相关论文: Semantic Context for Tool Orchestration

Code review is a cornerstone of software quality assurance, and recent advances in Large Language Models (LLMs) have shown promise in its automation. However, existing benchmarks for LLM-based code review face three major limitations. Lack…

The quality of AI-generated output is often attributed to prompting technique, but extensive empirical observation suggests that context completeness may be more strongly associated with output quality. This paper introduces Context…

In modern sequential decision-making systems, the construction of an optimal candidate action space is critical to efficient inference. However, existing approaches either rely on manually defined action spaces that lack scalability or…

Understanding the world around us and making decisions about the future is a critical component to human intelligence. As autonomous systems continue to develop, their ability to reason about the future will be the key to their success.…

Large Language Models (LLMs) have demonstrated exceptional performance across diverse tasks. However, their deployment in long-context scenarios faces high computational overhead and information redundancy. While soft prompt compression has…

Software development is a complex activity which depends on diverse technologies and people's expertise. The approaches to developing software highly depend on these different characteristics, which are the context developers are subject…

Standard contextual bandit problem assumes that all the relevant contexts are observed before the algorithm chooses an arm. This modeling paradigm, while useful, often falls short when dealing with problems in which valuable additional…

Tool-using large language model (LLM) agents often face a fundamental tension between answer quality and execution cost. Fixed workflows are stable but inflexible, while free-form multi-step reasoning methods such as ReAct may improve task…

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,…

The rise of large-scale pretrained models has made it feasible to generate predictive or synthetic features at low cost, raising the question of how to incorporate such surrogate predictions into downstream decision-making. We study this…

We study Contextual Multi-Armed Bandits (CMABs) for non-episodic sequential decision making problems where the context includes both textual and numerical information (e.g., recommendation systems, dynamic portfolio adjustments, offer…

Contextual bandit algorithms have transformed modern experimentation by enabling real-time adaptation for personalized treatment and efficient use of data. Yet these advantages create challenges for statistical inference due to adaptivity.…

This volume contains the proceedings of SOS 2011, the Eight Workshop on Structural Operational Semantics, held on the 5th of September 2011 in Aachen, Germany as an affiliated workshop of CONCUR 2011, the 22nd International Conference on…

We describe a new semantic parsing setting that allows users to query the system using both natural language questions and actions within a graphical user interface. Multiple time series belonging to an entity of interest are stored in a…

Semantic Role Labeling (SRL) aims at recognizing the predicate-argument structure of a sentence and can be decomposed into two subtasks: predicate disambiguation and argument labeling. Prior work deals with these two tasks independently,…

Existing Semantic Desktops are still reproached for being too complicated to use or not scaling well. Besides, a real "killer app" is still missing. In this paper, we present a new prototype inspired by NEPOMUK and its successors having a…

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…

We consider a novel variant of the contextual bandit problem (i.e., the multi-armed bandit with side-information, or context, available to a decision-maker) where the context used at each decision may be corrupted ("useless context"). This…

Providing Large Language Models with relevant contextual knowledge at inference time has been shown to greatly improve the quality of their generations. This is often achieved by prepending informative passages of text, or 'contexts',…

By design, word embeddings are unable to model the dynamic nature of words' semantics, i.e., the property of words to correspond to potentially different meanings. To address this limitation, dozens of specialized meaning representation…