English
Related papers

Related papers: Greedy Is a Strong Default: Agents as Iterative Op…

200 papers

Conventional recommendation systems (RSs) are typically optimized to enhance performance metrics uniformly across all training samples. This makes it hard for data-driven RSs to cater to a diverse set of users due to the varying properties…

Information Retrieval · Computer Science 2024-05-03 Kirandeep Kaur , Chirag Shah

High-quality prompts are crucial for Large Language Models (LLMs) to achieve exceptional performance. However, manually crafting effective prompts is labor-intensive and demands significant domain expertise, limiting its scalability.…

Computation and Language · Computer Science 2025-08-26 Zheng Dong , Luming Shang , Gabriela Olinto

Large language models (LLMs) have demonstrated remarkable capabilities in solving complex open-domain tasks, guided by comprehensive instructions and demonstrations provided in the form of prompts. However, these prompts can be lengthy,…

Artificial Intelligence · Computer Science 2023-11-20 Cho-Jui Hsieh , Si Si , Felix X. Yu , Inderjit S. Dhillon

A burgeoning area within reinforcement learning (RL) is the design of sequential decision-making agents centered around large language models (LLMs). While autonomous decision-making agents powered by modern LLMs could facilitate numerous…

Machine Learning · Computer Science 2026-02-10 Dilip Arumugam , Thomas L. Griffiths

The Random Mutation Hill-Climbing algorithm is a direct search technique mostly used in discrete domains. It repeats the process of randomly selecting a neighbour of a best-so-far solution and accepts the neighbour if it is better than or…

Artificial Intelligence · Computer Science 2016-06-21 Jialin Liu , Diego Peŕez-Liebana , Simon M. Lucas

In the problem of active sequential hypothesis testing (ASHT), a learner seeks to identify the true hypothesis from among a known set of hypotheses. The learner is given a set of actions and knows the random distribution of the outcome of…

Machine Learning · Computer Science 2021-10-08 Kyra Gan , Su Jia , Andrew Li

Reward models are central to large language model (LLM) post-training. However, past work has shown that they can reward spurious or undesirable attributes such as length, format, hallucinations, and sycophancy. In this work, we introduce…

Machine Learning · Computer Science 2026-02-18 Atticus Wang , Iván Arcuschin , Arthur Conmy

A major problem in data augmentation is to ensure that the generated new samples cover the search space. This is a challenging problem and requires exploration for data augmentation policies to ensure their effectiveness in covering the…

Machine Learning · Computer Science 2020-10-08 Alireza Naghizadeh , Mohammadsajad Abavisani , Dimitris N. Metaxas

We study sample complexity of optimizing "hill-climbing friendly" functions defined on a graph under noisy observations. We define a notion of convexity, and we show that a variant of best-arm identification can find a near-optimal solution…

Machine Learning · Computer Science 2020-06-05 Tan Nguyen , Ali Shameli , Yasin Abbasi-Yadkori , Anup Rao , Branislav Kveton

We observe that LLM cascading and routing implicitly solves an anytime computation problem -- a class of algorithms, well-studied in classical AI, that improve solutions as additional computation is allocated. We formalize this connection…

Computation and Language · Computer Science 2026-04-14 Arindam Khaled

We investigate the power of randomized algorithms for the maximum cardinality matching (MCM) and the maximum weight matching (MWM) problems in the online preemptive model. In this model, the edges of a graph are revealed one by one and the…

Data Structures and Algorithms · Computer Science 2015-07-03 Ashish Chiplunkar , Sumedh Tirodkar , Sundar Vishwanathan

The exploration-exploitation trade-off is central to sequential decision-making and black-box optimization, yet how Large Language Models (LLMs) reason about and manage this trade-off remains poorly understood. Unlike Bayesian Optimization,…

Machine Learning · Computer Science 2026-04-01 Andrea Carbonati , Mohammadsina Almasi , Hadis Anahideh

Evaluating large language models (LLMs) in diverse and challenging scenarios is essential to align them with human preferences. To mitigate the prohibitive costs associated with human evaluations, utilizing a powerful LLM as a judge has…

Computation and Language · Computer Science 2025-03-10 Tianjun Wei , Wei Wen , Ruizhi Qiao , Xing Sun , Jianghong Ma

Learning to optimize is an approach that leverages training data to accelerate the solution of optimization problems. Many approaches use unrolling to parametrize the update step and learn optimal parameters. Although L2O has shown…

Optimization and Control · Mathematics 2025-07-15 Patrick Fahy , Mohammad Golbabaee , Matthias J. Ehrhardt

Speculative decoding, which combines a draft model with a target model, has emerged as an effective approach to accelerate large language model (LLM) inference. However, existing methods often face a trade-off between the acceptance rate…

Computation and Language · Computer Science 2025-05-14 Danying Ge , Jianhua Gao , Qizhi Jiang , Yifei Feng , Weixing Ji

Large Language Models (LLMs) have been widely adopted in ranking systems such as information retrieval (IR) systems and recommender systems (RSs). To alleviate the latency of auto-regressive decoding, some studies explore the single (first)…

Artificial Intelligence · Computer Science 2025-05-28 Yingpeng Du , Tianjun Wei , Zhu Sun , Jie Zhang

Generative optimization uses large language models (LLMs) to iteratively improve artifacts (such as code, workflows or prompts) using execution feedback. It is a promising approach to building self-improving agents, yet in practice remains…

The availability of a wide range of large language models (LLMs) embedded in various agentic systems has significantly increased the potential of model selection strategies to improve the cost-performance tradeoff. Existing strategies…

Computation and Language · Computer Science 2025-05-23 Jasper Dekoninck , Maximilian Baader , Martin Vechev

We present a lazy incremental search algorithm, Lifelong-GLS (L-GLS), along with its bounded suboptimal version, Bounded L-GLS (B-LGLS) that combine the search efficiency of incremental search algorithms with the evaluation efficiency of…

Robotics · Computer Science 2022-10-25 Jaein Lim , Mahdi Ghanei , R. Connor Lawson , Siddhartha Srinivasa , Panagiotis Tsiotras

Conventional recommendation systems (RSs) are typically optimized to enhance performance metrics uniformly across all training samples, inadvertently overlooking the needs of diverse user populations. The performance disparity among various…

Information Retrieval · Computer Science 2025-10-21 Kirandeep Kaur , Vinayak Gupta , Manya Chadha , Chirag Shah