Sunhao Dai

KID-22's activity

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

upvoted a collection 15 days ago

DR-Venus

Collection

5 items • Updated 13 days ago • 17

upvoted a paper 15 days ago

DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data

Paper • 2604.19859 • Published 17 days ago • 51

upvoted a paper 16 days ago

LoopCTR: Unlocking the Loop Scaling Power for Click-Through Rate Prediction

Paper • 2604.19550 • Published 17 days ago • 4

upvoted a paper 29 days ago

RAGEN-2: Reasoning Collapse in Agentic RL

Paper • 2604.06268 • Published Apr 7 • 66

upvoted a paper 30 days ago

Learning to Retrieve from Agent Trajectories

Paper • 2604.04949 • Published Mar 30 • 70

upvoted a collection about 1 month ago

LRAT

Collection

Official resources for LRAT, including trajectory-trained dense retrievers and the LRAT training dataset for agentic search. • 4 items • Updated 30 days ago • 4

upvoted 2 papers about 2 months ago

AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents

Paper • 2603.14465 • Published Mar 15 • 23

MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning

Paper • 2603.03379 • Published Mar 3 • 32

upvoted a paper 2 months ago

OmniGAIA: Towards Native Omni-Modal AI Agents

Paper • 2602.22897 • Published Feb 26 • 53

upvoted 3 papers 3 months ago

DLLM-Searcher: Adapting Diffusion Large Language Model for Search Agents

Paper • 2602.07035 • Published Feb 3 • 30

UI-Venus-1.5 Technical Report

Paper • 2602.09082 • Published Feb 9 • 157

GISA: A Benchmark for General Information-Seeking Assistant

Paper • 2602.08543 • Published Feb 9 • 26

upvoted 2 papers 4 months ago

Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text

Paper • 2601.10355 • Published Jan 15 • 39

When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs

Paper • 2601.11000 • Published Jan 16 • 27

upvoted a collection 4 months ago

MatchTIR

Collection

The official datasets and model checkpoints of MatchTIR. • 6 items • Updated Jan 16 • 3

upvoted a paper 4 months ago

MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching

Paper • 2601.10712 • Published Jan 15 • 24

upvoted a paper 5 months ago

RecGPT-V2 Technical Report

Paper • 2512.14503 • Published Dec 16, 2025 • 18

upvoted a paper 7 months ago

Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn LLM Agents

Paper • 2510.14967 • Published Oct 16, 2025 • 34

upvoted a paper 8 months ago

OnePiece: Bringing Context Engineering and Reasoning to Industrial Cascade Ranking System

Paper • 2509.18091 • Published Sep 22, 2025 • 34

upvoted a paper 9 months ago

RecGPT Technical Report

Paper • 2507.22879 • Published Jul 30, 2025 • 38