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