Related papers: Remember Your Trace: Memory-Guided Long-Horizon Ag…
Long-horizon conversational agents require persistent memory for coherent reasoning, yet uncontrolled accumulation causes temporal decay and false memory propagation. Benchmarks such as LOCOMO and LOCCO report performance degradation from…
Large Language Models (LLMs) have demonstrated remarkable capabilities in orchestrating tools for reasoning tasks. However, existing methods rely on a step-wise paradigm that lacks a global perspective, which causes error accumulation over…
Amodal completion, generating invisible parts of occluded objects, is vital for applications like image editing and AR. Prior methods face challenges with data needs, generalization, or error accumulation in progressive pipelines. We…
Large language models are transitioning from generalpurpose knowledge engines to realworld problem solvers, yet optimizing them for deep search tasks remains challenging. The central bottleneck lies in the extreme sparsity of highquality…
Continual memory augmentation lets computer-using agents (CUAs) learn from prior interactions, but unvetted memories can encode domain-inappropriate or unsafe heuristics--spurious rules that drift from user intent and safety constraints. We…
The field of Artificial Intelligence is undergoing a transition from Generative AI -- probabilistic generation of text and images -- to Agentic AI, in which autonomous systems execute actions within external environments on behalf of users.…
Large language model (LLM)-powered multi-agent systems (MAS) have demonstrated cognitive and execution capabilities that far exceed those of single LLM agents, yet their capacity for self-evolution remains hampered by underdeveloped memory…
LLM-driven agents, particularly those using general frameworks like ReAct or human-inspired role-playing, often struggle in specialized domains that necessitate rigorously structured workflows. Fields such as remote sensing, requiring…
Despite advances in multimodal large language models, autonomous web agents still struggle to reliably execute long-horizon tasks on complex and dynamic web interfaces. Existing agents often suffer from inaccurate element grounding, the…
Autonomous web navigation requires agents to perceive complex visual environments and maintain long-term context, yet current Large Language Model (LLM) based agents often struggle with spatial disorientation and navigation loops. In this…
Modern information systems require autonomous agents capable of navigating complex workflows, yet current methodologies often struggle with the transition from structured metadata parsing to general environmental perception. While the…
Agentic AI has significantly extended the capabilities of large language models (LLMs) by enabling complex reasoning and tool use. However, most existing frameworks are tailored to domains such as mathematics, coding, or web automation, and…
In recent research advancements within the community, large language models (LLMs) have sparked great interest in creating autonomous agents. However, current prompt-based agents often heavily rely on large-scale LLMs. Meanwhile, although…
We introduce LEGOMem, a modular procedural memory framework for multi-agent large language model (LLM) systems in workflow automation. LEGOMem decomposes past task trajectories into reusable memory units and flexibly allocates them across…
Large Language Models (LLMs) have substantially influenced various software engineering tasks. Indeed, in the case of software refactoring, traditional LLMs have shown the ability to reduce development time and enhance code quality.…
Recent advances in large language models have highlighted their potential to automate computational research, particularly reproducing experimental results. However, existing approaches still use fixed sequential agent pipelines with weak…
Multi-agent systems provide a powerful way to extend large language models (LLMs) by decomposing a complex task into specialized subtasks handled by different agents. However, their performance is often hindered by error propagation,…
The surging demand for adapting long-form cinematic content into short videos has motivated the need for versatile automatic video compilation systems. However, existing compilation methods are limited to predefined tasks, and the community…
Modern software ecosystems face a rapidly growing number of disclosed vulnerabilities, increasing the need for automated repair techniques that can operate reliably at repository scale. Although Large Language Model (LLM)-based agents have…
Large language models (LLMs) are increasingly deployed as intelligent agents that reason, plan, and interact with their environments. To effectively scale to long-horizon scenarios, a key capability for such agents is a memory mechanism…