opportunity. This study introduces a novel approach to cross-domain…
We introduce the Discrete Inverse Continuity Equation (DICE) method, a generative modeling approach that learns the evolution of a stochastic process from given sample populations at a finite number of time points. Models learned with DICE…
LLM-based autonomous agents have demonstrated strong capabilities in reasoning, planning, and tool use, yet remain limited when tasks require sustained coordination across roles, tools, and environments. Multi-agent systems address this…
The dominant paradigm for improving mathematical reasoning in language models relies on Reinforcement Learning with verifiable rewards. Yet existing methods treat each problem instance in isolation without leveraging the reusable strategies…
This paper introduces a novel method for closed information extraction. The method employs a discriminative approach that incorporates type and entity-specific information to improve relation extraction accuracy, particularly benefiting…
Self-consistency-based approaches, which involve repeatedly sampling multiple outputs and selecting the most consistent one as the final response, prove to be remarkably effective in improving the factual accuracy of large language models.…
Edge-cloud collaborative computing (ECCC) has emerged as a pivotal paradigm for addressing the computational demands of modern intelligent applications, integrating cloud resources with edge devices to enable efficient, low-latency…
Scientific discovery is being revolutionized by AI and autonomous systems, yet current autonomous laboratories remain isolated islands unable to collaborate across institutions. We present the Autonomous Interconnected Science Lab Ecosystem…
In active sequential testing, also termed pure exploration, a learner is tasked with the goal to adaptively acquire information so as to identify an unknown ground-truth hypothesis with as few queries as possible. This problem, originally…
Exploring unknown environments efficiently is a fundamental challenge in unsupervised goal-conditioned reinforcement learning. While selecting exploratory goals at the frontier of previously explored states is an effective strategy, the…
Imitation learning has shown success in many tasks by learning from expert demonstrations. However, most existing work relies on large-scale demonstrations from technical professionals and close monitoring of the training process. These are…
Inner interpretability is a promising field aiming to uncover the internal mechanisms of AI systems through scalable, automated methods. While significant research has been conducted on large language models, limited attention has been paid…