AdaPRA: Process Reward Agents with Adaptive Rubrics for Data Science
Paper • 2610.33245 • Published • 3
Yury Panikov
panikov
AI & ML interests
None yet
Recent Activity
upvoted a paper about 12 hours ago
AdaPRA: Process Reward Agents with Adaptive Rubrics for Data Science upvoted a paper about 12 hours ago
AlphaBet: Reinforcement Learning for LLM Event Forecasting Agents upvoted a paper about 12 hours ago
PhysEvolve: Verifier-grounded Self-evolution for Physical Reasoning with Executable WorldsOrganizations
None yet
upvoted 6
papers about 12 hours ago
AlphaBet: Reinforcement Learning for LLM Event Forecasting Agents
Paper • 2610.22684 • Published • 4
PhysEvolve: Verifier-grounded Self-evolution for Physical Reasoning with Executable Worlds
Paper • 2610.34921 • Published • 6
What Outcome RL Buys: Finishing, Reliability, Rarely Reach
Paper • 2610.34894 • Published • 6
Self-Assessment Reinforcement Learning for Search-State Awareness in Retrieval-Augmented Large Language Models
Paper • 2610.30435 • Published • 7
MLE-World: Predicting Machine Learning Experiment Outcomes with a Learned World Model
Paper • 2610.37175 • Published • 6
upvoted 9
papers about 13 hours ago
Truncate or Not? A Scaling Study of Looped Transformers with Truncated Backpropagation
Paper • 2610.26030 • Published • 32
RynnWorld-Latent: A Cross-Embodiment World Model Conditioned on Universal Latent Actions
Paper • 2610.36791 • Published • 10
SearchHorizonBench: A Benchmark for Search Value in AI Agents
Paper • 2610.34714 • Published • 12
The Lexical Imprint of Pre-training Data
Paper • 2602.10657 • Published • 12
Timestral
Paper • 2610.37585 • Published • 13
MoveBench: A Rubric-Based Benchmark for Evaluating Large Language Models in Sports and Health Coaching
Paper • 2610.26185 • Published • 15
Omni-InteractScope: Benchmarking Proactive and Agentic Interaction in Continuous Omnimodal Streams
Paper • 2610.35439 • Published • 16
Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data
Paper • 2610.37386 • Published • 23
h1: A Taste of the Bitter Lesson in Automated Theorem Proving
Paper • 2610.35962 • Published • 19
upvoted 5
papers about 20 hours ago
Harness-Model Collaboration for Long-Horizon Continual Learning
Paper • 2610.34724 • Published • 21
EmbeddingGemma 2: Unified and Efficient Multimodal Representations
Paper • 2610.37364 • Published • 31
On the SPOT: Enhancing Speculative Decoding for Diffusion Language Models via Commit-Order Prediction
Paper • 2610.22543 • Published • 49
What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents
Paper • 2610.34491 • Published • 37
Nemotron-Labs-Diffusion-Uni: Elastic Self-Refining Unified Diffusion LLM with Cross-Paradigm On-Policy Distillation
Paper • 2610.36466 • Published • 33