Related papers: Diagnosing Retrieval vs. Utilization Bottlenecks i…

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…

Large Language Model (LLM) has exhibited strong reasoning ability in text-based contexts across various domains, yet the limitation of context window poses challenges for the model on long-range inference tasks and necessitates a memory…

As LLMs and foundation models scale, checkpoint/restore has become a critical pattern for training and inference. With 3D parallelism (tensor, pipeline, data), checkpointing involves many processes, each managing numerous tensors of varying…

Memory emerges as the core module in the large language model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game playing, scientific discovery), where memory can enable knowledge accumulation, iterative…

Agentic memory systems have become critical for enabling LLM agents to maintain long-term context and retrieve relevant information efficiently. However, existing memory frameworks suffer from a fundamental limitation: they perform…

Current LLM agents lack principled mechanisms for managing persistent memory across long interaction horizons. We present a biologically-grounded memory architecture comprising six cognitive mechanisms: (1) sleep-phase consolidation, (2)…

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…

Information retrieval systems are crucial for enabling effective access to large document collections. Recent approaches have leveraged Large Language Models (LLMs) to enhance retrieval performance through query augmentation, but often rely…

Large audio language models (LALMs) process both speech and environmental acoustic cues, yet struggle to retain non-speech information across multi-turn interactions. The performance gap between semantic (speech) and acoustic (non-speech)…

Retrieval-augmented generation (RAG) improves language model (LM) performance by providing relevant context at test time for knowledge-intensive situations. However, the relationship between parametric knowledge acquired during pretraining…

Large language model (LLM) agents require long-term memory to leverage information from past interactions. However, existing memory systems often face a fidelity--efficiency trade-off: raw dialogue histories are expensive, while flat facts…

Large Language Models (LLMs) demonstrate remarkable capabilities in question answering (QA), but metrics for assessing their reliance on memorization versus retrieval remain underdeveloped. Moreover, while finetuned models are…

LLM-based agents have been extensively applied across various domains, where memory stands out as one of their most essential capabilities. Previous memory mechanisms of LLM-based agents are manually predefined by human experts, leading to…

Multi-trajectory inference for tool-use LLM agents - generating multiple reasoning attempts and selecting among them - benefits from transferring knowledge across attempts so that later ones avoid the pitfalls of earlier ones. Existing…

To enable reliable long-term interaction, LLM agents require a memory system that can faithfully store, efficiently retrieve, and deeply reason over accumulated dialogue history. Most existing methods adopt an extracted fact based paradigm:…

When LLM conversations grow beyond the context window, old content must be evicted -- but how does the model recover it when needed? We propose cooperative paging: evicted segments are replaced with minimal keyword bookmarks ([pN:keywords],…

Long-term memory is one of the key factors influencing the reasoning capabilities of Large Language Model Agents (LLM Agents). Incorporating a memory mechanism that effectively integrates past interactions can significantly enhance…

Large Language Models (LLMs) have emerged as a promising paradigm for next-generation recommender systems, offering strong semantic understanding and natural-language reasoning abilities. Despite recent progress, current LLM-based…

MLLMs exhibit strong reasoning on isolated queries, yet they operate de novo -- solving each problem independently and often repeating the same mistakes. Existing memory-augmented agents mainly store past trajectories for reuse. However,…

Statefulness is essential for large language model (LLM) agents to perform long-term planning and problem-solving. This makes memory a critical component, yet its management and evolution remain largely underexplored. Existing evaluations…