Open Data Synthesis For Deep Research
Paper
•
2509.00375
•
Published
•
65
HF Daily
-
-
Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training
Paper • 2509.03403 • Published • 20 -
LMEnt: A Suite for Analyzing Knowledge in Language Models from Pretraining Data to Representations
Paper • 2509.03405 • Published • 19 -
SATQuest: A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LLMs
Paper • 2509.00930 • Published • 3 -
Drivel-ology: Challenging LLMs with Interpreting Nonsense with Depth
Paper • 2509.03867 • Published • 199 -
Towards a Unified View of Large Language Model Post-Training
Paper • 2509.04419 • Published • 67 -
Inverse IFEval: Can LLMs Unlearn Stubborn Training Conventions to Follow Real Instructions?
Paper • 2509.04292 • Published • 54 -
Delta Activations: A Representation for Finetuned Large Language Models
Paper • 2509.04442 • Published • 5 -
Why Language Models Hallucinate
Paper • 2509.04664 • Published • 155 -
Set Block Decoding is a Language Model Inference Accelerator
Paper • 2509.04185 • Published • 47 -
Bootstrapping Task Spaces for Self-Improvement
Paper • 2509.04575 • Published • 5 -
On Robustness and Reliability of Benchmark-Based Evaluation of LLMs
Paper • 2509.04013 • Published • 3 -
Reverse-Engineered Reasoning for Open-Ended Generation
Paper • 2509.06160 • Published • 138 -
Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models
Paper • 2509.06949 • Published • 50 -
Reinforcement Learning Foundations for Deep Research Systems: A Survey
Paper • 2509.06733 • Published • 28 -
Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers
Paper • 2509.06493 • Published • 9 -
SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents
Paper • 2509.06283 • Published • 8 -
Test-Time Scaling in Reasoning Models Is Not Effective for Knowledge-Intensive Tasks Yet
Paper • 2509.06861 • Published • 7 -
R^textbf{2AI}: Towards Resistant and Resilient AI in an Evolving World
Paper • 2509.06786 • Published • 3 -
Parallel-R1: Towards Parallel Thinking via Reinforcement Learning
Paper • 2509.07980 • Published • 87 -
Sharing is Caring: Efficient LM Post-Training with Collective RL Experience Sharing
Paper • 2509.08721 • Published • 443 -
Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding
Paper • 2509.06923 • Published • 17 -
Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
Paper • 2509.03646 • Published • 23 -
ΔL Normalization: Rethink Loss Aggregation in RLVR
Paper • 2509.07558 • Published • 5 -
From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers
Paper • 2509.06938 • Published • 2 -
A Survey of Reinforcement Learning for Large Reasoning Models
Paper • 2509.08827 • Published • 128 -
CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models
Paper • 2509.09675 • Published • 24 -
The Majority is not always right: RL training for solution aggregation
Paper • 2509.06870 • Published • 8 -
Statistical Methods in Generative AI
Paper • 2509.07054 • Published • 7