paper-with-me

Papers

Metis: Bridging Text and Code Memory for Self-Evolving Agents

2026-06-23 · Zijie Dai, Siuhin He, Hui Li, Qihui Zhou, Jiajun Li, Mingcong Song, Guoping Long, Hongjie Si, Xin Yao, Lin Zhang, James Cheng, Xiao Yan arxiv

Self-evolving agents improve over time by distilling experience from past executions and reusing it in future tasks. Existing systems represent such experience either as natural-language text injected into the agent context or as code exposed as callable tools. However, the choice between these representations is typically made at design time rather than derived from the characteristics of the experience itself, leaving the trade-offs between them poorly understood. We present the first controlled study that isolates text memory and code memory over an identical set of experiences. Our results show that the two forms exhibit complementary trade-offs in construction cost, execution efficiency, and transferability, such that neither representation alone is sufficient. Guided by these findings, we propose Metis, a self-evolving agent system built on a hierarchical dual-representation memory. Metis organizes textual experience into execution plans, environment facts, and common pitfalls, and selectively crystallizes recurring plans into validated callable tools. This design combines the broad applicability of text memory with the execution efficiency of code memory while incurring tool-generation cost only when justified by repeated reuse. We evaluate Metis on AppWorld, a challenging benchmark for interactive agents. The results show that Metis improves task accuracy by up to 20.6% over ReAct while reducing execution cost by up to 22.8%. Compared with representative self-evolving agent systems, Metis consistently achieves a better balance between accuracy, execution efficiency, and memory-construction cost.

📄 PDF Abstract BibTeX arXiv:2606.24151

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Internalizing Curriculum Judgment for LLM Reinforcement Fine-Tuning

2026-05-11 · Han Zheng, Yining Ma, Karthick Gunasekaran, Bharathan Balaji 외 arxiv

In LLM Reinforcement Fine-Tuning (RFT), curriculum learning drives both efficiency and performance. Yet, current methods externalize curriculum judgment via handcrafted heuristics or auxiliary models, risking misalignmen…

Mathematical ReasoningCode Generation

Metis: Memory Foundation Model

2026-07-29 · Zeyu Zhang, Ziliang Guo, Yihang Sun, Xichong Zhang 외 arxiv

Recent advances in AI agents have increasingly internalized native capabilities into their underlying foundation models, giving rise to multimodal foundation models and large reasoning models. However, agent memory is st…

Metis: A Foundation Speech Generation Model with Masked Generative Pre-training

2025-02-05 · Yuancheng Wang, Jiachen Zheng, Junan Zhang, Xueyao Zhang 외

We introduce Metis, a foundation model for unified speech generation. Unlike previous task-specific or multi-task models, Metis follows a pre-training and fine-tuning paradigm. It is pre-trained on large-scale unlabeled …

Self-Supervised LearningSpeech EnhancementTarget Speaker Extractiontext-to-speech+2

METIS: Mentoring Engine for Thoughtful Inquiry & Solutions

2026-01-19 · Abhinav Rajeev Kumar, Dhruv Trehan, Paras Chopra arxiv

Many students lack access to expert research mentorship. We ask whether an AI mentor can move undergraduates from an idea to a paper. We build METIS, a tool-augmented, stage-aware assistant with literature search, curate…

Metis-RISE: RL Incentivizes and SFT Enhances Multimodal Reasoning Model Learning

2025-06-16 · Haibo Qiu, Xiaohan Lan, Fanfan Liu, Xiaohu Sun 외

Recent advancements in large language models (LLMs) have witnessed a surge in the development of advanced reasoning paradigms, which are now being integrated into multimodal large language models (MLLMs). However, existi…

Multimodal ReasoningReinforcement Learning (RL)