Related papers: Mitigating Provenance-Role Collapse in Long-Term A…

Large language models (LLMs) are increasingly augmented with long-term memory systems to overcome finite context windows and enable persistent reasoning across interactions. However, recent research finds that LLMs become more vulnerable…

Large language model (LLM) agents face fundamental limitations in long-horizon reasoning due to finite context windows, making effective memory management critical. Existing methods typically handle long-term memory (LTM) and short-term…

In this study, we propose a novel human-like memory architecture designed for enhancing the cognitive abilities of large language model based dialogue agents. Our proposed architecture enables agents to autonomously recall memories…

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…

The rapid evolution of Large Language Model (LLM) agents has necessitated robust memory systems to support cohesive long-term interaction and complex reasoning. Benefiting from the strong capabilities of LLMs, recent research focus has…

Current unlearning and safety training methods consistently fail to remove dangerous knowledge from language models. We identify the root cause - unlearning targets representations which are too general - and develop a highly selective…

Memory management is vital for LLM agents to handle long-term interaction and personalization. Most research focuses on how to organize and use memory summary, but often overlooks the initial memory extraction stage. In this paper, we argue…

Long-horizon LLM agents require memory systems that remain accurate under fixed context budgets. However, existing systems struggle with two persistent challenges in long-term dialogue: (i) \textbf{disconnected evidence}, where multi-hop…

Agentic memory systems enable large language model (LLM) agents to maintain state across long interactions, supporting long-horizon reasoning and personalization beyond fixed context windows. Despite rapid architectural development, the…

In the current field of agent memory, extensive explorations have been conducted in the area of memory retrieval, yet few studies have focused on exploring the memory content. Most research simply stores summarized versions of historical…

Transformers suffer from a high computational cost that grows with sequence length for self-attention, making inference in long streams prohibited by memory consumption. Constant-memory alternatives such as RNNs and SSMs compress history…

Large Language Models (LLMs) have made extraordinary progress in the field of Artificial Intelligence and have demonstrated remarkable capabilities across a large variety of tasks and domains. However, as we venture closer to creating…

Information retrieval in Large Language Models (LLMs) is increasingly recognized as intertwined with generation capabilities rather than mere lookup. While longer contexts are often assumed to improve retrieval, the effects of intra-context…

Long-horizon agentic reasoning necessitates effectively compressing growing interaction histories into a limited context window. Most existing memory systems serialize history as text, where token-level cost is uniform and scales linearly…

Large Language Model (LLM) agents are increasingly used in real-world products, where personalized and context-aware user interactions are essential. A central enabler of such capabilities is the agent's long-term semantic memory system,…

Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents. Recent work has further explored augmenting these agents with memory mechanisms to support long-horizon reasoning.…

Large Language Model (LLM) agents are increasingly expected to maintain coherent, long-term personalized memory, yet current benchmarks primarily measure static fact retrieval, overlooking the ability to revise stored beliefs when new…

Large language models (LLMs) face persistent challenges when handling long-context tasks, most notably the lost in the middle issue, where information located in the middle of a long input tends to be underutilized. Some existing methods…

Large Language Model (LLM)-based agents are increasingly deployed for complex, tool-based tasks where long-term memory is critical to driving actions. Existing benchmarks, however, primarily test a angent's ability to passively retrieve…

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…