相关论文: Reflection-Based Memory For Web navigation Agents

Deep learning-based recommendation has become a widely adopted technique in various online applications. Typically, a deployed model undergoes frequent re-training to capture users' dynamic behaviors from newly collected interaction logs.…

Finetuning language agents with reasoning-action trajectories is effective, but obtaining these trajectories from human annotations or stronger models is costly and sometimes impractical. In this paper, we investigate the use of…

Table-based question answering requires complex reasoning capabilities that current LLMs struggle to achieve with single-pass inference. Existing approaches, such as Chain-of-Thought reasoning and question decomposition, lack error…

Owing to recent advancements, Large Language Models (LLMs) can now be deployed as agents for increasingly complex decision-making applications in areas including robotics, gaming, and API integration. However, reflecting past experiences in…

Recent advances in large language models (LLMs) have enabled the development of autonomous agents capable of complex reasoning and multi-step problem solving. However, these agents struggle to adapt to specialized environments and do not…

Graph Neural Networks (GNNs) have achieved remarkable success in graph-based learning by propagating information among neighbor nodes via predefined aggregation mechanisms. However, such fixed schemes often suffer from two key limitations.…

Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters. In this work, we investigate strategies to endow agents with a…

Assistive agents should be able to perform under-specified long-horizon tasks while respecting user preferences. We introduce Actively Discovering and Adapting to Preferences for any Task (ADAPT) -- a benchmark designed to evaluate agents'…

Reflexion-style agents rely on self-generated reflections as memory, implicitly assuming that agents can accurately diagnose their own failures.We show that this assumption can fail systematically: across ALFWorld and HumanEval, agents…

Autonomous navigation in complex and partially observable environments remains a central challenge in robotics. Several bio-inspired models of mapping and navigation based on place cells in the mammalian hippocampus have been proposed. This…

Recent advances in LLM agents have largely built on reasoning backbones like ReAct, which interleave thought and action in complex environments. However, ReAct often produces ungrounded or incoherent reasoning steps, leading to misalignment…

As deep learning continues to make progress for challenging perception tasks, there is increased interest in combining vision, language, and decision-making. Specifically, the Vision and Language Navigation (VLN) task involves navigating to…

The ultimate navigation efficiency of mobile robots in human environments will depend on how we will appraise them: merely as impersonal machines or as human-like agents. In the latter case, an agent may take advantage of the cooperative…

Pre-trained Vision-Language-Action (VLA) models represent a major leap towards general-purpose robots, yet efficiently adapting them to novel, specific tasks in-situ remains a significant hurdle. While reinforcement learning (RL) is a…

Mobile robots are often tasked with repeatedly navigating through an environment whose traversability changes over time. These changes may exhibit some hidden structure, which can be learned. Many studies consider reactive algorithms for…

Despite the rapid advancements in LLM agents, they still face the challenge of generating meaningful reflections due to inadequate error analysis and a reliance on rare successful trajectories, especially in complex tasks. In this work, we…

Large language models are increasingly deployed as autonomous agents that must plan, act, and recover from mistakes through long-horizon interaction with environments that provide rich feedback. However, prevailing outcome-driven…

We present a theoretical study of continual and experiential learning in large language model agents that combine episodic memory with reinforcement learning. We argue that the key mechanism for continual adaptation, without updating model…

While large language models (LLMs) show impressive decision-making abilities, current methods lack a mechanism for automatic self-improvement from errors during task execution. We propose LEAP, an iterative fine-tuning framework that…

Catastrophic forgetting of previous knowledge is a critical issue in continual learning typically handled through various regularization strategies. However, existing methods struggle especially when several incremental steps are performed.…