Related papers: ReasoningBank: Scaling Agent Self-Evolving with Re…
While large language model (LLM) agents can effectively use external tools for complex real-world tasks, they require memory systems to leverage historical experiences. Current memory systems enable basic storage and retrieval but lack…
Agent memory shapes how Large Language Model (LLM)-powered agents, akin to the human brain, progressively refine themselves through environment interactions. Existing paradigms remain constrained: parametric memory forcibly adjusts model…
Augmented Reality (AR) systems are increasingly integrating foundation models, such as Multimodal Large Language Models (MLLMs), to provide more context-aware and adaptive user experiences. This integration has led to the development of AR…
Large language model (LLM) agents have evolved to intelligently process information, make decisions, and interact with users or tools. A key capability is the integration of long-term memory capabilities, enabling these agents to draw upon…
Most existing spatial reasoning benchmarks focus on static or globally observable environments, failing to capture the challenges of long-horizon reasoning and memory utilization under partial observability and dynamic changes. We introduce…
Complex reasoning in tool-augmented agent frameworks is inherently long-horizon, causing reasoning traces and transient tool artifacts to accumulate and strain the bounded working context of large language models. Without explicit memory…
Although numerous strategies have recently been proposed to enhance the autonomous interaction capabilities of multimodal agents in graphical user interface (GUI), their reliability remains limited when faced with complex or out-of-domain…
Autonomous agents powered by large language models (LLMs) have the potential to significantly enhance human productivity by reasoning, using tools, and executing complex tasks in diverse environments. However, current approaches to…
Large Reasoning Models (LRMs) like o3 and DeepSeek-R1 have achieved remarkable progress in reasoning tasks with long cot. However, they remain computationally inefficient and struggle with accuracy when solving problems requiring complex…
Agentic memory is emerging as a key enabler for large language models (LLM) to maintain continuity, personalization, and long-term context in extended user interactions, critical capabilities for deploying LLMs as truly interactive and…
Effective decision-making in the real world depends on memory that is both stable and adaptive: environments change over time, and agents must retain relevant information over long horizons while also updating or overwriting outdated…
While humans naturally learn and adapt from past experiences, large language models (LLMs) and their agentic counterparts struggle to retain reasoning from previous tasks and apply them in future contexts. To address this limitation, we…
Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks. With the paradigm shift toward self-evolving agentic learning, models are increasingly expected…
Revolutionary advancements in Large Language Models have drastically reshaped our interactions with artificial intelligence systems. Despite this, a notable hindrance remains-the deficiency of a long-term memory mechanism within these…
In this study, we propose a novel human-like memory architecture designed for enhancing the cognitive abilities of large language model based dialogue agents. Our proposed architecture enables agents to autonomously recall memories…
Existing methods for AI psychological counselors predominantly rely on supervised fine-tuning using static dialogue datasets. However, this contrasts with human experts, who continuously refine their proficiency through clinical practice…
Large language model (LLM)-powered agents are increasingly used in recommender systems (RSs) to achieve personalized behavior modeling, where the memory mechanism plays a pivotal role in enabling the agents to autonomously explore, learn…
Reasoning is a core capability of large language models, yet how multi-step reasoning is learned and executed remains unclear. We study this question in a controlled cellular-automata (1dCA) framework that excludes memorisation by using…
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,…
Multi-agent systems based on large language models, particularly centralized architectures, have recently shown strong potential for complex and knowledge-intensive tasks. However, central agents often suffer from unstable long-horizon…