DongkiKim

DongkiKim's activity

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

upvoted a paper 5 days ago

RunningTab: Direct Workspace Interaction with Environment-Side Tabs

Paper • 2610.10444 • Published 6 days ago • 40

upvoted a paper 6 days ago

AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents

Paper • 2610.05140 • Published 9 days ago • 45

submitted a paper to Daily Papers 6 days ago

AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents

Paper • 2610.05140 • Published 9 days ago • 45

authored a paper 7 days ago

AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents

Paper • 2610.05140 • Published 9 days ago • 45

upvoted 2 papers 12 days ago

Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Paper • 2609.39982 • Published 13 days ago • 120

EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery

Paper • 2609.40340 • Published 13 days ago • 111

upvoted a paper 13 days ago

Follow the Entities: A Corpus Map for Agentic Search

Paper • 2609.37226 • Published 14 days ago • 100

authored 3 papers 14 days ago

Rethinking Reward Models for Multi-Domain Test-Time Scaling

Paper • 2510.00492 • Published Oct 1, 2025 • 28

ES-Merging: Biological MLLM Merging via Embedding Space Signals

Paper • 2603.14405 • Published May 31

AdaPath: Query-Adaptive Path-Finding via Path-Bank for Multi-Hop Implicit Biomedical KGQA

Paper • 2608.30556 • Published Aug 31

upvoted 2 papers 14 days ago

Surprising Success, Repeated Failure: Entropy-Guided Credit Assignment for Exploration in LLM Reasoning

Paper • 2609.33781 • Published 16 days ago • 46

Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge

Paper • 2609.34327 • Published 15 days ago • 41

upvoted a paper 2 months ago

Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory

Paper • 2608.07169 • Published Aug 7 • 50

upvoted a paper 4 months ago

TIDE: Proactive Multi-Problem Discovery via Template-Guided Iteration

Paper • 2606.04743 • Published Jun 3 • 47

upvoted 6 papers 5 months ago

OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources

Paper • 2605.29250 • Published May 28 • 79

Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents

Paper • 2605.28775 • Published May 27 • 35

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning

Paper • 2605.28774 • Published May 27 • 90

It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs

Paper • 2605.20258 • Published May 18 • 30

Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR

Paper • 2605.15726 • Published May 15 • 36

PREPING: Building Agent Memory without Tasks

Paper • 2605.13880 • Published May 11 • 28