Reinforcement Learning with Verifiable Rewards
PulseAugur coverage of Reinforcement Learning with Verifiable Rewards — every cluster mentioning Reinforcement Learning with Verifiable Rewards across labs, papers, and developer communities, ranked by signal.
- developed Grpo 90%
- developed by Grpo 90%
- instance of Qwen3 1.7B 90%
- instance of CatalyzeX Code Finder for Papers 90%
- used by Grpo 70%
- competes with Grpo 70%
- used by Qwen3-1.7B-Base 70%
- used by Qwen3 1.7B 70%
- used by Influence Flower 70%
- instance of Influence Flower 70%
- instance of IArxiv Recommender 70%
- authored by CatalyzeX Code Finder for Papers 50%
13 day(s) with sentiment data
-
New RL Method Enhances Creative Generation Without Direct Verification
Researchers have developed Rubric Curriculum RL (RcRL), a novel approach to improve reinforcement learning in domains where direct verification of outputs is difficult, such as creative writing or complex problem-solvin…
-
RLVR enhances model reasoning by improving solution selection, not knowledge acquisition
A new study investigates the mechanism behind Reinforcement Learning with Verifiable Rewards (RLVR), a technique that significantly improves model reasoning. Contrary to the popular belief that RLVR teaches models new p…
-
New GRIT framework improves visual grounding in VLM reasoning
Researchers have introduced GRIT, a new training framework designed to improve the visual grounding of text-rich reasoning in vision-language models (VLMs). The framework addresses the issue of Correct-but-Visually-Misg…
-
New CRoS metric enhances LLM reasoning by scrambling CoT steps
Researchers have introduced CRoS, a new metric for evaluating the causality of Chain-of-Thought (CoT) reasoning in language models. Unlike previous methods that perturb reasoning steps, CRoS scrambles the order of these…
-
Nemotron Labs releases Dory1.0-4B looped language model
Nemotron Labs has released Dory1.0-4B, a 4-billion-parameter language model that utilizes a novel looped architecture. This design allows the model to achieve improved accuracy and token efficiency by applying a shared …
-
DUET method optimizes RLVR token budgets, boosting quality and speed
Researchers have developed DUET, a novel method for optimizing token budget allocation in reinforcement learning with verifiable rewards (RLVR). DUET jointly tunes prompt selection and rollout length, outperforming prev…
-
New SCARL method aligns language model confidence with rewards
Researchers have introduced SCARL, a novel reinforcement learning technique designed to improve language model reasoning. SCARL addresses the issue of confidence misalignment in reinforcement learning with verifiable re…
-
RLVR offers no free lunch: gains in pass@1 incur pass@k costs, study finds · 3 sources tracked
A new theoretical paper argues that Reinforcement Learning with Verifiable Rewards (RLVR) does not fundamentally improve a language model's reasoning capabilities. Instead, it demonstrates that any gain in solving probl…
-
New LFPO framework aligns Diffusion LLMs efficiently
Researchers have developed a new framework called Sequence Likelihood-Free Policy Optimization (LFPO) to address the challenges of aligning Diffusion Large Language Models (dLLMs). Unlike previous methods that struggled…
-
New distillation methods enhance LLM reasoning and image generation
Researchers are developing advanced on-policy distillation (OPD) techniques to improve language model performance, particularly in areas like mathematical reasoning and text-to-image generation. New methods such as Stud…
-
New PICO method enhances LLM reasoning on complex problems
Researchers have introduced Policy-Compatible Reinforcement Learning (PICO), a novel method designed to improve the reasoning capabilities of large language models, particularly on complex problems where standard reinfo…
-
Research paper details how LLM reinforcement learning clipping affects entropy
A new research paper explores the impact of clipping mechanisms in reinforcement learning for large language models (LLMs). The study reveals that 'clip-low' increases entropy, promoting exploration, while 'clip-high' d…
-
New RoAR Method Enhances LLM Reasoning by Penalizing Spurious Logic
Researchers have developed a new method called RoAR (Rollout-Agreement Reward) to improve the reasoning capabilities of language models trained with Group-Based Policy Optimization (GRPO). By analyzing the agreement amo…
-
New SEPO framework boosts LLM reasoning via guided exploration
Researchers have introduced Self-Evolution Policy Optimization (SEPO), a novel framework designed to enhance the reasoning abilities of large language models (LLMs). SEPO addresses limitations in existing methods like R…
-
Reinforcement Learning Enhances VLM Image Quality Assessment, But Reasoning Reliance Unclear
A new arXiv paper investigates the impact of Reinforcement Learning with Verifiable Rewards (RLVR) on large Vision-Language Models (VLMs) for image quality assessment (IQA). The study found that RL-trained models outper…
-
New research explores reinforcement learning generalization across domains
A new arXiv paper explores the transfer of learning between different domains in reinforcement learning (RL) for language models. The study, titled "Where and What to Reward? Understanding Generalization Between Verifia…
-
New SOPO framework improves LLM hallucination detection, beats GPT-5
Researchers have developed a new framework called Socratic Guided Policy Optimization (SOPO) to improve the detection of hallucinations in large language models. SOPO utilizes a Socratic feedback mechanism where a teach…
-
New framework enhances multimodal reasoning in reinforcement learning
Researchers have introduced Outcome-Conditioned Visual Credit (OVC), a new framework designed to improve multimodal reasoning in reinforcement learning. OVC addresses the limitation of uniformly assigning credit to all …
-
New RLVR methods enhance LLM reasoning by improving sample diversity
Researchers have developed new methods to improve the reasoning capabilities of large language models (LLMs) through reinforcement learning with verifiable rewards (RLVR). One approach, Flat-RLVR, addresses the issue of…
-
New CCR training method slashes RLVR costs by 80% for large models
Researchers have developed a new training method called Concurrent Constraint Reinforcement (CCR) to improve the efficiency of Reinforcement Learning with Verifiable Rewards (RLVR). CCR places multiple independently ver…