Related papers: HiMAC: Hierarchical Macro-Micro Learning for Long-…

Reinforcement Learning (RL) has proven highly effective at enhancing the complex reasoning abilities of Large Language Models (LLMs), yet underlying mechanisms driving this success remain largely opaque. Our analysis reveals that puzzling…

Large language model (LLM)-based agents have shown strong potential in multi-task scenarios, owing to their ability to transfer knowledge across diverse tasks. However, existing approaches often treat prior experiences and knowledge as…

The advancement of artificial intelligence toward agentic science is currently bottlenecked by the challenge of ultra-long-horizon autonomy, the ability to sustain strategic coherence and iterative correction over experimental cycles…

Understanding and replicating human mobility requires not only spatial-temporal accuracy but also an awareness of the cognitive hierarchy underlying real-world travel decisions. Traditional agent-based or deep learning models can reproduce…

Large language model (LLM) web agents are increasingly used for web navigation but remain far from human reliability on realistic, long-horizon tasks. Existing evaluations focus primarily on end-to-end success, offering limited insight into…

While Large Language Models (LLM) enable non-experts to specify open-world multi-robot tasks, the generated plans often lack kinematic feasibility and are not efficient, especially in long-horizon scenarios. Formal methods like Linear…

Training large language models (LLMs) to reason via reinforcement learning (RL) significantly improves their problem-solving capabilities. In agentic settings, existing methods like ReAct prompt LLMs to explicitly plan before every action;…

Hierarchical multi-agent systems based on large language models (LLMs) have become a common paradigm for building AI assistants in vertical domains such as e-commerce, where a master agent coordinates multiple specialized sub-agents.…

Agentic RAG is a powerful technique for incorporating external information that LLMs lack, enabling better problem solving and question answering. However, suboptimal search behaviors exist widely, such as over-search (retrieving…

While agent evaluation has shifted toward long-horizon tasks, most benchmarks still emphasize local, step-level reasoning rather than the global constrained optimization (e.g., time and financial budgets) that demands genuine planning…

Large Language Models (LLMs) have achieved remarkable advancements in natural language processing tasks, yet they encounter challenges in complex decision-making scenarios that require long-term reasoning and alignment with high-level…

A broad use case of large language models (LLMs) is in goal-directed decision-making tasks (or "agent" tasks), where an LLM needs to not just generate completions for a given prompt, but rather make intelligent decisions over a multi-turn…

Large Language Models (LLMs) have emerged as one of the most significant technological advancements in artificial intelligence in recent years. Their ability to understand, generate, and reason with natural language has transformed how we…

Achieving safe and coordinated behavior in dynamic, constraint-rich environments remains a major challenge for learning-based control. Pure end-to-end learning often suffers from poor sample efficiency and limited reliability, while…

Language model (LM)-based agents have demonstrated promising capabilities in automating complex tasks from natural language instructions, yet they continue to struggle with long-horizon planning and reasoning. To address this, we propose an…

We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents. Agentic Reasoning dynamically leverages web search, code execution, and structured memory to address…

Large Language Models (LLMs) have recently demonstrated impressive action sequence prediction capabilities but often struggle with dynamic, long-horizon tasks such as real-time strategic games. In a game such as StarCraftII (SC2), agents…

Hierarchical Reinforcement Learning (HRL) is well-suitedd for solving complex tasks by breaking them down into structured policies. However, HRL agents often struggle with efficient exploration and quick adaptation. To overcome these…

Collective learning can be greatly enhanced when agents effectively exchange knowledge with their peers. In particular, recent work studying agents that learn to teach other teammates has demonstrated that action advising accelerates…

Recent advancements in reinforcement learning have made significant impacts across various domains, yet they often struggle in complex multi-agent environments due to issues like algorithm instability, low sampling efficiency, and the…