No article text was recorded for this version.
verifiable reward dependency
Version 2 of 2873 papers984 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
- Blog: Training Medical QA Models Based on Mixed Rewards from Multiple-Choice and Open-Ended Questions
- Blog: LaSeR: Reinforcement Learning with Last-Token Self-Rewarding
- Blog: Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
- Blog: Semantically-Aware Rewards for Open-Ended R1 Training in Free-Form Generation
- Blog: RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments
- Blog: Vision-G1: Towards General Vision Language Reasoning with Multi-Domain Data Curation
- Blog: AudSemThinker: Enhancing Audio-Language Models through Reasoning over Semantics of Sound
- Blog: Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains
- Blog: Nemotron-CrossThink: Scaling Self-Learning beyond Math Reasoning
- Blog: A Survey of Reinforcement Learning for Large Reasoning Models
- Blog: Reinforcement Learning with Rubric Anchors
- Blog: Reinforcing General Reasoning without Verifiers
- Blog: Visual-RFT: Visual Reinforcement Fine-Tuning
- Blog: SPARK: Stepwise Process-Aware Rewards for Reference-Free Reinforcement Learning
- Blog: Hybrid Reinforcement: when reward is sparse, better to be dense
- Blog: Reverse-Engineered Reasoning for Open-Ended Generation
- Blog: 100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models
- Blog: A Rolling Stone Gathers No Moss: Adaptive Policy Optimization for Stable Self-Evaluation in Large Multimodal Models
- Blog: Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
- Blog: Agentic Reinforcement Learning with Implicit Step Rewards
- Blog: Retrospective on the 2021 MineRL BASALT Competition on Learning from Human Feedback
- Blog: Direct Reasoning Optimization: LLMs Can Reward And Refine Their Own Reasoning for Open-Ended Tasks
- Blog: Rectifying LLM Thought from Lens of Optimization
- Blog: GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning
- Blog: AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning
- Blog: AuPair: Golden Example Pairs for Code Repair
- Blog: ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search
- Blog: QuRL: Rubrics As Judge For Open-Ended Question Answering
- Blog: Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values
- Blog: SPARK: Synergistic Policy And Reward Co-Evolving Framework
- Blog: Activating Visual Context and Commonsense Reasoning through Masked Prediction in VLMs
- Blog: Optimizing Anytime Reasoning via Budget Relative Policy Optimization
- Blog: Co-Reinforcement Learning for Unified Multimodal Understanding and Generation
- Blog: DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
- Blog: NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions
- Blog: DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search
- Blog: One Sample to Rule Them All: Extreme Data Efficiency in RL Scaling
- Blog: Beyond Verifiable Rewards: Scaling Reinforcement Learning in Language Models to Unverifiable Data
- Blog: Iterative Reasoning Preference Optimization
- Blog: AdaTooler-V: Adaptive Tool-Use for Images and Videos
- Blog: Precision over Diversity: High-Precision Reward Generalizes to Robust Instruction Following
- Blog: VeriRole: Verifiable Role-Awareness through Hint-Guided Reinforcement Learning
- Blog: Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision
- Blog: CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards
- Blog: RLPR: Extrapolating RLVR to General Domains without Verifiers
- Blog: Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains
- Blog: GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning
- Blog: LLMs Can Reason Faster Only If We Let Them
- Blog: Demystifying Long Chain-of-Thought Reasoning in LLMs
- Blog: Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision
- Blog: Metis-RISE: RL Incentivizes and SFT Enhances Multimodal Reasoning Model Learning
- Blog: Diagnosing and Mitigating System Bias in Self-Rewarding RL
- Blog: Generalizing Experience for Language Agents with Hierarchical MetaFlows
- Blog: Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning
- Blog: Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
- Blog: Learning to Reason for Long-Form Story Generation
- Blog: SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting
- Blog: Reverse-Engineered Reasoning for Open-Ended Generation
- Blog: ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning
Showing 60 of 873 papers.
History & citation
Current · Permanent link
- Verifiable Visual Reasoning via Reinforcement Learning merged into this direction (76% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_verifiable_reward_dependency_47f12b3b,
title = {verifiable reward dependency},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/verifiable-reward-dependency/rdr_47f12b3bea00431fbdb9a49062d61631},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_verifiable_reward_dependency_47f12b3b_v2,
title = {verifiable reward dependency},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/verifiable-reward-dependency/rdr_47f12b3bea00431fbdb9a49062d61631/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}