Related papers: EvoMem: Improving Multi-Agent Planning with Dual-E…

LLM agents operating under organizational policies must comply with authorization constraints typically specified in natural language. In practice, such specifications inevitably contain ambiguities and logical or semantic gaps that cause…

To support long-term interaction in complex environments, LLM agents require memory systems that manage historical experiences. Existing approaches either retain full interaction histories via passive context extension, leading to…

Autonomous Vehicles (AVs) have entered the commercialization stage, but their limited ability to interact and express intentions still poses challenges in interactions with Human-driven Vehicles (HVs). Recent advances in large language…

LLM-based conversational AI agents struggle to maintain coherent behavior over long horizons due to limited context. While RAG-based approaches are increasingly adopted to overcome this limitation by storing interactions in external memory…

Deep reinforcement learning algorithms have recently been used to train multiple interacting agents in a centralised manner whilst keeping their execution decentralised. When the agents can only acquire partial observations and are faced…

Enterprise AI deploys dozens of autonomous agent nodes across workflows, each acting on the same entities with no shared memory and no common governance. We identify five structural challenges arising from this memory governance gap: memory…

As LLM agents evolve into collaborative multi-agent systems, their memory requirements grow rapidly in complexity. This position paper frames multi-agent memory as a computer architecture problem. We distinguish shared and distributed…

In drug discovery, molecular optimization aims to iteratively refine a lead compound to improve molecular properties while preserving structural similarity to the original molecule. However, each oracle evaluation is expensive, making…

Recent advancements in large language models (LLMs) have enabled LLM-based agents to successfully tackle interactive planning tasks. However, despite their successes, existing approaches often suffer from planning hallucinations and require…

External memory systems are pivotal for enabling Large Language Model (LLM) agents to maintain persistent knowledge and perform long-horizon decision-making. Existing paradigms typically follow a two-stage process: computationally expensive…

Long-horizon language agents must operate under limited runtime memory, yet existing memory mechanisms often organize experience around descriptive criteria such as relevance, salience, or summary quality. For an agent, however, memory is…

This study proposes a multi-agent language framework that enables continual strategy evolution without fine-tuning the language model's parameters. The core idea is to liberate the latent vectors of abstract concepts from traditional static…

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…

Planning has been part of the core pursuit for artificial intelligence since its conception, but earlier AI agents mostly focused on constrained settings because many of the cognitive substrates necessary for human-level planning have been…

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…

Memory-augmented LLM agents offer an appealing shortcut to continual learning: rather than updating model parameters, they accumulate experience in external memory, seemingly sidestepping the stability-plasticity dilemma of parametric…

Large language models (LLMs) increasingly serve as the central control unit of AI agents, yet current approaches remain limited in their ability to deliver personalized interactions. While Retrieval Augmented Generation enhances LLM…

Memory systems often organize user-agent interactions as retrievable external memory and are crucial for long-running agents by overcoming the limited context windows of LLMs. However, existing memory systems invoke LLMs to process every…

Visually impaired individuals face significant challenges in environmental perception. Traditional assistive technologies often lack adaptive intelligence, focusing on individual components rather than integrated systems. While…

Exploration remains the key bottleneck for large language model agents trained with reinforcement learning. While prior methods exploit pretrained knowledge, they fail in environments requiring the discovery of novel states. We propose…