Related papers: A Single Revision Step Improves Token-Efficient LL…

A promising approach for improving reasoning in large language models is to use process reward models (PRMs). PRMs provide feedback at each step of a multi-step reasoning trace, potentially improving credit assignment over outcome reward…

Existing large language models (LLMs) evaluation methods typically focus on testing the performance on some closed-environment and domain-specific benchmarks with human annotations. In this paper, we explore a novel unsupervised evaluation…

The evaluation of Large Language Models (LLMs) increasingly relies on other LLMs acting as judges. However, current evaluation paradigms typically yield a single score or ranking, answering which model is better but not why. While essential…

Large language models (LLMs) are increasingly used in applications requiring factual accuracy, yet their outputs often contain hallucinated responses. While fact-checking can mitigate these errors, existing methods typically retrieve…

AI-driven materials discovery that couples automated experimentation with algorithmic decision-making requires process aware recipe to property predictors that are accurate, calibrated, and physically admissible. We approach this as a…

Despite significant advancements in the general capability of large language models (LLMs), they continue to struggle with consistent and accurate reasoning, especially in complex tasks such as mathematical and code reasoning. One key…

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have empowered large language models (LLMs) to tackle challenging reasoning tasks such as mathematics and programming. Despite its promise, the RLVR paradigm poses…

Speculative decoding (SD) is a powerful technique for accelerating the inference process of large language models (LLMs) without sacrificing accuracy. Typically, SD employs a small draft model to generate a fixed number of draft tokens,…

How should one judge whether a given large language model (LLM) can reliably perform economic reasoning? Most existing LLM benchmarks focus on specific applications and fail to present the model with a rich variety of economic tasks. A…

Recent progress has expanded the use of large language models (LLMs) in drug discovery, including synthesis planning. However, objective evaluation of retrosynthesis performance remains limited. Existing benchmarks and metrics typically…

Reinforcement Learning with Verifiable Rewards (RLVR) has significantly improved LLM reasoning, but its sparse, outcome-based reward provides no guidance for intermediate steps, slowing exploration. We propose Progressively Ascending…

Large language models (LLMs) can improve their accuracy on various tasks through iteratively refining and revising their output based on feedback. We observe that these revisions can introduce errors, in which case it is better to roll back…

Formal verification via theorem proving enables the expressive specification and rigorous proof of software correctness, but it is difficult to scale due to the significant manual effort and expertise required. While Large Language Models…

Efficiently routing queries to the optimal large language model (LLM) is crucial for optimizing the cost-performance trade-off in multi-model systems. However, most existing routers rely on single-model selection, making them susceptible to…

Large language models (LLMs) achieve strong reasoning performance through chain-of-thought (CoT) reasoning, yet often generate unnecessarily long reasoning paths that incur high inference cost. Recent self-consistency-based approaches…

Although Large Vision-Language Models (LVLMs) have achieved impressive results, their high computational costs pose a significant barrier to wide application. To enhance inference efficiency, most existing approaches can be categorized as…

Reinforcement learning has become the standard for improving reasoning in large language models, yet evidence increasingly suggests that RL does not teach new strategies; it redistributes probability mass over solutions the base model…

Automated Program Repair (APR) struggles with complex logic errors and silent failures. Current LLM-based APR methods are mostly static, relying on source code and basic test outputs, which fail to accurately capture complex runtime…

Automated generation of feedback on programming assignments holds significant benefits for programming education, especially when it comes to advanced assignments. Automated Program Repair techniques, especially Large Language Model based…

While large language models (LLMs) have demonstrated remarkable success on a broad range of tasks, math reasoning remains a challenging one. One of the approaches for improving math reasoning is self-correction, which designs self-improving…