Distilling Feedback into Memory-as-a-Tool

2026-01-09 · Víctor Gallego arxiv

We propose a framework that amortizes the cost of inference-time reasoning by converting transient critiques into retrievable guidelines, through a file-based memory system and agent-controlled tool calls. We evaluate this method on the Rubric Feedback Bench, a novel dataset for rubric-based learning. Experiments demonstrate that our augmented LLMs rapidly match the performance of test-time refinement pipelines while drastically reducing inference cost.

📄 PDF Abstract BibTeX arXiv:2601.05960

Code (0)

등록된 구현이 없습니다.

MemToolAgent: Leveraging Memory for Tool Using Agents Based on Environment and User Feedback

2026-06-06 · Suleyman Armagan Er, Danilo Ribeiro, Yogesh Virkar, Surafel Lakew 외 arxiv

Modern large language model (LLM) agents can use external tools to help users solve complex tasks. However, for problems that require learning from long-term historical events or from previous agent-environment interacti…

VeriSkill: A Self-Evolution Framework for Program Verification Skills

2026-07-30 · Changguo Jia, Tianqi Zhao, Zhiyou Xiao, Weiming Zhang 외 arxiv

Automating program verification with LLM agents requires generating specifications, annotations, auxiliary lemmas, and tool invocations, all of which depend on reusable skills. A natural remedy is skill self-evolution: d…

MapCoder-Lite: Distilling Multi-Agent Coding into a Single Small LLM

2025-09-22 · Woongkyu Lee, Junhee Cho, Jungwook Choi arxiv

Large language models (LLMs) have advanced code generation from single-function tasks to competitive-programming problems, but existing multi-agent solutions either rely on costly large-scale (>30B) models or collapse wh…

Code Generation

MARDoc: A Memory-Aware Refinement Agent Framework for Multimodal Long Document QA

2026-06-04 · Kaifeng Chen, Hongtao Liu, Qiyao Peng, Jian Yang 외 arxiv

Iterative retrieval-reasoning agents have recently shown promise for multimodal long-document question answering. However, most existing systems maintain a single growing context that mixes retrieval traces, observations…

Question Answering

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

2026-06-23 · Zijie Dai, Siuhin He, Hui Li, Qihui Zhou 외 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 cont…