Related papers: M$^\star$: Every Task Deserves Its Own Memory Harn…
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…
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change over time, and agents must retain relevant information over long horizons while also updating or overwriting outdated…
Building models of natural language processing (NLP) is challenging in low-resource scenarios where only limited data are available. Optimization-based meta-learning algorithms achieve promising results in low-resource scenarios by adapting…
Memory emerges as the core module in the Large Language Model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game playing, scientific discovery), where memory can enable knowledge accumulation, iterative…
Large Language Models (LLMs) show promise in code generation tasks. However, their code-writing abilities are often limited in scope: while they can successfully implement simple functions, they struggle with more complex tasks. A…
The STAR architecture was designed to test the value of the full Selective Tuning model of visual attention for complex real-world visuospatial tasks and behaviors. However, knowledge of how humans solve such tasks in 3D as active observers…
Large Reasoning Models (LRMs) face two fundamental limitations: excessive token consumption when overanalyzing simple information processing tasks, and inability to access up-to-date knowledge beyond their training data. We introduce MARS…
Multi-agent systems perform well on general reasoning tasks. However, the lack of training in specialized areas hinders their accuracy. Current training methods train a unified large language model (LLM) for all agents in the system. This…
LLM-powered embodied agents have shown success on conventional object-rearrangement tasks, but providing personalized assistance that leverages user-specific knowledge from past interactions presents new challenges. We investigate these…
Search is a key service within constraint programming systems, and it demands the restoration of previously accessed states during the exploration of a search tree. Restoration proceeds either bottom-up within the tree to roll back…
Large Language Model (LLM)-based agents have recently shown impressive capabilities in complex reasoning and tool use via multi-step interactions with their environments. While these agents have the potential to tackle complicated tasks,…
Self-reflection enables language agents to iteratively refine solutions, yet often produces repetitive outputs that limit reasoning performance. Recent studies have attempted to address this limitation through various approaches, among…
Memory systems are widely adopted to enhance LLMs for long-horizon tasks, and are commonly organized as multi-agent pipelines with memory building, summarizing, and retrieval agents. To empower this system, existing RL-based methods either…
Recent advances in language model (LM) agents and function calling have enabled autonomous, feedback-driven systems to solve problems across various digital domains. To better understand the unique limitations of LM agents, we introduce…
Multi-agent systems built on Large Language Models (LLMs) show exceptional promise for complex collaborative problem-solving, yet they face fundamental challenges stemming from context window limitations that impair memory consistency, role…
Digital collectible card games are not only a growing part of the video game industry, but also an interesting research area for the field of computational intelligence. This game genre allows researchers to deal with hidden information,…
Statefulness is essential for large language model (LLM) agents to perform long-term planning and problem-solving. This makes memory a critical component, yet its management and evolution remain largely underexplored. Existing evaluations…
Large language models (LLMs) are transforming web search by shifting from document ranking to synthesizing answers, and are increasingly deployed as autonomous agentic search systems that iteratively interact with external knowledge…
A common challenge for most current recommender systems is the cold-start problem. Due to the lack of user-item interactions, the fine-tuned recommender systems are unable to handle situations with new users or new items. Recently, some…
As Large Language Models (LLMs) are increasingly used for long-duration tasks, maintaining effective long-term memory has become a critical challenge. Current methods often face a trade-off between cost and accuracy. Simple storage methods…