MegaFlow: Large-Scale Distributed Orchestration System for the Agentic Era
Paper • 2601.07526 • Published • 23
May Papers -- Best of Best
The papers I've found so far in May that I consider best of the best, whether that be from the perspective of providing a new perspective on a probl..
-
-
Intelligent AI Delegation
Paper • 2602.11865 • Published • 16 -
ENGRAM: Effective, Lightweight Memory Orchestration for Conversational Agents
Paper • 2511.12960 • Published • 1 -
CityRAG: Stepping Into a City via Spatially-Grounded Video Generation
Paper • 2604.19741 • Published • 17 -
Thinking to Recall: How Reasoning Unlocks Parametric Knowledge in LLMs
Paper • 2603.09906 • Published • 75 -
CUA-Skill: Develop Skills for Computer Using Agent
Paper • 2601.21123 • Published • 14 -
Effective Reasoning Chains Reduce Intrinsic Dimensionality
Paper • 2602.09276 • Published • 12 -
Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models
Paper • 2602.04649 • Published • 13 -
SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback
Paper • 2601.18202 • Published • 9 -
Aletheia tackles FirstProof autonomously
Paper • 2602.21201 • Published • 6 -
Linear representations in language models can change dramatically over a conversation
Paper • 2601.20834 • Published • 21 -
MARS: Modular Agent with Reflective Search for Automated AI Research
Paper • 2602.02660 • Published • 67 -
LightRAG: Simple and Fast Retrieval-Augmented Generation
Paper • 2410.05779 • Published • 39 -
Reasoning Models Struggle to Control their Chains of Thought
Paper • 2603.05706 • Published • 38 -
Experiential Reinforcement Learning
Paper • 2602.13949 • Published • 75 -
Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
Paper • 2602.23008 • Published • 37 -
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Paper • 2601.07372 • Published • 48 -
WebWorld: A Large-Scale World Model for Web Agent Training
Paper • 2602.14721 • Published • 19 -
DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints
Paper • 2601.18137 • Published • 36 -
PlotCraft: Pushing the Limits of LLMs for Complex and Interactive Data Visualization
Paper • 2511.00010 • Published • 2