mlsanityData to 7 Oct 2026

Distilling Feedback into Memory-as-a-Tool

arXiv 2601.05960 ↗First posted 9 Jan 2026cs.CLcited by 2

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 19 of its 26 references that are in the map. First posted on arXiv 9 Jan 2026.

Builds on

19 of 26 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters6 Aug
  2. 2023Self-Refine: Iterative Refinement with Self-Feedback30 Mar

Other references · 17

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  4. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  5. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
  6. 2025Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domainscited by 328
  7. 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learningcited by 220
  8. 2025Agentic Reasoning: A Streamlined Framework for Enhancing LLM Reasoning with Agentic Toolscited by 106
  9. 2024Feedback Loops With Language Models Drive In-Context Reward Hackingcited by 70
  10. 2024MemLLM: Finetuning LLMs to Use An Explicit Read-Write Memorycited by 35
  11. 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Userscited by 32
  12. 2025RoboMemory: A Brain-inspired Multi-memory Agentic Framework for Interactive Environmental Learning in Physical Embodied Systemscited by 14
5 more
  1. 2015Learning with Memory Embeddingscited by 8
  2. 2025Configurable Preference Tuning with Rubric-Guided Synthetic Datacited by 7
  3. 2025Specification Self-Correction: Mitigating In-Context Reward Hacking Through Test-Time Refinementcited by 6
  4. 2025MetaSC: Test-Time Safety Specification Optimization for Language Modelscited by 4
  5. 2018Interactive Reinforcement Learning with Dynamic Reuse of Prior Knowledge from Human/Agent's Demonstrationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026SkillX: Automatically Constructing Skill Knowledge Bases for Agentscited by 69
  2. 2026STEM Agent: A Self-Adapting, Tool-Enabled, Extensible Architecture for Multi-Protocol AI Agent Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026MemoryCPT: An End-to-End Agent Memory Framework for Cost-Performance Trade-off
  2. 2026LIMBO: Lifelong Inference-Time Memory and Budget Optimization for LLM Agents
  3. 2026Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents
  4. 2026ElasticMem: Latent Memory as a Learnable Resource for LLM Agents
  5. 2026MILES: Modular Instruction Memory with Learnable Selection for Self-Improving LLM Reasoning
  6. 2025Reuse, Don't Recompute: Efficient Large Reasoning Model Inference via Memory Orchestration
  7. 2026Understanding and Mitigating Inference-Time Overreliance Using Agentic Memory
  8. 2025Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs