Related papers: Outcome-Aware Tool Selection for Semantic Routers:…

Multi-tenant LLM serving frameworks widely adopt shared Key-Value caches to enhance efficiency. However, this creates side-channel vulnerabilities enabling prompt leakage attacks. Prior studies identified these attack surfaces yet focused…

Linear Temporal Logic (LTL) provides a rigorous framework for specifying long-horizon robotic tasks, yet existing approaches face a trade-off: model-based synthesis relies on accurate labeled transition systems, whereas learning-based…

Decision Transformers have recently emerged as a new and compelling paradigm for offline Reinforcement Learning (RL), completing a trajectory in an autoregressive way. While improvements have been made to overcome initial shortcomings,…

This paper introduces two novel approaches for Online Multi-Task Learning (MTL) Regression Problems. We employ a high performance graph-based MTL formulation and develop two alternative recursive versions based on the Weighted Recursive…

Large Language Models (LLMs) consistently benefit from scaled Chain-of-Thought (CoT) reasoning, but also suffer from heavy computational overhead. To address this issue, efficient reasoning aims to incentivize short yet accurate thinking…

The discovery of reusable sub-routines simplifies decision-making and planning in complex reinforcement learning problems. Previous approaches propose to learn such temporal abstractions in a purely unsupervised fashion through observing…

LLMs demonstrate strong performance in auto-mated software engineering, particularly for code generation and issue resolution. While proprietary models like GPT-4o achieve high benchmarks scores on SWE-bench, their API dependence, cost, and…

Large Language Model (LLM) agents increasingly use external tools for complex tasks and rely on embedding-based retrieval to select a small top-k subset for reasoning. As these systems scale, the robustness of this retrieval stage is…

Inference-time reasoning scaling has significantly advanced the capabilities of Large Language Models (LLMs) in complex problem-solving. A prevalent approach involves external search guided by Process Reward Models (PRMs). However, a…

LLM agents must select tools from large API libraries and order them correctly. Existing methods use semantic similarity for both retrieval and ordering, but ordering depends on inter-tool data dependencies that are absent from tool…

We investigate machine learning approaches for optimizing real-time staffing decisions in semi-automated warehouse sortation systems. Operational decision-making can be supported at different levels of abstraction, with different…

Agents built on large language models (LLMs) rely on a range of reliability techniques, including retry, majority voting, and self-consistency, that have been developed in parallel rather than within a common analytical framework. We…

Intent detection is a critical component of task-oriented dialogue systems (TODS) which enables the identification of suitable actions to address user utterances at each dialog turn. Traditional approaches relied on computationally…

Tool-augmented reasoning has become a popular direction for LLM-based agents, and it is widely assumed to improve reasoning and reliability. However, we demonstrate that this consensus does not always hold: in the presence of semantic…

Large language models (LLMs) have garnered significant attention due to their impressive natural language processing (NLP) capabilities. Recently, many studies have focused on the tool utilization ability of LLMs. They primarily…

Emerging computation-intensive applications impose stringent latency requirements on resource-constrained mobile devices. Mobile Edge Computing (MEC) addresses this challenge through task offloading. However, designing effective policies…

Agentic reinforcement learning has advanced large language models (LLMs) to reason through long chain-of-thought trajectories while interleaving external tool use. Existing approaches assume a fixed inventory of tools, limiting LLM agents'…

Attention mechanisms, primarily designed to capture pairwise correlations between words, have become the backbone of machine learning, expanding beyond natural language processing into other domains. This growth in adaptation comes at the…

With the rise of Transformer models in NLP and CV domain, Multi-Head Attention has been proven to be a game-changer. However, its expensive computation poses challenges to the model throughput and efficiency, especially for the long…

Chain-of-thought (CoT) prompting is a popular in-context learning (ICL) approach for large language models (LLMs), especially when tackling complex reasoning tasks. Traditional ICL approaches construct prompts using examples that contain…