Related papers: Compiled Memory: Not More Information, but More Pr…
Most prior works on communication in multi-agent reinforcement learning have focused on emergent communication, which often results in inefficient and non-interpretable systems. Inspired by the role of language in natural intelligence, we…
While end-to-end neural conversation models have led to promising advances in reducing hand-crafted features and errors induced by the traditional complex system architecture, they typically require an enormous amount of data due to the…
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…
With the growing adoption of Large Language Model (LLM) agents in persistent, real-world roles, they naturally encounter continuous streams of tasks and inevitable failures. A key limitation, however, is their inability to systematically…
Conversational agents struggle to handle long conversations due to context window limitations. Therefore, memory systems are developed to leverage essential historical information. Existing memory systems typically follow a pipeline of…
We study how to endow GUI agents with scalable memory that help generalize across unfamiliar interfaces and long-horizon tasks. Prior GUI agents compress past trajectories into text tokens, which balloons context length and misses decisive…
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…
Vision-language models (VLMs) have shown remarkable general capabilities, yet embodied agents built on them fail at complex tasks, often skipping critical steps, proposing invalid actions, and repeating mistakes. These failures arise from a…
Retrieval-Augmented Generation remains the dominant pattern for giving LLMs persistent memory, but a visible cluster of personal wiki-style memory architectures emerged in April 2026 -- design proposals from Karpathy, MemPalace, and LLM…
With the rapid development of large language models, AI assistants like ChatGPT have become increasingly integrated into people's works and lives but are limited in personalized services. In this paper, we present a plug-and-play framework…
Large language models show promise for financial decision-making, yet deploying them as autonomous trading agents raises fundamental challenges: how to adapt instructions when rewards arrive late and obscured by market noise, how to…
AI agents are increasingly used in long, multi-turn workflows in both research and enterprise settings. As interactions grow, agent behavior often degrades due to loss of constraint focus, error accumulation, and memory-induced drift. This…
Learning how to do things from trial and error in real time is a hallmark of biological intelligence, yet most LLM-based agents lack mechanisms to acquire procedural knowledge after deployment. We propose Procedural Recall for Agents with…
Although speech emotion recognition (SER) has advanced significantly with deep learning, annotation remains a major hurdle. Human annotation is not only costly but also subject to inconsistencies annotators often have different preferences…
In order for large language models to achieve true conversational continuity and benefit from experiential learning, they need memory. While research has focused on the development of complex memory systems, it remains unclear which types…
While knowledge distillation has become a mature field for compressing large language models (LLMs) into smaller ones by aligning their outputs or internal representations, the distillation of LLM-based agents, which involve planning,…
Large language models (LLMs) have evolved into agentic systems capable of autonomous tool use and multi-step reasoning for complex problem-solving. However, post-training approaches building upon general-purpose foundation models…
The evolution of next-Generation (xG) wireless networks marks a paradigm shift from connectivity-centric architectures to Artificial Intelligence (AI)-native designs that tightly integrate data, computing, and communication. Yet existing AI…
Although data-free incremental learning methods are memory-friendly, accurately estimating and counteracting representation shifts is challenging in the absence of historical data. This paper addresses this thorny problem by proposing a…
Large Language Model (LLM) agents struggle with long-horizon software engineering tasks due to "Context Bloat." As interaction history grows, computational costs explode, latency increases, and reasoning capabilities degrade due to…