Related papers: CoSPlay: Cooperative Self-Play at Test-Time with S…

Simulation offers a scalable and low-cost way to enrich vision-language-action (VLA) training, reducing reliance on expensive real-robot demonstrations. However, most sim-real co-training methods rely on supervised fine-tuning (SFT), which…

Continual supervised fine-tuning (SFT) is the de facto recipe for adapting large language models (LLMs) to a stream of downstream tasks, but it suffers from catastrophic forgetting of earlier capabilities. Recent work shows that on-policy…

Unit testing is a core practice in programming, enabling systematic evaluation of programs produced by human developers or large language models (LLMs). Given the challenges in writing comprehensive unit tests, LLMs have been employed to…

To automatically tune configurations for the best possible system performance (e.g., runtime or throughput), much work has been focused on designing intelligent heuristics in a tuner. However, existing tuner designs have mostly ignored the…

Reinforcement learning with verifiable rewards (RLVR) has advanced the reasoning capabilities of large language models. However, existing methods rely solely on outcome rewards, without explicitly optimizing verification or leveraging…

We demonstrate that co-training (Blum & Mitchell, 1998) can improve the performance of prompt-based learning by using unlabeled data. While prompting has emerged as a promising paradigm for few-shot and zero-shot learning, it is often…

Self-play, where the algorithm learns by playing against itself without requiring any direct supervision, has become the new weapon in modern Reinforcement Learning (RL) for achieving superhuman performance in practice. However, the…

Test-time scaling (TTS) improves large language models (LLMs) by allocating additional compute at inference time. In practice, TTS is often achieved through parallel scaling: generating multiple candidate responses and selecting the best…

Code large language models (LLMs) have become indispensable tools for building efficient and automated coding pipelines. Existing models are typically post-trained using reinforcement learning (RL) from general-purpose LLMs using "human…

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…

The increasing demand for programming language education and growing class sizes require immediate and personalized feedback. However, traditional code review methods have limitations in providing this level of feedback. As the capabilities…

Role-Playing Language Agents (RPLAs) have emerged as a significant application direction for Large Language Models (LLMs). Existing approaches typically rely on prompt engineering or supervised fine-tuning to enable models to imitate…

Self-play reinforcement learning trains language models on their own generated tasks, co-evolving a proposer and solver without human labels. Recent systems report strong reasoning gains, but collapse and instability are widely observed and…

Existing methods fail to effectively steer Large Language Models (LLMs) between textual reasoning and code generation, leaving symbolic computing capabilities underutilized. We introduce CodeSteer, an effective method for guiding LLM…

Tree Search (TS) is crucial to some of the most influential successes in reinforcement learning. Here, we tackle two major challenges with TS that limit its usability: \textit{distribution shift} and \textit{scalability}. We first discover…

With the rapid advancement of large language models (LLMs) technologies, their application in the domain of autonomous driving has become increasingly widespread. However, existing methods suffer from unstructured reasoning, poor…

Asymmetric self-play has emerged as a promising paradigm for post-training large language models, where a teacher continually generates questions for a student to solve at the edge of the student's learnability. Although these methods…

Training data imbalance poses a major challenge for code LLMs. Most available data heavily over represents raw opensource code while underrepresenting broader software engineering tasks, especially in low resource languages like Golang. As…

Training large language models (LLMs) for non-verifiable tasks, such as creative writing, dialogue, and ethical reasoning, remains challenging due to the absence of ground-truth labels. While LLM-as-Judge approaches offer a scalable…

Despite recent progress in video large language models (VideoLLMs), a key open challenge remains: how to equip models with chain-of-thought (CoT) reasoning abilities grounded in fine-grained object-level video understanding. Existing…