Memory enables language model assistants to maintain continuity across sessions and generate personalized responses, but knowing more about a user does not necessarily produce responses they prefer. Existing evaluations assess memory capabilities without directly establishing whether memory use benefits the user. To st...
Yijiang River Dong, Ze-Xue He, Cheng Yu et al.· 0 citations
SWE-Verifier is introduced, a lightweight generative model that selectively triggers candidate sampling and verification that achieves comparable or higher resolution than the trajectory and all-step baselines at substantially lower cost.
Kai-Jian Zou, V. Chennareddy, Yun-Xiang Zhang et al.· 0 citations
It is found that temporal costs limit success in evolving environments and that higher reasoning effort has mixed effects under time pressure, reflecting a trade-off between decision quality and timely execution.
Jing-Yu Tang, Xu Yang, Zhe-Hao Zhang et al.· 0 citations
The introduction of Relic, which turns recurring collaboration failures into organization-owned, executable protocols, and how collaboration experience can become persistent organizational state that remains useful beyond the members who created it are shown.
Hong-Yi Du, Tian-Yi Zhang, Wei-Jia Zhang et al.· arXiv.org· 0 citations
MemoryArena is introduced, a unified evaluation gym for benchmarking agent memory in multi-session Memory-Agent-Environment loops with explicitly interdependent subtasks, where agents must learn from earlier actions and feedback by distilling experiences into memory, and subsequently use that memory to guide later acti...
This position paper argues that AI-assisted deliberation offers a more promising path by lowering barriers to meaningful engagement without substituting machine judgment for human choice.
José Ramón Enríquez, Jia-Xin Pei, A. Pentland· arXiv.org· 0 citations
A user-centric framework for systematically auditing system prompts in AI systems, AISPA is introduced, a user-centric framework for systematically auditing system prompts in AI systems that examines specific parts of a system prompt and evaluates them along eight dimensions that matter to users.
Xiangning Lin, Shenzhe Zhu, Shu Yang et al.· arXiv.org· 0 citations
ChainSWE is introduced, the first benchmark for evaluating agents on sequential, dependent bug fixes within a shared codebase, and reveals a consistent performance drop by up to 70% as the chain length increases.
Qirui Jin, Lingching Tung, Kenan Li et al.· 1 citation· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.