# TALM: Dynamic Tree-Structured Multi-Agent Framework with Long-Term Memory for Scalable Code Generation

arXiv: https://arxiv.org/abs/2510.23010 · HTML: https://mlsanity.com/paper/2510.23010/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 24 references that are in the map.
- First posted on arXiv 27 Oct 2025.

## Placed in

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

## Builds on (most cited first, 19 of 19)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions](https://mlsanity.com/paper/2406.15877/) (2024)
- [LooGLE: Can Long-Context Language Models Understand Long Contexts?](https://mlsanity.com/paper/2311.04939/) (2023)
- [MapCoder: Multi-Agent Code Generation for Competitive Problem Solving](https://mlsanity.com/paper/2405.11403/) (2024)
- [ClassEval: A Manually-Crafted Benchmark for Evaluating LLMs on Class-level Code Generation](https://mlsanity.com/paper/2308.01861/) (2023)
- [Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models](https://mlsanity.com/paper/2402.14848/) (2024)
- [Self-planning Code Generation with Large Language Models](https://mlsanity.com/paper/2303.06689/) (2023)
- [TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generation](https://mlsanity.com/paper/2402.10178/) (2024)

## Built on by (most cited first, 5 of 5)

- [Code as Agent Harness](https://mlsanity.com/paper/2605.18747/) (2026)
- [Graph-based Agent Memory: Taxonomy, Techniques, and Applications](https://mlsanity.com/paper/2602.05665/) (2026)
- [AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents](https://mlsanity.com/paper/2512.23343/) (2025)
- [Evaluating Memory Structure in LLM Agents](https://mlsanity.com/paper/2602.11243/) (2026)
- [ReusStdFlow: A Standardized Reusability Framework for Dynamic Workflow Construction in Agentic AI](https://mlsanity.com/paper/2602.14922/) (2026)

## Abstract (arXiv)

Agentic code generation requires large language models (LLMs) capable of complex context management and multi-step reasoning. Prior multi-agent frameworks attempt to address these challenges through collaboration, yet they often suffer from rigid workflows and high reasoning recovery costs. To overcome these limitations, we propose TALM (Tree-Structured Multi-Agent Framework with Long-Term Memory), a dynamic framework that integrates structured task decomposition, localized re-reasoning, and long-term memory mechanisms. TALM employs an extensible tree-based collaboration structure. The parent-child relationships, when combined with a divide-and-conquer strategy, enhance reasoning flexibility and enable efficient error correction across diverse task scopes. Furthermore, a long-term memory module enables semantic querying and integration of prior knowledge, supporting implicit self-improvement through experience reuse. Experimental results on HumanEval, BigCodeBench, and ClassEval benchmarks demonstrate that TALM consistently delivers strong reasoning performance and high token efficiency, highlighting its robustness and practical utility in complex code generation tasks.