SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments Paper • 2610.12611 • Published Oct 8 • 84
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment Paper • 2608.05102 • Published Aug 5 • 64
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling Paper • 2606.18023 • Published Jun 16 • 151
OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories Paper • 2605.04036 • Published May 5 • 70
InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agents Paper • 2510.02271 • Published Oct 2, 2025 • 8
