Related papers: Quantifying Empirical Compute-Supervision Tradeoff…
When feedback is absorbed faster than task structure can be evaluated, the learner will favor feedback over truth. A two-timescale model shows this feedback-truth gap is inevitable whenever the two rates differ and vanishes only when they…
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an indispensable paradigm for enhancing reasoning in Large Language Models (LLMs). However, standard policy optimization methods, such as Group Relative Policy…
Proponents of software verification suggest that code simplicity is linked to the effort to verify code, hypothesizing that formal verifiers produce fewer false positive warnings and require less manual intervention when analyzing simpler…
While scaling laws for large language models (LLMs) during pre-training have been extensively studied, their behavior under reinforcement learning (RL) post-training remains largely unexplored. This paper presents a systematic empirical…
The recent boom in the literature on entropy-regularized reinforcement learning (RL) approaches reveals that Kullback-Leibler (KL) regularization brings advantages to RL algorithms by canceling out errors under mild assumptions. However,…
Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a key paradigm for post-training Large Language Models (LLMs), particularly for complex reasoning tasks. However, vanilla RLVR training has been shown to improve…
Video generation models produce visually coherent content but struggle with tasks requiring spatial reasoning and multi-step planning. Reinforcement learning (RL) offers a path to improve generalization, but its effectiveness in video…
Unsupervised visual representation learning offers the opportunity to leverage large corpora of unlabeled trajectories to form useful visual representations, which can benefit the training of reinforcement learning (RL) algorithms. However,…
Reinforcement learning with verifiable reward (RLVR) has been instrumental in eliciting strong reasoning capabilities from large language models (LLMs) via long chains of thought (CoT). During RLVR training, we formalize and systemically…
Reinforcement learning (RL) algorithms interact with their environment in a trial-and-error fashion. Such interactions can be expensive, inefficient, and timely when learning on a physical system rather than in a simulation. This work…
Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based feedback from unit tests, but its scalability is fundamentally constrained by the availability and…
Post-training has become a crucial step for unlocking the capabilities of large language models, with reinforcement learning (RL) emerging as a critical paradigm. Recent RL-based post-training has increasingly split into two paradigms:…
Training Large Language Models (LLMs) to reason often relies on Reinforcement Learning (RL) with task-specific verifiers. However, many real-world reasoning-intensive tasks lack verifiers, despite offering abundant expert demonstrations…
Aligning generative recommender systems to user preferences via post-training is critical for closing the gap between next-item prediction and actual recommendation quality. Existing post-training methods are ill-suited for production-scale…
Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing Large Language Models (LLMs), exemplified by the success of OpenAI's o-series. In RLVR, rewards are derived from verifiable signals-such…
Recent advances highlight Reinforcement Learning with Verifiable Rewards (RLVR) as a promising method for enhancing LLMs' capabilities. However, it remains unclear whether the current practice of RLVR truly expands a model's reasoning…
In the ongoing race towards experimental implementations of quantum error correction (QEC), finding ways to automatically discover codes and encoding strategies tailored to the qubit hardware platform is emerging as a critical problem.…
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an effective paradigm for improving the reasoning capabilities of large language models. However, RLVR training is often hindered by sparse binary rewards and weak credit…
In this work, we study the problem of code generation with a large language model (LLM), with a focus on generating SQL queries from natural language questions. We ask: Instead of using supervised fine tuning with text-code pairs, can we…
Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures. When all rollouts are wrong, gradients stall; when one happens to be correct, the update usually…