# PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agents

arXiv: https://arxiv.org/abs/2605.08468 · HTML: https://mlsanity.com/paper/2605.08468/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 51 of its 67 references that are in the map.
- First posted on arXiv 8 May 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 30 of 51)

- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning](https://mlsanity.com/paper/2207.01780/) (2022)
- [RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning](https://mlsanity.com/paper/2410.02089/) (2024)
- [MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents](https://mlsanity.com/paper/2602.02474/) (2026)
- [Practical Program Repair in the Era of Large Pre-trained Language Models](https://mlsanity.com/paper/2210.14179/) (2022)
- [Establishing Best Practices for Building Rigorous Agentic Benchmarks](https://mlsanity.com/paper/2507.02825/) (2025)
- [MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrieval](https://mlsanity.com/paper/2512.16962/) (2025)
- [Automated Repair of Programs from Large Language Models](https://mlsanity.com/paper/2205.10583/) (2022)
- [AgentRx: Diagnosing AI Agent Failures from Execution Trajectories](https://mlsanity.com/paper/2602.02475/) (2026)
- [Calibration and Correctness of Language Models for Code](https://mlsanity.com/paper/2402.02047/) (2024)
- [RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repair](https://mlsanity.com/paper/2309.06057/) (2023)
- [Memory Poisoning Attack and Defense on Memory Based LLM-Agents](https://mlsanity.com/paper/2601.05504/) (2026)
- [Large Language Models Are Semi-Parametric Reinforcement Learning Agents](https://mlsanity.com/paper/2306.07929/) (2023)
- [Vibe Coding vs. Agentic Coding: Fundamentals and Practical Implications of Agentic AI](https://mlsanity.com/paper/2505.19443/) (2025)
- [ReGAL: Refactoring Programs to Discover Generalizable Abstractions](https://mlsanity.com/paper/2401.16467/) (2024)
- [CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks](https://mlsanity.com/paper/2507.10535/) (2025)
- [Privacy Implications of Retrieval-Based Language Models](https://mlsanity.com/paper/2305.14888/) (2023)
- [Securing Agentic AI: A Comprehensive Threat Model and Mitigation Framework for Generative AI Agents](https://mlsanity.com/paper/2504.19956/) (2025)
- [CodeJudge-Eval: Can Large Language Models be Good Judges in Code Understanding?](https://mlsanity.com/paper/2408.10718/) (2024)
- [RefactorBench: Evaluating Stateful Reasoning in Language Agents Through Code](https://mlsanity.com/paper/2503.07832/) (2025)
- [SkillCraft: Can LLM Agents Learn to Use Tools Skillfully?](https://mlsanity.com/paper/2603.00718/) (2026)
- [Toward Secure Code Generation: Bridging Correctness and Security via Task-Adaptive Vulnerability Modeling and Execution-Based Benchmarking](https://mlsanity.com/paper/2407.02395/) (2024)
- [Off-Policy Reinforcement Learning with Delayed Rewards](https://mlsanity.com/paper/2106.11854/) (2021)
- [Reasoning Through Execution: Unifying Process and Outcome Rewards for Code Generation](https://mlsanity.com/paper/2412.15118/) (2024)
- [Online Multi-LLM Selection via Contextual Bandits under Unstructured Context Evolution](https://mlsanity.com/paper/2506.17670/) (2025)
- [Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned](https://mlsanity.com/paper/2603.05344/) (2026)
- [Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures](https://mlsanity.com/paper/2604.03515/) (2026)
- [Fault Localization with Code Coverage Representation Learning](https://mlsanity.com/paper/2103.00270/) (2021)
- [Defining and Detecting the Defects of the Large Language Model-based Autonomous Agents](https://mlsanity.com/paper/2412.18371/) (2024)
- [Beyond Consensus: Mitigating the Agreeableness Bias in LLM Judge Evaluations](https://mlsanity.com/paper/2510.11822/) (2025)

## Abstract (arXiv)

Local LLM-based coding agents increasingly work in settings where correctness is earned through execution feedback, persistent state, and bounded repair, not through a single fluent answer. Static retrieval, long-context prompting, self-refinement, execution-feedback repair, and reinforcement learning over model weights each address part of this setting, but they do not jointly provide validation-grounded episodic memory, adaptive retrieval-action selection, delayed credit assignment, and structural skill reuse around a frozen local model. We introduce PYTHALAB-MERA, a lightweight external controller for local validation-conditioned code generation. The frozen language model proposes complete source files; the controller decides which memory records and AST-derived skills should enter the next prompt, validates each candidate through a fail-fast pipeline, converts validation outcomes into bounded shaped rewards, and propagates delayed credit through TD(lambda)-style eligibility traces. We evaluate the implementation as a local CLI artifact on reinforcement-learning coding tasks with strict validation gates. In the measured hard RL setting with three tasks, three repetitions, and a three-attempt budget, PYTHALAB-MERA passed 8/9 strict validations; the self-refinement baseline and the investigated GRACE extension each passed 0/9. These results support a deliberately bounded claim: in this recorded setting, the external memory-and-retrieval controller improved validation success. They do not establish general-purpose code synthesis, state-of-the-art performance, formal program correctness, or formal safety.