Related papers: Act Wisely: Cultivating Meta-Cognitive Tool Use in…

Humans often acquire new skills through observation and imitation. For robotic agents, learning from the plethora of unlabeled video demonstration data available on the Internet necessitates imitating the expert without access to its…

Reinforcement learning has emerged as a paradigm for post-training large language models, boosting their reasoning capabilities. Such approaches compute an advantage value for each sample, reflecting better or worse performance than…

Metasurface inverse design has become central to realizing complex optical functionality, yet translating target responses into executable, solver-compatible workflows still demands specialized expertise in computational electromagnetics…

The role of reinforcement learning (RL) in enhancing the reasoning of large language models (LLMs) is becoming increasingly significant. Despite the success of RL in many scenarios, there are still many challenges in improving the reasoning…

Agentic artificial intelligence systems produce outputs through sequences of interdependent autonomous decisions, yet standard evaluation assesses outputs alone and cannot diagnose the underlying process. We develop a behavioral evaluation…

Recent advances in multimodal large reasoning models (MLRMs) have substantially improved their ability to solve complex textual and visual tasks. However, these models tend to overthink on simple problems, producing unnecessarily lengthy…

We present a controlled study of multi-hop contextual reasoning in large language models, providing a clean demonstration of the task-method dissociation: rule-based pattern matching achieves 100% success on structured information retrieval…

Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon actions where a single misstep, such as accessing files or entering credentials, can cause…

Self-evaluation, a model's ability to assess the correctness of its own output, is crucial for Large Multimodal Models (LMMs) to achieve self-improvement in multi-turn conversations, yet largely absent in foundation models. Recent work has…

Reinforcement learning for LLMs is vulnerable to reward hacking, where models exploit shortcuts to maximize reward without solving the intended task. We systematically study this phenomenon in coding tasks using an environment-manipulation…

Reinforcement learning algorithms require a large amount of samples; this often limits their real-world applications on even simple tasks. Such a challenge is more outstanding in multi-agent tasks, as each step of operation is more costly…

Conversational recommender systems (CRSs) operate under incremental preference revelation, requiring systems to make recommendation decisions under uncertainty. While recent approaches particularly those built on large language models…

Embodied navigation agents built upon large reasoning models (LRMs) can handle complex, multimodal environmental input and perform grounded reasoning per step to improve sequential decision-making for long-horizon tasks. However, a critical…

Online meta-learning is emerging as an enabling technique for achieving edge intelligence in the IoT ecosystem. Nevertheless, to learn a good meta-model for within-task fast adaptation, a single agent alone has to learn over many tasks, and…

We consider a sequential decision making problem where the agent faces the environment characterized by the stochastic discrete events and seeks an optimal intervention policy such that its long-term reward is maximized. This problem exists…

Automatic heuristic design (AHD) has emerged as a promising paradigm for solving NP-hard combinatorial optimization problems (COPs). Recent works show that large language models (LLMs), when integrated into well-designed frameworks (i.e.,…

Language models (LMs) are becoming increasingly dependent on external tools. LM-based agentic frameworks frequently interact with their environment via such tools to search files, run code, call APIs, etc. Further, modern reasoning-based…

Agentic methods have emerged as a powerful and autonomous paradigm that enhances reasoning, collaboration, and adaptive control, enabling systems to coordinate and independently solve complex tasks. We extend this paradigm to safety…

Large Language Models (LLMs) increasingly rely on Chain-of-Thought (CoT) reasoning to improve accuracy on complex tasks. However, always generating lengthy reasoning traces is inefficient, leading to excessive token usage and higher…

Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of existing methods is that they typically employ undifferentiated exploration strategies,…