Related papers: MemEvolve: Meta-Evolution of Agent Memory Systems

Large Language Model (LLM) agents have demonstrated remarkable proficiency in learned tasks, yet they often struggle to adapt to non-stationary environments with feedback. While In-Context Learning and external memory offer some…

Existing Large Language Models (LLMs) usually remain static after deployment, which might make it hard to inject new knowledge into the model. We aim to build models containing a considerable portion of self-updatable parameters, enabling…

Large language models are increasingly expected to serve as general-purpose agents that interact with external, stateful tool environments. The Model Context Protocol (MCP) and broader agent skills offer a unified interface for connecting…

Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool…

Recent advances in vision-language navigation (VLN) were mainly attributed to emerging large language models (LLMs). These methods exhibited excellent generalization capabilities in instruction understanding and task reasoning. However,…

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…

Large language models (LLMs) have made significant advances in the field of natural language processing, but they still face challenges such as continuous decision-making, lack of long-term memory, and limited context windows in dynamic…

LLM agents increasingly rely on memory mechanisms to reuse knowledge from past problem-solving experiences. However, existing methods typically construct memory for a single agent and reuse it with the same underlying model, tightly…

Embodied agents are expected to operate persistently in dynamic physical environments, continuously acquiring new capabilities over time. Existing approaches to improving agent performance often rely on modifying the agent itself -- through…

Large language model (LLM) agents accumulate rich episodic trajectories while solving real-world tasks, but it remains unclear whether such experience can be distilled into reusable procedural skills. We introduce SkillEvolBench, a…

Recently, large language model based (LLM-based) agents have been widely applied across various fields. As a critical part, their memory capabilities have captured significant interest from both industrial and academic communities. Despite…

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…

Many real-world systems, such as transportation systems, ecological systems, and Internet systems, are complex systems. As an important tool for studying complex systems, computational experiments can map them into artificial society models…

Large Language Models (LLMs) have shown strong potential as conversational agents. Yet, their effectiveness remains limited by deficiencies in robust long-term memory, particularly in complex, long-term web-based services such as online…

Large language models hold promise as scientific assistants, yet existing agents either rely solely on algorithm evolution or on deep research in isolation, both of which face critical limitations. Pure algorithm evolution, as in…

Optimizing large-scale machine learning systems, such as recommendation models for global video platforms, requires navigating a massive hyperparameter search space and, more critically, designing sophisticated optimizers, architectures,…

Self-evolving large language model (LLM) agents continually improve by accumulating and reusing past experience, yet it remains unclear whether they faithfully rely on that experience to guide their behavior. We present the first systematic…

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…

The exploration of whether agents can align with their environment without relying on human-labeled data presents an intriguing research topic. Drawing inspiration from the alignment process observed in intelligent organisms, where…

A central challenge in building continually improving agents is that training environments are typically static or manually constructed. This restricts continual learning and generalization beyond the training distribution. We address this…