21 accepted papers
We present \textbf{ExCyTIn-Bench}, the first benchmark to \textbf{E}valuate an LLM agent \textbf{X} on the task of \textbf{Cy}ber \textbf{T}hreat \textbf{In}vestigation through security questions derived from investigation graphs. Real‑world security analysts must sift through a large number of hete…
Enabling large language models with external tools has become a pivotal strategy for extending their functionality beyond text space. To enhance LLMs' tool-calling abilities, previous approaches primarily rely on supervised fine-tuning (SFT) with trajectories distilled from stronger models, often re…
Large language models (LLMs) are increasingly deployed as digital agents that perform multi-step digital work on a computer, but the environments in which they operate remain fragmented and task-specific. Our position is that digital agents need Agent-Native Computer: interfaces that expose system c…
Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning capabilities of large language models by learning directly from rule-based outcome rewards. Recent RLVR works that operate under the zero setting avoid supervision in labeling the reasoning process, bu…
Large language models (LLMs) are powerful tools but are often expensive to deploy at scale. LLM query routing mitigates this by dynamically assigning queries to models of varying cost and quality to obtain a desired tradeoff. Prior query routing approaches generate only one response from the select…
LLM-based optimization has shown remarkable potential in improving agentic systems. However, the conventional approach of prompting LLM-based generative optimizer with the trajectories on the whole training dataset in a single pass becomes untenable as datasets grow, leading to context window overfl
Document Visual Question Answering (DocVQA) is a practical yet challenging task, which is to ask questions based on documents while referring to multiple pages and different modalities of information, e.g., images and tables. To handle multi-modality, recent methods follow a similar Retrieval Augmen
Failure attribution in LLM multi-agent systems—identifying the agent and step responsible for task failures—provides crucial clues for systems debugging but remains underexplored and labor-intensive. In this paper, we propose and formulate a new research area: automated failure attribution for LLM…
We study reward poisoning attacks on Combinatorial Multi-armed Bandits (CMAB). We first provide a sufficient and necessary condition for the attackability of CMAB, a notion to capture the vulnerability and robustness of CMAB. The attackability condition depends on the intrinsic properties of the cor…
The rapid development of Large Language Models (LLMs) has led to a surge in applications that facilitate collaboration among multiple agents, assisting humans in their daily tasks. However, a significant gap remains in assessing to what extent LLM-powered applications genuinely enhance user experien…
In-context learning is a promising paradigm that utilizes in-context examples as prompts for the predictions of large language models. These prompts are crucial for achieving strong performance. However, since the prompts need to be sampled from a large volume of annotated examples, finding the righ…
Researchers and practitioners have recently reframed powerful Large Language Models (LLMs) as *agents*, enabling them to automate complex tasks largely via the use of specialized functions. To facilitate the development of LLM agents, we present a novel paradigm of training LLM agents without modify…
Coreset selection is powerful in reducing computational costs and accelerating data processing for deep learning algorithms. It strives to identify a small subset from large-scale data, so that training only on the subset practically performs on par with full data. Practitioners regularly desire to…
We study the multi-fidelity multi-armed bandit ($\texttt{MF-MAB}$), an extension of the canonical multi-armed bandit (MAB) problem. $\texttt{MF-MAB}$ allows each arm to be pulled with different costs (fidelities) and observation accuracy. We study both the best arm identification with fixed confiden…
Motivated by various practical applications, we propose a novel and general formulation of targeted multi-objective hyperparameter optimization. Our formulation allows a clear specification of an automatable optimization goal using lexicographic preference over multiple objectives. We then propose a…
Off-policy Learning to Rank (LTR) aims to optimize a ranker from data collected by a deployed logging policy. However, existing off-policy learning to rank methods often make strong assumptions about how users generate the click data, i.e., the click model, and hence need to tailor their methods spe…
We propose the ChaCha (Champion-Challengers) algorithm for making an online choice of hyperparameters in online learning settings. ChaCha handles the process of determining a champion and scheduling a set of ‘live’ challengers over time based on sample complexity bounds. It is guaranteed to have sub…
We study the problem of using low cost to search for hyperparameter configurations in a large search space with heterogeneous evaluation cost and model quality. We propose a blended search strategy to combine the strengths of global and local search, and prioritize them on the fly with the goal of m…
The increasing demand for democratizing machine learning algorithms calls for hyperparameter optimization (HPO) solutions at low cost. Many machine learning algorithms have hyperparameters which can cause a large variation in the training cost. But this effect is largely ignored in existing HPO meth…
Non-stationary bandits and clustered bandits lift the restrictive assumptions in contextual bandits and provide solutions to many important real-world scenarios. Though they have been studied independently so far, we point out the essence in solving these two problems overlaps considerably. In this…
Implicit feedback, such as user clicks, although abundant in online information service systems, does not provide substantial evidence on users' evaluation of system's output. Without proper modeling, such incomplete supervision inevitably misleads model estimation, especially in a bandit learning s…