IQuest · 10 records

dateidtitleauthorsvenue↑
2026-11-182611.21152From Repositories to Training Environments: Scaling Long-Horizon Coding Agents with Environment Evolution LoopYang Tian et al.arXiv12
2026-10-272610.37161WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent TrainingZiyang Zeng et al.arXiv36
2026-10-262610.35013Multiscale Policy Optimization for Long-Horizon LLM AgentsTao Ren et al.arXiv30
2026-10-222610.30949IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI SystemsA. Jian Yang et al.arXiv99
2026-10-152610.22507RealCLI: Toward a Unified Evaluation of Human-Agent Collaboration for CLI AgentsYunqi Liu et al.arXiv18
2026-09-012608.30530WebWorld: The Browser as a World Model for Self-Improving Web CodeJiajun Wu et al.arXiv9
2026-08-262608.23181CyberFactory: Scaling Cyber Security Capabilities with Instances from the WildJian Yang et al.arXiv35
2026-08-242608.16647Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language ModelsZhaoyi Li et al.arXiv16
2026-07-202607.16051Loop the Loopies!Zitian Gao et al.arXiv51
2026-05-122605.10344TMAS: Scaling Test-Time Compute via Multi-Agent SynergyGeorge Wu et al.arXiv48