AI Agent Papers2026
Provides a training-free multimodal reasoning harness that combines heterogeneous visual tools, persistent multimodal memory, and code execution so MLLMs can iteratively acquire and compose grounded evidence. Improves accuracy on 22 benchmarks by about 9.7–12.6 points while cutting comparative token costs.
Embodied AI2026
Learns executable language-conditioned local navigation by pretraining on instruction-conditioned Internet egocentric videos, aligning learned visual dynamics with simulated action labels, then jointly fine-tuning for navigation. Achieves high success rates on short-horizon benchmarks (86.5% OVON, 94.9% HabitatGS-LN) with real-robot validation and released code/data.
AI Agent Papers2026
Evaluates AI agent harness reliability and failure attribution using inspectable execution traces and evidence from multiple sources. Its 95 tasks cover seven dimensions and score task performance separately from harness reliability.
AI Agent Papers2026
Synthesizes multi-step tool interactions and trains agents only on actions supported by information visible at decision time. Tests across five Qwen3 scales show gains on Tau1, Tau2, and BFCL.