Demystifying Reinforcement Learning in Agentic Reasoning
Paper
•
2510.11701
•
Published
•
27
Read Later Stack
-
-
Self-Improving LLM Agents at Test-Time
Paper • 2510.07841 • Published • 9 -
Making Mathematical Reasoning Adaptive
Paper • 2510.04617 • Published • 22 -
DocReward: A Document Reward Model for Structuring and Stylizing
Paper • 2510.11391 • Published • 26 -
Skill-Targeted Adaptive Training
Paper • 2510.10023 • Published • 9 -
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs
Paper • 2510.11696 • Published • 154 -
DITING: A Multi-Agent Evaluation Framework for Benchmarking Web Novel Translation
Paper • 2510.09116 • Published • 92 -
FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution
Paper • 2510.12747 • Published • 31 -
Dr.LLM: Dynamic Layer Routing in LLMs
Paper • 2510.12773 • Published • 28 -
A Survey of Vibe Coding with Large Language Models
Paper • 2510.12399 • Published • 45 -
Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks
Paper • 2510.12635 • Published • 14 -
LLM Reasoning for Machine Translation: Synthetic Data Generation over Thinking Tokens
Paper • 2510.11919 • Published • 4 -
HoneyBee: Data Recipes for Vision-Language Reasoners
Paper • 2510.12225 • Published • 9 -
Diffusion Transformers with Representation Autoencoders
Paper • 2510.11690 • Published • 138 -
Don't Just Fine-tune the Agent, Tune the Environment
Paper • 2510.10197 • Published • 26 -
InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue
Paper • 2510.13747 • Published • 28 -
Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs
Paper • 2510.13795 • Published • 42 -
The Art of Scaling Reinforcement Learning Compute for LLMs
Paper • 2510.13786 • Published • 21 -
When Models Lie, We Learn: Multilingual Span-Level Hallucination Detection with PsiloQA
Paper • 2510.04849 • Published • 88 -
Agentic Entropy-Balanced Policy Optimization
Paper • 2510.14545 • Published • 86 -
From Pixels to Words -- Towards Native Vision-Language Primitives at Scale
Paper • 2510.14979 • Published • 53 -
TokDrift: When LLM Speaks in Subwords but Code Speaks in Grammar
Paper • 2510.14972 • Published • 27 -
BitNet Distillation
Paper • 2510.13998 • Published • 30 -
Attention Is All You Need for KV Cache in Diffusion LLMs
Paper • 2510.14973 • Published • 25 -
PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model
Paper • 2510.14528 • Published • 28 -
Large Language Models Do NOT Really Know What They Don't Know
Paper • 2510.09033 • Published • 14 -
Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures
Paper • 2510.14616 • Published • 9 -
LiveResearchBench: A Live Benchmark for User-Centric Deep Research in the Wild
Paper • 2510.14240 • Published • 9 -
Qwen3Guard Technical Report
Paper • 2510.14276 • Published • 8 -
MoM: Mixtures of Scenario-Aware Document Memories for Retrieval-Augmented Generation Systems
Paper • 2510.14252 • Published • 2 -
RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems
Paper • 2510.13910 • Published • 1