SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.05960 · 2026

Distilling Feedback into Memory-as-a-Tool

Víctor Gallego

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 3 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
vicgalle/feedback-memory-as-a-tool canonical 0 of 3
FunctionStatusWhere it lives
build_eval_prompt Not yet run vicgalle/feedback-memory-as-a-tool/claude_exp.py
code served (permissive licence) · get_code("c0e0e9541de31131")
extract_tag Not yet run vicgalle/feedback-memory-as-a-tool/claude_exp.py
code served (permissive licence) · get_code("9635d892e9eab4d2")
score_suffix Not yet run vicgalle/feedback-memory-as-a-tool/claude_exp.py
code served (permissive licence) · get_code("cf8194e53fc73396")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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. Code: github.com/vicgalle/feedback-memory-as-a-tool Data: hf.co/datasets/vicgalle/rubric-feedback-bench

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2601.05960")
get_code_for_paper("2601.05960")
have("2601.05960")

Connect an agent — have() is free.