Related papers: UMEM: Unified Memory Extraction and Management Fra…
We present Mem-$\pi$, a framework for adaptive memory in large language model (LLM) agents, where useful guidance is generated on demand rather than retrieved from external memory stores. Existing memory-augmented agents typically rely on…
In real-world recommender systems, different retrieval objectives are typically addressed using task-specific datasets with carefully designed model architectures. We demonstrate that Large Language Models (LLMs) can function as universal…
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 (LLMs) have recently emerged as promising tools for solving challenging robotic tasks, even in the presence of action and observation uncertainties. Recent LLM-based decision-making methods (also referred to as…
Deploying Multimodal Large Language Models as the brain of embodied agents remains challenging, particularly under long-horizon observations and limited context budgets. Existing memory assisted methods often rely on textual summaries,…
Ultra long video understanding remains an open challenge, as existing vision language models (VLMs) falter on such content due to limited context length and inefficient long term memory retention. To address this, recent works have…
Self-reflection enables language agents to iteratively refine solutions, yet often produces repetitive outputs that limit reasoning performance. Recent studies have attempted to address this limitation through various approaches, among…
Vision-Language Models (VLMs) often yield inconsistent descriptions of the same object across viewpoints, hindering the ability of embodied agents to construct consistent semantic representations over time. Previous methods resolved…
Recent advances in large language models (LLMs) have scaled the potential for reasoning and agentic search, wherein models autonomously plan, retrieve, and reason over external knowledge to answer complex queries. However, the iterative…
Large language models (LLMs) achieve strong performance across a wide range of tasks, but remain frozen after pretraining until subsequent updates. Many real-world applications require timely, domain-specific information, motivating the…
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…
Autoregressive language models (ARMs) have been shown to memorize and occasionally reproduce training data verbatim, raising concerns about privacy and copyright liability. Diffusion language models (DLMs) have recently emerged as a…
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…
Memory systems address the challenge of context loss in Large Language Model during prolonged interactions. However, compared to human cognition, the efficacy of these systems in processing emotion-related information remains inconclusive.…
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…
Large language model (LLM) multi-agent systems can scale along two distinct dimensions: by increasing the number of agents and by improving through accumulated experience over time. Although prior work has studied these dimensions…
Large language model (LLM) agents increasingly rely on external memory to support long-horizon interaction, personalized assistance, and multi-step reasoning. However, existing memory systems still face three core challenges: they often…
Large Language Model (LLM)-based agents are increasingly applied to tasks requiring structured reasoning, tool use, and environmental adaptation, such as data manipulation, multistep planning, and computer-use automation. However, despite…
Neural network language models (LMs) are confronted with significant challenges in generalization and robustness. Currently, many studies focus on improving either generalization or robustness in isolation, without methods addressing both…
Large language models (LLMs) have achieved impressive linguistic capabilities. However, a key limitation persists in their lack of human-like memory faculties. LLMs exhibit constrained memory retention across sequential interactions,…