TGR-EvoDAG is proposed, a multi-agent code evolution framework tailored for GR that enables the first autonomous evolution of a complete GR pipeline, and introduces stage-aware cost planning to optimize GPU-hour budgets, and active downstream co-adaptation to navigate temporary regressions and unlock cross-stage gains.
Jun-Lin He, Jun-Zhang Zhu, Yu-Dong Li et al.· 0 citations
DriveMind is proposed, an MLLM-based driving framework that keeps several hypotheses about the scene alive at the same time and updates their weights as new frames arrive and improves fine-grained interactive driving abilities such as merging, emergency braking, and give-way.
Yan Shi, Ke-Hua Chen, Jia-Rui Qi et al.· 0 citations
Memory lets an embodied agent reuse past experience, yet retaining useful information does not ensure that the agent can apply it when conditions change. We present MemTransfer, a benchmark comparing six memory representations, a working-memory baseline and five representations of past experience, under a shared frozen...
This work evaluates 25 model and agent systems under a controlled tool-using protocol, then uses controlled studies to locate failures in evidence access, tool selection, memory, reasoning, interaction, and scientific execution.
Zhiqing Cui, Xinxiang Yin, Yihong Tang et al.· 0 citations
Evaluated on diverse mathematical, algorithmic, and systems optimization tasks, CORAL sets new state-of-the-art results on 10 tasks, achieving 3-10 times higher improvement rates with far fewer evaluations than fixed evolutionary search baselines across tasks.
Ao Qu, Handi Zheng, Zi-Jian Zhou et al.· arXiv.org· 38 citations· ⚡7
WorldCupArena is presented, a dynamic benchmark for language models and deep-research agents that can be reused for future leagues and cups, and shows only small gains in result and exact-score accuracy, but a clearer gain in Scoreline.
Zhaokai Wang, T. Gui, Jiayuan Rao et al.· arXiv.org· 1 citation· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.