Related papers: MEMAUDIT: An Exact Package-Oracle Evaluation Proto…

Large language models (LLMs) achieve state-of-the-art accuracy on complex reasoning tasks by generating multiple chain-of-thought (CoT) traces, but using a fixed token budget per query leads to over-computation on easy inputs and…

Large language model (LLM)-based coding agents achieve impressive results on controlled benchmarks yet routinely produce pull requests that real maintainers reject. The root cause is not functional incorrectness but a lack of organicity:…

Text documents, including programs, typically have human-readable semantic structure. Historically, programmatic access to these semantics has required explicit in-document tagging. Especially in systems where the text has an execution…

Large Language Models (LLMs) have become a mainstay for many everyday applications. However, as data evolve their knowledge quickly becomes outdated. Continual learning aims to update LLMs with new information without erasing previously…

Automatic prompt optimization is a promising approach for adapting large language models (LLMs) to downstream tasks, yet existing methods typically search for a specific prompt specialized to a fixed task. This paradigm limits…

The scaling law, which indicates that model performance improves with increasing dataset and model capacity, has fueled a growing trend in expanding recommendation models in both industry and academia. However, the advent of large-scale…

In order for large language models to achieve true conversational continuity and benefit from experiential learning, they need memory. While research has focused on the development of complex memory systems, it remains unclear which types…

Automated code documentation is essential for modern software development, providing the contextual grounding that both human developers and coding agents rely on to navigate large codebases. Existing repository-level approaches process…

Large Language Models (LLMs) are increasingly used as autonomous agents in complex, long-horizon applications, where effective memory is critical for sustained performance. Yet existing memory benchmarks are largely dialogue-centric, while…

Supply chain operations traditionally involve a variety of complex decision making problems. Over the last few decades, supply chains greatly benefited from advances in computation, which allowed the transition from manual processing to…

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…

Large Language Models (LLMs) are being increasingly used as a building block in data systems to process large text datasets. To do so, LLM model providers offer multiple LLMs with different sizes, spanning various cost-quality trade-offs…

Episodic memory allows LLM agents to accumulate and retrieve experience, but current methods treat each memory independently, i.e., evaluating retrieval quality in isolation without accounting for the dependency chains through which…

Evaluating the quality of machine-generated natural language content is a challenging task in Natural Language Processing (NLP). Recently, large language models (LLMs) like GPT-4 have been employed for this purpose, but they are…

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…

Traditional enterprises face significant challenges in processing business documents, where tasks like extracting transport references from invoices remain largely manual despite their crucial role in logistics operations. While Large…

Long-term conversational memory in practical LLM applications is inherently collaborative: information is produced by multiple participants, scattered across groups and channels, revised over time, and implicitly grounded in roles and…

Large-batch training has become a cornerstone in accelerating the training of deep neural networks, yet it poses challenges in optimization and generalization. Existing optimizers like AdamW present performance degradation during language…

Modern language agents must operate over long-horizon, multi-turn interactions, where they retrieve external information, adapt to observations, and answer interdependent queries. Yet, most LLM systems rely on full-context prompting,…

Large language models are prominently used in real-world applications, often tasked with reasoning over large volumes of documents. An exciting development in this space is models boasting extended context capabilities, with some…