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

• URL: http://arxiv.org/abs/2604.04247v1
• Date: Sun, 05 Apr 2026 20:07:48 GMT
• Title: Combee: Scaling Prompt Learning for Self-Improving Language Model Agents
• Abstract summary: Recent advances in prompt learning allow large language model agents to acquire task-relevant knowledge from inference-time context without parameter changes.<n>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.<n>We propose Combee, a novel framework to scale parallel prompt learning for self-improving agents.
• Score: 58.781108056413274
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Knowledge-Centric Self-Improvement [28.85741798328687]
  Self-improving AI systems treat the agent as the object that improves, by optimizing prompts, harnesses, or even the agent's own code.<n>This agent-centric view can make improvements expensive to maintain and difficult to transfer.<n>We study a complementary paradigm: knowledge-centric self-improvement, in which agents remain generic and disposable.
  arXiv  Detail & Related papers  (2026-07-21T21:38:39Z)
• Harnessing LLM Agents with Skill Programs [58.356514745548026]
  We introduce HASP, a new framework that upgrades skills into executable Program Functions (PFs)<n>PFs act as executable guardrails that activate on failure-prone states and modify the next action or inject corrective context.<n> HASP drives substantial gains compared to both training-free and training-based methods on web-search, math reasoning, and coding tasks.
  arXiv  Detail & Related papers  (2026-05-18T01:35:11Z)
• Learning to Share: Selective Memory for Efficient Parallel Agentic Systems [49.78267008828593]
  Agentic systems solve complex tasks by coordinating multiple agents that iteratively reason, invoke tools, and exchange intermediate results.<n>Recent approaches deploy multiple agent teams running in parallel to explore diverse reasoning trajectories.<n>We propose Learning to Share (LTS), a learned shared-memory mechanism for parallel agentic frameworks.
  arXiv  Detail & Related papers  (2026-02-05T18:20:21Z)
• Towards Continuous Intelligence Growth: Self-Training, Continual Learning, and Dual-Scale Memory in SuperIntelliAgent [10.571643330948858]
  SuperIntelliAgent is an agentic learning framework that couples a trainable small diffusion model (the learner) with a frozen large language model (the verifier)<n>Unlike conventional supervised fine-tuning, SuperIntelliAgent learns autonomously without annotation.<n>We posit that pairing a trainable learner with a reasoning-capable verifier forms a minimal reliable unit of growing intelligence.
  arXiv  Detail & Related papers  (2025-11-28T18:32:49Z)
• Reinforcement Learning for Machine Learning Engineering Agents [52.03168614623642]
  We show that agents backed by weaker models that improve via reinforcement learning can outperform agents backed by much larger, but static models.<n>We propose duration- aware gradient updates in a distributed asynchronous RL framework to amplify high-cost but high-reward actions.<n>We also propose environment instrumentation to offer partial credit, distinguishing almost-correct programs from those that fail early.
  arXiv  Detail & Related papers  (2025-09-01T18:04:10Z)
• STEVE: A Step Verification Pipeline for Computer-use Agent Training [84.24814828303163]
  STEVE is a step verification pipeline for computer-use agent training.<n> GPT-4o is used to verify the correctness of each step in the trajectories based on the screens before and after the action execution.<n>Our agent outperforms supervised finetuning by leveraging both positive and negative actions within a trajectory.
  arXiv  Detail & Related papers  (2025-03-16T14:53:43Z)
• Multi-Agent Transfer Learning via Temporal Contrastive Learning [8.487274986507922]
  This paper introduces a novel transfer learning framework for deep multi-agent reinforcement learning. The approach automatically combines goal-conditioned policies with temporal contrastive learning to discover meaningful sub-goals.
  arXiv  Detail & Related papers  (2024-06-03T14:42:14Z)
• Impact of Decentralized Learning on Player Utilities in Stackelberg Games [57.08270857260131]
  In many two-agent systems, each agent learns separately and the rewards of the two agents are not perfectly aligned. We model these systems as Stackelberg games with decentralized learning and show that standard regret benchmarks result in worst-case linear regret for at least one player. We develop algorithms to achieve near-optimal $O(T2/3)$ regret for both players with respect to these benchmarks.
  arXiv  Detail & Related papers  (2024-02-29T23:38:28Z)
• Efficient Fine-Tuning of Compressed Language Models with Learners [12.768368718187428]
  We introduce Learner modules and priming, novel methods for fine-tuning BERT-based models. Learner modules navigate the double bind of 1) training efficiently by fine-tuning a subset of parameters, and 2) training effectively by ensuring quick convergence and high metric scores. Our results on DistilBERT demonstrate that learners perform on par with or surpass the baselines.
  arXiv  Detail & Related papers  (2022-08-03T13:42:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.