Related papers: DEBATE, TRAIN, EVOLVE: Self Evolution of Language …

We propose TraceRL, a trajectory-aware reinforcement learning framework for diffusion language models (DLMs) that incorporates preferred inference trajectory into post-training, and is applicable across different architectures. Equipped…

Collecting ground-truth rewards or human demonstrations for multi-step reasoning tasks is often prohibitively expensive, particularly in interactive domains such as web tasks. We introduce Self-Taught Lookahead (STL), a reward-free…

Recent advances in reasoning models have yielded impressive results in mathematics and coding. However, most approaches rely on static datasets, which have been suggested to encourage memorisation and limit generalisation. We introduce…

Large Language Model (LLM)-guided evolutionary search is increasingly used for automated algorithm discovery, yet most current methods track search progress primarily through executable programs and scalar fitness. Even when…

Multi-agent debate has been shown to improve reasoning in large language models (LLMs). However, it is compute-intensive, requiring generation of long transcripts before answering questions. To address this inefficiency, we develop a…

Language models are increasingly used not only as standalone predictors but also as components in larger inference systems, from test-time reasoning to multi-model collaboration. We study language model networks, where pre-trained language…

Large language models (LLMs) have shown impressive performance by generating reasoning paths before final answers, but learning such a reasoning path requires costly human supervision. To address this issue, recent studies have explored…

Test-time Training enables model adaptation using only test questions and offers a promising paradigm for improving the reasoning ability of large language models (LLMs). However, it faces two major challenges: test questions are often…

This paper introduces DebateBrawl, an innovative AI-powered debate platform that integrates Large Language Models (LLMs), Genetic Algorithms (GA), and Adversarial Search (AS) to create an adaptive and engaging debating experience.…

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

As Large Multimodal Models (LMMs) scale up and reinforcement learning (RL) methods mature, LMMs have made notable progress in complex reasoning and decision making. Yet training still relies on static data and fixed recipes, making it…

Test-Time Scaling (TTS) enhances the reasoning ability of large language models (LLMs) by allocating additional computation during inference. However, existing approaches primarily rely on output-level sampling while overlooking the role of…

Large language models (LLMs) demonstrate strong chain-of-thought (CoT) reasoning abilities, while smaller models (<= 3B parameters) significantly underperform on multi-step reasoning tasks. Based on empirical analyses of the Qwen-2.5 model…

Long-form chain-of-thought reasoning has become a cornerstone of advanced reasoning in large language models. While recent verification-refinement frameworks have enabled proprietary models to solve Olympiad-level problems, their…

Large Language Models (LLMs) like GPT-4 have revolutionized natural language processing, showing remarkable linguistic proficiency and reasoning capabilities. However, their application in strategic multi-agent decision-making environments…

Training large language models (LLMs) to spend more time thinking and reflection before responding is crucial for effectively solving complex reasoning tasks in fields such as science, coding, and mathematics. However, the effectiveness of…

Data augmentation has been widely used to improve deep neural networks in many research fields, such as computer vision. However, less work has been done in the context of text, partially due to its discrete nature and the complexity of…

Despite impressive breadth, LLMs still rely on explicit reasoning instructions or static, one-fits-all steering methods, leaving a gap for adaptive, instruction-free reasoning amplification. We present Prototype-Based Dynamic Steering…

Dialogue relation extraction (DRE) aims to extract relations between two arguments within a dialogue, which is more challenging than standard RE due to the higher person pronoun frequency and lower information density in dialogues. However,…

The central challenge of AI for Science is not reasoning alone, but the ability to create computational methods in an open-ended scientific world. Existing LLM-based agents rely on static, pre-defined tool libraries, a paradigm that…