Maojia Song

OrangeEye's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in Tej3/MathAgen about 4 hours ago

dataset_fix

#1 opened about 4 hours ago by

OrangeEye

authored 16 papers about 6 hours ago

Repurposing Synthetic Data for Fine-grained Search Agent Supervision

Paper • 2510.24694 • Published Oct 28, 2025 • 25

Tongyi DeepResearch Technical Report

Paper • 2510.24701 • Published Oct 28, 2025 • 105

Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics

Paper • 2510.05137 • Published Oct 1, 2025 • 6

LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactions

Paper • 2508.18321 • Published Aug 24, 2025 • 2

PromptDistill: Query-based Selective Token Retention in Intermediate Layers for Efficient Large Language Model Inference

Paper • 2503.23274 • Published Mar 30, 2025

M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework

Paper • 2411.06176 • Published Nov 9, 2024 • 45

Measuring and Enhancing Trustworthiness of LLMs in RAG through Grounded Attributions and Learning to Refuse

Paper • 2409.11242 • Published Sep 17, 2024 • 7

AutoEnv: Automated Environments for Measuring Cross-Environment Agent Learning

Paper • 2511.19304 • Published Nov 24, 2025 • 92

From Perception to Action: An Interactive Benchmark for Vision Reasoning

Paper • 2602.21015 • Published Feb 24 • 26

Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization

Paper • 2602.22675 • Published Feb 26 • 23

Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems

Paper • 2601.21742 • Published Jan 29

Foundation Protocol: A Coordination Layer for Agentic Society

Paper • 2605.23218 • Published May 22 • 83

Agents' Last Exam

Paper • 2606.05405 • Published Jun 3 • 392

EdgeBench: Unveiling Scaling Laws of Learning from Real-World Environments

Paper • 2607.05155 • Published Jul 6 • 18

Harnessing Agentic Evolution

Paper • 2605.13821 • Published May 13

HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

Paper • 2609.01437 • Published 8 days ago • 258

upvoted a paper about 2 months ago

Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories

Paper • 2607.15330 • Published Jul 16 • 75

liked a dataset about 2 months ago

EverMind-AI/EvoAgentBench

Viewer • Updated Jul 16 • 578 • 271 • 16

upvoted a paper 2 months ago

Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks

Paper • 2606.29082 • Published Jun 27 • 43