Víctor Gallego
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.
| Repository | Role | Ran |
|---|---|---|
| vicgalle/feedback-memory-as-a-tool | canonical | 0 of 3 |
| Function | Status | Where 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") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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
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.