Related papers: Socratic-Zero : Bootstrapping Reasoning via Data-F…

Large Language Models (LLMs) are widely used as judges to evaluate response quality, providing a scalable alternative to human evaluation. However, most LLM judges operate solely on intrinsic text-based reasoning, limiting their ability to…

Recent breakthroughs in generative reasoning have fundamentally reshaped how large language models (LLMs) address complex tasks, enabling them to dynamically retrieve, refine, and organize information into coherent multi-step reasoning…

Large Language Models (LLMs) have demonstrated remarkable reasoning abilities, yet existing test-time frameworks often rely on coarse self-verification and self-correction, limiting their effectiveness on complex tasks. In this paper, we…

We study whether self-learning can scale LLM-based agents without relying on human-curated datasets or predefined rule-based rewards. Through controlled experiments in a search-agent setting, we identify two key determinants of scalable…

Synthesizing high-quality mathematical reasoning data without human priors remains a significant challenge. Current approaches typically rely on seed data mutation or simple prompt engineering, often suffering from mode collapse and limited…

Despite the remarkable success of large language models (LLMs), they still face bottlenecks while deploying in dynamic, real-world settings with primary challenges being concept drift and the high cost of gradient-based adaptation.…

Equipping large language models (LLMs) with complex, interleaved reasoning and tool-use capabilities has become a key focus in agentic AI research, especially with recent advances in reasoning-oriented (``thinking'') models. Such…

Evaluating AI tutor responses requires more than factual correctness: tutors must identify mistakes, locate errors, provide guidance, and offer actionable next steps. We present GRADE, a systematic study of open-source models for…

Current inference scaling methods, such as Self-consistency and Best-of-N, have proven effective in improving the accuracy of LLMs on complex reasoning tasks. However, these methods rely heavily on the quality of candidate responses and are…

Training models on synthetic data has emerged as an increasingly important strategy for improving the performance of generative AI. This approach is particularly helpful for large multimodal models (LMMs) due to the relative scarcity of…

The performance gap between closed-source and open-source large language models (LLMs) is largely attributed to disparities in access to high-quality training data. To bridge this gap, we introduce a novel framework for the automated…

Large pretrained (e.g., "foundation") models exhibit distinct capabilities depending on the domain of data they are trained on. While these domains are generic, they may only barely overlap. For example, visual-language models (VLMs) are…

Improving the mathematical reasoning capabilities of Large Language Models (LLMs) is critical for advancing artificial intelligence. However, access to extensive, diverse, and high-quality reasoning datasets remains a significant challenge,…

Modern large language models (LLMs) have demonstrated impressive capabilities at sophisticated tasks, often through step-by-step reasoning similar to humans. This is made possible by their strong few and zero-shot abilities -- they can…

We present Logics-STEM, a state-of-the-art reasoning model fine-tuned on Logics-STEM-SFT-Dataset, a high-quality and diverse dataset at 10M scale that represents one of the largest-scale open-source long chain-of-thought corpora.…

As LLM-driven autonomous agents evolve to perform complex, multi-step tasks that require integrating multiple datasets, the problem of discovering relevant data sources becomes a key bottleneck. Beyond the challenge posed by the sheer…

Self-play has enabled large language models to autonomously improve through self-generated challenges. However, existing self-play methods for vision-language models rely on passive interaction with static image collections, resulting in…

Large language models (LLMs) have demonstrated unprecedented capability in reasoning with natural language. Coupled with this development is the emergence of embodied AI in robotics. Despite showing promise for verbal and written reasoning…

Despite impressive progress on complex reasoning, current large language models (LLMs) typically operate in isolation - treating each problem as an independent attempt, without accumulating or integrating experiential knowledge. In…

Reinforcement Learning from Verifiable Rewards (RLVR) is bottlenecked by data: existing synthesis pipelines rely on expert-written code or fixed templates, confining growth to instance-level perturbations. We shift the evolvable unit from…