Test-Time Deep Thinking to Explore Implicit Rules
KDD 2026 (CCF-A). Co-corresponding author. Test-time deep thinking that infers implicit environment rules to guide agent exploration.
wentong-chen
•
•
1 min read
Test-Time Deep Thinking to Explore Implicit Rules
KDD 2026 (CCF-A). Co-corresponding author. Test-time deep thinking that infers implicit environment rules to guide agent exploration.
wentong-chen
AgentCPM-Explore
Project Lead — open-source 4B agent model for long-horizon deep exploration; tops GAIA and HLE among open models of its size
•
1 min read
AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents
ArXiv 2026. First author. Open-source 4B agent model achieving SOTA on GAIA & HLE, surpassing GPT-5 and Claude-4.5-Sonnet. 830+ GitHub Stars.
AgentCPM-Explore: Realizing Long-Horizon Deep Exploration for Edge-Scale Agents
ArXiv 2026. First author. Open-source 4B agent model achieving SOTA on GAIA & HLE, surpassing GPT-5 and Claude-4.5-Sonnet. 830+ GitHub Stars.
Reflective Reinforcement Tool Learning
Reflective reinforcement learning for tool learning.
Reflective Reinforcement Tool Learning
Reflective reinforcement learning for tool learning.
AgentRL
Project Lead — fully asynchronous agent RL training infrastructure for the AgentCPM model family: 100+ tools, 20+ benchmarks, full-cycle visualization
•
1 min read