Humans efficiently process multimodal streams spanning hours to years, building persistent, fine-grained spatiotemporal memories that support reasoning about and predicting long-horizon events. In contrast, existing benchmarks focus on short- and medium-context tasks, and most foundation models struggle to preserve fin...
Yan-Hao Jia, Yi Zhu, Yi-Ran Zhong et al.· 0 citations
Qwen-Planner-Agent is built, which achieves the best overall performance among all evaluated models and systems on MobilePA-Bench, improving over its base model across tool use, memory, skills, and sub-agent coordination.
Tingyu Qu, Wei-Gao Sun, Yuecheng Liu et al.· arXiv.org· 2 citations
Omni-Decision is presented, an omni-modal agent built on evidence-ledger planning: it replaces the growing dialogue history with an explicit evidence ledger that records what evidence is still missing, what has been confirmed, and where records conflict.
Long-horizon agentic tasks require an agent to modify an environment through a sequence of tool calls, with success determined by the final state. The standard recipe assigns a single outcome reward at the end and compares trajectories sampled for the same task. As a result, a group with no successful trajectory yields...
Ming Ma, Yi Zhu, Yi-Ran Zhong et al.· arXiv.org· 2 citations· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.