Related papers: POLCA: Stochastic Generative Optimization with LLM

Long-horizon large language model (LLM) agents are fundamentally limited by context. As interactions become longer, tool descriptions, retrieved memories, and raw environmental feedback accumulate and push out the information needed for…

The efficacy of large language models (LLMs) in understanding and generating natural language has aroused a wide interest in developing prompt-based methods to harness the power of black-box LLMs. Existing methodologies usually prioritize a…

We study a type of Online Linear Programming (OLP) problem that maximizes the objective function with stochastic inputs. The performance of various algorithms that analyze this type of OLP is well studied when the stochastic inputs follow…

Large Language Models (LLMs) have achieved remarkable success across diverse tasks, largely driven by well-designed prompts. However, crafting and selecting such prompts often requires considerable human effort, significantly limiting its…

While reinforcement learning (RL) holds great potential for decision making in the real world, it suffers from a number of unique difficulties which often need specific consideration. In particular: it is highly non-stationary; suffers from…

Chemical process optimization maximizes production efficiency and economic performance, but optimization algorithms, including gradient-based solvers, numerical methods, and parameter grid searches, become impractical when operating…

Generative AI has significantly advanced text-driven image generation, but it still faces challenges in producing outputs that consistently align with evolving user preferences and intents, particularly in multi-turn dialogue scenarios. In…

Generative design refers to computational design methods that can automatically conduct design exploration under constraints defined by designers. Among many approaches, topology optimization-based generative designs aim to explore diverse…

Topology optimization is a widely used design method that produces optimized material distributions for prescribed objectives and constraints through well-established numerical algorithms. Throughout the workflow, engineers make a series of…

Recently, latent reasoning has been introduced into large language models (LLMs) to leverage rich information within a continuous space. However, without stochastic sampling, these methods inevitably collapse to deterministic inference,…

Prompt engineering is a new paradigm for enhancing the performance of trained neural network models. For optimizing text-style prompts, existing methods usually individually operate small portions of a text step by step, which either breaks…

Recent studies increasingly explore Large Language Models (LLMs) as a new paradigm for recommendation systems due to their scalability and world knowledge. However, existing work has three key limitations: (1) most efforts focus on…

In tackling the challenges of large language model (LLM) performance for Text-to-SQL tasks, we introduce CHASE-SQL, a new framework that employs innovative strategies, using test-time compute in multi-agent modeling to improve candidate…

Large Language Models (LLMs) perform best with well-crafted prompts, yet prompt engineering remains manual, inconsistent, and inaccessible to non-experts. We introduce Promptomatix, an automatic prompt optimization framework that transforms…

Finding effective prompts for language models (LMs) is critical yet notoriously difficult: the prompt space is combinatorially large, rewards are sparse due to expensive target-LM evaluation. Yet, existing RL-based prompt optimizers often…

Automatic code optimization remains a difficult challenge, particularly for complex loop nests on modern hardware. This paper investigates a novel approach to code optimization where Large Language Models (LLMs) guide the process through a…

Reinforcement learning (RL) has emerged as a powerful paradigm for fine-tuning Large Language Models (LLMs) for text generation. In particular, recent LLMs such as ChatGPT and GPT-4 can engage in fluent conversations with users after…

Generating challenging instances is crucial for the evaluation and advancement of combinatorial optimization solvers. In this work, we introduce EALG (Evolutionary Adversarial Generation of Language Model-Guided Generators), a novel…

We introduce a new analytic framework to analyze the convergence of the Randomized Stochastic Gradient Descent Ascent (RSGDA) algorithm for stochastic minimax optimization problems. Under the so-called NC-PL condition on one of the…

Large Language Models (LLMs) have demonstrated superior listwise ranking performance. However, their superior performance often relies on large-scale parameters (\eg, GPT-4) and a repetitive sliding window process, which introduces…