Related papers: Neural Paging: Learning Context Management Policie…

Mapping parallel threads onto non-box-shaped domains is a known challenge in GPU computing; efficient mapping prevents performance penalties from unnecessary resource allocation. Currently, achieving this requires significant analytical…

Large language models (LLMs) are revolutionizing education, with LLM-based agents playing a key role in simulating student behavior. A major challenge in student simulation is modeling the diverse learning patterns of students at various…

Large Language Model (LLM)-based web agents excel at knowledge-intensive tasks but face a fundamental conflict between the need for extensive exploration and the constraints of limited context windows. Current solutions typically rely on…

Existing multilingual long-context benchmarks, often based on the popular needle-in-a-haystack test, primarily evaluate a model's ability to locate specific information buried within irrelevant texts. However, such a retrieval-centric…

Large language models (LLMs) increasingly rely on long-context processing, but expanding context windows introduces substantial computational and financial costs. Existing context reduction approaches, including retrieval and memory…

This study investigates the reasoning robustness of large language models (LLMs) on mathematical problem-solving tasks under systematically introduced input perturbations. Using the GSM8K dataset as a controlled testbed, we evaluate how…

Large language models (LLMs) with extended context windows have made significant strides yet remain a challenge due to the scarcity of long documents. Existing methods tend to synthesize long-context data but lack a clear mechanism to…

Pretrained large Language Models (LLMs) are able to answer questions that are unlikely to have been encountered during training. However a diversity of potential applications exist in the broad domain of reasoning systems and considerations…

A key missing capacity of current language models (LMs) is grounding to real-world environments. Most existing work for grounded language understanding uses LMs to directly generate plans that can be executed in the environment to achieve…

Large Language Models (LLMs) enhanced with external contexts, such as through retrieval-augmented generation (RAG), often face challenges in handling imperfect evidence. They tend to over-rely on external knowledge, making them vulnerable…

Existing large language model (LLM) based memory systems apply universal, static policies that overlook a fundamental reality: the contexts that are worth storing in memory are different across users. This misalignment wastes limited memory…

We introduce Lossless Context Management (LCM), a deterministic architecture for LLM memory that outperforms Claude Code on long-context tasks. When benchmarked using Opus 4.6, our LCM-augmented coding agent, Volt, achieves higher scores…

Large Language Models (LLMs) face fundamental challenges in long-context reasoning: many documents exceed their finite context windows, while performance on texts that do fit degrades with sequence length, necessitating their augmentation…

As Large Language Models (LLMs) become increasingly popular, caching responses so that they can be reused by users with semantically similar queries has become a vital strategy for reducing inference costs and latency. Existing caching…

Retrieval-augmented generation (RAG) has become the default strategy for providing large language model (LLM) agents with contextual knowledge. Yet RAG treats memory as a stateless lookup table: information persists indefinitely, retrieval…

Large Language Models (LLM) have emerged as a tool for robots to generate task plans using common sense reasoning. For the LLM to generate actionable plans, scene context must be provided, often through a map. Recent works have shifted from…

Neural-symbolic methods have demonstrated efficiency in enhancing the reasoning abilities of large language models (LLMs). However, existing methods mainly rely on syntactically mapping natural languages to complete formal languages like…

We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents. Agentic Reasoning dynamically leverages web search, code execution, and structured memory to address…

Large Language Models (LLMs) struggle with long-context reasoning, not only due to the quadratic scaling of computational complexity with sequence length but also because of the scarcity and expense of annotating long-context data. There…

Recent research has highlighted that Large Language Models (LLMs), even when trained to generate extended long reasoning steps, still face significant challenges on hard reasoning problems. However, much of the existing literature relies on…