# Combee: Scaling Prompt Learning for Self-Improving Language Model Agents

arXiv: https://arxiv.org/abs/2604.04247 · HTML: https://mlsanity.com/paper/2604.04247/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 41 of its 51 references that are in the map.
- First posted on arXiv 5 Apr 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)
- Synthetic data and self-improvement for LLMs / [Self-rewarding alignment and self-training](https://mlsanity.com/synth/self-rewarding-alignment-and-self-training/)

## Builds on (most cited first, 30 of 41)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Large Language Models Are Human-Level Prompt Engineers](https://mlsanity.com/paper/2211.01910/) (2022)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [ExpeL: LLM Agents Are Experiential Learners](https://mlsanity.com/paper/2308.10144/) (2023)
- [DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines](https://mlsanity.com/paper/2310.03714/) (2023)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning](https://mlsanity.com/paper/2507.19457/) (2025)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents](https://mlsanity.com/paper/2407.18901/) (2024)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [Don't Decay the Learning Rate, Increase the Batch Size](https://mlsanity.com/paper/1711.00489/) (2017)
- [ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory](https://mlsanity.com/paper/2509.25140/) (2025)
- [An Empirical Model of Large-Batch Training](https://mlsanity.com/paper/1812.06162/) (2018)
- [SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning](https://mlsanity.com/paper/2602.08234/) (2026)
- [TextGrad: Automatic "Differentiation" via Text](https://mlsanity.com/paper/2406.07496/) (2024)
- [Scaling Large Language Model-based Multi-Agent Collaboration](https://mlsanity.com/paper/2406.07155/) (2024)
- [Many-Shot In-Context Learning](https://mlsanity.com/paper/2404.11018/) (2024)
- [Chain of Agents: Large Language Models Collaborating on Long-Context Tasks](https://mlsanity.com/paper/2406.02818/) (2024)
- [More Agents Is All You Need](https://mlsanity.com/paper/2402.05120/) (2024)

## Built on by (most cited first, 9 of 9)

- [Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces](https://mlsanity.com/paper/2605.10913/) (2026)
- [Decentralized Multi-Agent Systems with Shared Context](https://mlsanity.com/paper/2606.10662/) (2026)
- [When Does Continual Learning Require Learning](https://mlsanity.com/paper/2607.07847/) (2026)
- [Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0](https://mlsanity.com/paper/2607.14004/) (2026)
- [FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration](https://mlsanity.com/paper/2605.08520/) (2026)
- [Ace-Skill: Bootstrapping Multimodal Agents with Prioritized and Clustered Evolution](https://mlsanity.com/paper/2605.08887/) (2026)
- [When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis](https://mlsanity.com/paper/2609.15309/) (2026)
- [Diffuse AI Control on Fuzzy Tasks](https://mlsanity.com/paper/2606.08892/) (2026)
- [EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents](https://mlsanity.com/paper/2606.11182/) (2026)

## Abstract (arXiv)

Recent advances in prompt learning allow large language model agents to acquire task-relevant knowledge from inference-time context without parameter changes. For example, existing methods (like ACE or GEPA) can learn system prompts to improve accuracy based on previous agent runs. However, these methods primarily focus on single-agent or low-parallelism settings. This fundamentally limits their ability to efficiently learn from a large set of collected agentic traces. It would be efficient and beneficial to run prompt learning in parallel to accommodate the growing trend of learning from many agentic traces or parallel agent executions. Yet without a principled strategy for scaling, current methods suffer from quality degradation with high parallelism. To improve both the efficiency and quality of prompt learning, we propose Combee, a novel framework to scale parallel prompt learning for self-improving agents. Combee speeds up learning and enables running many agents in parallel while learning from their aggregate traces without quality degradation. To achieve this, Combee leverages parallel scans and employs an augmented shuffle mechanism; Combee also introduces a dynamic batch size controller to balance quality and delay. Evaluations on AppWorld, Terminal-Bench, Formula, and FiNER demonstrate that Combee achieves up to 17x speedup over previous methods with comparable or better accuracy and equivalent cost.