Related papers: Learning to Build the Environment: Self-Evolving R…
Reinforcement learning (RL) is effective in enhancing the accuracy of large language models in complex reasoning tasks. Existing RL policy optimization frameworks rely on final-answer correctness as feedback signals and rarely capture the…
Reinforcement Learning from Verifiable Rewards (RLVR) on chain-of-thought reasoning has become a standard part of language model post-training recipes. A common assumption is that the reasoning chains trained through RLVR reliably represent…
Multimodal large language models (MLLMs) achieve ever-stronger performance on visual-language tasks. Even as traditional visual question answering (VQA) benchmarks approach saturation, reliable deployment requires satisfying low error…
Multimodal large language models (MLLMs) have advanced perception across text, vision, and audio, yet they often struggle with structured cross-modal reasoning, particularly when integrating audio and visual signals. We introduce…
We introduce OpenVLThinker, one of the first open-source large vision-language models (LVLMs) to exhibit sophisticated chain-of-thought reasoning, achieving notable performance gains on challenging visual reasoning tasks. While text-based…
Complex reasoning tasks often rely on the ability to consistently and accurately apply simple rules across incremental steps, a foundational capability which we term "level-0" reasoning. To systematically evaluate this capability, we…
Self-improving large language models (LLMs) -- i.e., to improve the performance of an LLM by fine-tuning it with synthetic data generated by itself -- is a promising way to advance the capabilities of LLMs while avoiding extensive…
Retrieval-augmented generation agents development is hindered by the lack of process-level supervision to effectively guide agentic capabilities like task decomposition, retriever invocation, and stepwise decision-making. While…
Reinforcement learning with verifiable rewards (RLVR) has significantly boosted the reasoning capability of language models (LMs). However, existing RLVR approaches train LMs based on their own on-policy responses and are constrained by the…
Reinforcement learning has become the central approach for language models (LMs) to learn from environmental reward or feedback. In practice, the environmental feedback is usually sparse and delayed. Learning from such signals is…
Previous LLMs-based RL studies typically follow either supervised learning with high annotation costs, or unsupervised paradigms using voting or entropy-based rewards. However, their performance remains far from satisfactory due to the…
The main issue with most evaluation schemes today is their "static" nature: the same problems are reused repeatedly, allowing for memorization, format exploitation, and eventual saturation. To measure genuine AI progress, we need evaluation…
Test-time scaling for complex reasoning tasks shows that leveraging inference-time compute, by methods such as independently sampling and aggregating multiple solutions, results in significantly better task outcomes. However, a critical…
We propose a new Verbal Reinforcement Learning (VRL) framework for interpretable task-level planning in mobile robotic systems operating under execution uncertainty. The framework follows a closed-loop architecture that enables iterative…
Evaluating language models fairly is increasingly difficult as static benchmarks risk contamination by training data, obscuring whether models truly reason or recall. We introduce BeyondBench, an evaluation framework using algorithmic…
Whether Reinforcement Learning with Verifiable Rewards (RLVR) endows Large Language Models (LLMs) with new capabilities or merely elicits latent traces remains a central debate. In this work, we align with the former view, proposing a…
Self-evolution offers a promising path for improving reasoning models without relying on intensive human annotation. However, extending this paradigm to video understanding remains underexplored and challenging: videos are long, dynamic,…
We study how large language models can be used to evolve inventory policies in online, non-stationary environments. Our work is motivated by recent advances in LLM-based evolutionary search, such as AlphaEvolve, which demonstrates strong…
When agents interact with a complex environment, they must form and maintain beliefs about the relevant aspects of that environment. We propose a way to efficiently train expressive generative models in complex environments. We show that a…
Existing reinforcement learning (RL)-based post-training methods for large language models have advanced rapidly, yet their design has largely been guided by heuristics rather than systematic theoretical principles. This gap limits our…