相关论文: Duel-Evolve: Reward-Free Test-Time Scaling via LLM…

Current alignment methods for Large Language Models (LLMs) rely on compressing vast amounts of human preference data into static, absolute reward functions, leading to data scarcity, noise sensitivity, and training instability. We introduce…

Test-time scaling has emerged as a promising direction for enhancing the reasoning capabilities of Large Language Models in last few years. In this work, we propose Population-Evolve, a training-free method inspired by Genetic Algorithms to…

While combining large language models (LLMs) with evolutionary algorithms (EAs) shows promise for solving complex optimization problems, current approaches typically evolve individual solutions, often incurring high LLM call costs. We…

Iterative preference optimization has recently become one of the de-facto training paradigms for large language models (LLMs), but the performance is still underwhelming due to too much noisy preference data yielded in the loop. To combat…

We present CodeEvolve, an evolutionary framework for improving program performance and code quality with Large Language Models (LLMs). CodeEvolve extends OpenEvolve with runtime-guided target selection, Monte Carlo Tree Search (MCTS),…

Large language models (LLMs) are highly sensitive to prompts, but most automatic prompt optimization (APO) methods assume access to ground-truth references (e.g., labeled validation data) that are costly to obtain. We propose the Prompt…

Test-time Scaling (TTS) has been demonstrated to significantly enhance the reasoning capabilities of Large Language Models (LLMs) during the inference phase without altering model parameters. However, existing TTS methods are largely…

Retrieval algorithms like BM25 and query likelihood with Dirichlet smoothing remain strong and efficient first-stage rankers, yet improvements have mostly relied on parameter tuning and human intuition. We investigate whether a large…

Enhancing the instruction-following ability of Large Language Models (LLMs) primarily demands substantial instruction-tuning datasets. However, the sheer volume of these imposes a considerable computational burden and annotation cost. To…

Reinforcement learning (RL) has emerged as an effective paradigm for improving the reasoning capability of vision-language models (VLMs). However, RL-based optimization typically depends on costly high-quality annotations that are difficult…

Preference optimization, particularly through Reinforcement Learning from Human Feedback (RLHF), has achieved significant success in aligning Large Language Models (LLMs) to adhere to human intentions. Unlike offline alignment with a fixed…

The paradigm of automated program generation is shifting from one-shot generation to inference-time search, where Large Language Models (LLMs) function as semantic mutation operators within evolutionary loops. While effective, these systems…

Recent advancements in large language models (LLMs) have significantly enhanced the ability of LLM-based systems to perform complex tasks through natural language processing and tool interaction. However, optimizing these LLM-based systems…

While astonishingly capable, large Language Models (LLM) can sometimes produce outputs that deviate from human expectations. Such deviations necessitate an alignment phase to prevent disseminating untruthful, toxic, or biased information.…

Preference alignment in Large Language Models (LLMs) has significantly improved their ability to adhere to human instructions and intentions. However, existing direct alignment algorithms primarily focus on relative preferences and often…

Evolutionary agentic systems intensify the trade-off between computational efficiency and reasoning capability by repeatedly invoking large language models (LLMs) during inference. This setting raises a central question: how can an agent…

LLM-driven program evolution can discover high-quality programs, but its cost and run-to-run variance hinder reliable progress. We propose TurboEvolve, a multi-island evolutionary framework that improves sample efficiency and robustness…

Recently, tremendous strides have been made to align the generation of Large Language Models (LLMs) with human values to mitigate toxic or unhelpful content. Leveraging Reinforcement Learning from Human Feedback (RLHF) proves effective and…

Large Language Models (LLMs) have achieved significant advances in reasoning tasks. A key approach is tree-based search with verifiers, which expand candidate reasoning paths and use reward models to guide pruning and selection. Although…

With the rapid advances in Large Language Models (LLMs), aligning LLMs with human preferences become increasingly important. Although Reinforcement Learning with Human Feedback (RLHF) proves effective, it is complicated and highly…