Large language model (LLM) agents now fix software, operate computers and serve customers, but their harnesses, the programs that run them, call a large LLM at every step, which makes long tasks slow and costly. Most of these calls end in a multiple-choice decision, such as which tool to call next. Decision models such...
Kun-Lun Zhu, Tao Feng, Xue-Ning Han et al.· 0 citations
Agent memory enables large language model (LLM) agents to reuse past experiences without updating their parameters. However, semantic similarity alone does not guarantee memory usefulness: downstream performance depends on how memories are selected and presented to the agent. We propose MemComposer, a memory composer t...
Yi-Xuan Xie, Xue-Qiang Xu, Xin-Yi Fan et al.· 0 citations
T2J-BENCH is introduced, a benchmark of 63 whole-repository PyTorch-to-JAX migration tasks spanning 18 model families across both training and serving, and TWINHARNESS, a reference-grounded agent harness that turns the agent's executable PyTorch source into legitimate self-verification feedback.
Tao Feng, Jie-Feng Chen, Lin-Xin Song et al.· 0 citations
Multimodal models and agents have emerged to enable AI systems to learn from and interact with the real world more like humans by integrating information across multiple modalities. However, enabling multimodal agents to continually acquire useful information from complex, heterogeneous multimodal data remains a signif...
Ming-Hao Guo, Qing-Yue Jiao, Xiu-Jin Liu et al.· 0 citations
Open-ended discovery requires learning from repeated attempts while continuing to explore directions whose value is not yet apparent. Search with a frozen large language model (LLM) can reuse previous solutions in context, but cannot update the model from its successes and failures on the test problem. Reinforcement le...
Tao Feng, Fangxu Yu, Zi-Jie Lei et al.· 0 citations
Memory has become integral to the LLM agent ecosystem, supporting information retention and reuse across interactions. However, most existing agent memory systems construct memory in a query-agnostic manner, which can incur unnecessary preprocessing cost and discard details that later prove essential. Recent studies ha...
Haozhen Zhang, Hao-Dong Yue, Quan-Yu Long et al.· 0 citations
This work presents a unified formulation of LLM routing as a sequential decision process characterized by five components: context encoders, model encoders, scoring functions, decision rules, and learning signals, covering single-turn, multi-turn, and personalized routing.
Tao Feng, Fangxu Yu, Haozhen Zhang et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
