Related papers: InfMem: Learning System-2 Memory Control for Long-…

Long-term conversational large language model (LLM) agents require memory systems that can recover relevant evidence from historical interactions without overwhelming the answer stage with irrelevant context. However, existing memory…

The computational difficulties of large language model (LLM) inference remain a significant obstacle to their widespread deployment. The need for many applications to support long input sequences and process them in large batches typically…

While role-playing agents excel in short-term interactions, long-term conversations overwhelm context windows, motivating external memory frameworks. Current systems typically rely on persona-agnostic summarization, which records facts…

Effectively processing long contexts remains a fundamental yet unsolved challenge for large language models (LLMs). Existing single-LLM-based methods primarily reduce the context window or optimize the attention mechanism, but they often…

A major challenge for Multi-Agent Systems is enabling agents to adapt dynamically to diverse environments in which opponents and teammates may continually change. Agents trained using conventional methods tend to excel only within the…

Large Language Models (LLMs) are widely used in generative applications such as chatting, code generation, and reasoning. However, many realworld workloads such as classification, question answering, recommendation, and text embedding rely…

Large language models (LLMs) excel at single-turn reasoning but often lose accuracy and coherence over extended, multi-turn interactions. Recent evaluations such as TurnBench highlight recurring failure modes-reasoning bias, task drift,…

Large Reasoning Models (LRMs) have shown promising accuracy improvements on complex problem-solving tasks. While these models have attained high accuracy by leveraging additional computation at test time, they need to generate long…

Transformer-based large language models (LLMs) demonstrate impressive performance across various natural language processing tasks. Serving LLM inference for generating long contents, however, poses a challenge due to the enormous memory…

Large language models (LLMs) have revolutionized the field of AI, demonstrating unprecedented capacity across various tasks. However, the inference process for LLMs comes with significant computational costs. In this paper, we propose an…

Modern language agents must operate over long-horizon, multi-turn histories, yet deploying such agents with Small Language Models (SLMs) remains fundamentally difficult. Full-context prompting causes context overflow, flat retrieval exposes…

This work introduces an efficient method to scale Transformer-based Large Language Models (LLMs) to infinitely long inputs with bounded memory and computation. A key component in our proposed approach is a new attention technique dubbed…

The stateless architecture of Large Language Models inherently lacks the mechanism to preserve dynamic context, compelling agents to redundantly reprocess history to maintain long-horizon autonomy. While latent memory offers a solution,…

In long-context large language model (LLM) inference, the prefill stage dominates computation due to self-attention over the complete input context. Sparse attention significantly reduces self-attention computation by limiting each token's…

While Large Language Models (LLMs) have achieved remarkable success in various fields, the efficiency of training and inference remains a major challenge. To address this issue, we propose SUBLLM, short for Subsampling-Upsampling-Bypass…

Large Language Models (LLMs) have demonstrated success across many benchmarks. However, they still exhibit limitations in long-context scenarios, primarily due to their short effective context length, quadratic computational complexity, and…

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…

One limitation of existing Transformer-based models is that they cannot handle very long sequences as input since their self-attention operations exhibit quadratic time and space complexity. This problem becomes especially acute when…

Large language models (LLMs) process entire input contexts indiscriminately, which is inefficient when the information required to answer a query is localized within the context. We present dynamic context cutoff, a novel method enabling…

Tool-integrated reasoning has emerged as a key focus for enabling agentic applications. Among these, DeepResearch Agents have gained significant attention for their strong performance on complex, open-ended information-seeking tasks. We…