Related papers: ACON: Optimizing Context Compression for Long-hori…

In this paper, we study whether an off-the-shelf LLM can be adapted into a discrete, variable-length token compressor and decompressor for long-context processing. To this end, we design a self-expressive autoencoding framework that…

Agents based on large language models have recently shown strong potential on real-world software engineering (SWE) tasks that require long-horizon interaction with repository-scale codebases. However, most existing agents rely on…

Large language models hold considerable promise for various applications, but their computational requirements create a barrier that many institutions cannot overcome. A single session using a 70-billion-parameter model can cost around $127…

Transformer-based language models (LMs) are inefficient in long contexts. We propose Dodo, a solution for context compression. Instead of one vector per token in a standard transformer model, Dodo represents text with a dynamic number of…

Rapidly increasing context lengths have led to the assumption that large language models (LLMs) can directly reason over entire codebases. Concurrently, recent advances in LLMs have enabled strong performance on software engineering…

Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical real-world tasks, such as large-scale software development,…

As large language models (LLMs) evolve into autonomous agents for long-horizon information-seeking, managing finite context capacity has become a critical bottleneck. Existing context management methods typically commit to a single fixed…

Large language models (LLMs) have become phenomenally surging, since 2018--two decades after introducing context-awareness into computing systems. Through taking into account the situations of ubiquitous devices, users and the societies,…

Large Language Models (LLMs) present a promising frontier in robotic task planning by leveraging extensive human knowledge. Nevertheless, the current literature often overlooks the critical aspects of robots' adaptability and error…

Despite improvements by length extrapolation, efficient attention and memory modules, handling infinitely long documents with linear complexity without performance degradation during extrapolation remains the ultimate challenge in long-text…

Retrieval-Augmented Generation (RAG) helps LLMs stay accurate, but feeding long documents into a prompt makes the model slow and expensive. This has motivated context compression, ranging from token pruning and summarization to…

Large Language Models (LLMs) are increasingly deployed across edge and cloud platforms for real-time question-answering and retrieval-augmented generation. However, processing lengthy contexts in distributed systems incurs high…

Understanding context is key to understanding human language, an ability which Large Language Models (LLMs) have been increasingly seen to demonstrate to an impressive extent. However, though the evaluation of LLMs encompasses various…

Recent advanced LLM-powered agent systems have exhibited their remarkable capabilities in tackling complex, long-horizon tasks. Nevertheless, they still suffer from inherent limitations in resource efficiency, context management, and…

Soft context compression reduces the computational workload of processing long contexts in LLMs by encoding long context into a smaller number of latent tokens. However, existing frameworks apply uniform compression ratios, failing to…

As large language models increasingly gain popularity in real-world applications, processing extremely long contexts, often exceeding the model's pre-trained context limits, has emerged as a critical challenge. While existing approaches to…

As a model-agnostic approach to long context modeling, multi-agent systems can process inputs longer than a large language model's context window without retraining or architectural modifications. However, their performance often heavily…

Large language model (LLM) agents increasingly operate over long and recurring external contexts, like document corpora and code repositories. Across invocations, existing approaches preserve either the agent's trajectory, passive access to…

LLM-powered agents often use prompt compression to reduce inference costs, but this introduces a new security risk. Compression modules, which are optimized for efficiency rather than safety, can be manipulated by adversarial inputs,…

Question-answering (QA) is a significant application of Large Language Models (LLMs), shaping chatbot capabilities across healthcare, education, and customer service. However, widespread LLM integration presents a challenge for small…