Search papers, labs, and topics across Lattice.
This paper introduces a knowledge-centric approach to self-improvement in AI systems, contrasting with traditional agent-centric methods that tie improvements to specific agent designs. By leveraging a curated knowledge base, agents can contribute insights from their experiences, allowing for more transferable and inspectable improvements across tasks. The study demonstrates that this method enhances solve rates and reduces costs compared to agent-centric baselines, with distilled knowledge effectively transferring across different tasks and LLM families.
Knowledge-centric self-improvement can significantly boost AI performance while slashing maintenance costs and enhancing transferability across tasks.
Self-improving AI systems typically treat the agent as the object that improves, by optimizing prompts, workflows, harnesses, or even the agent's own code. This agent-centric view can make improvements expensive to maintain and difficult to transfer, because gains become tied to a particular agent design, task distribution, or adaptation run. We study a complementary paradigm: knowledge-centric self-improvement, in which agents remain generic and disposable while the persistent object is a curated knowledge base that agents can leverage for future tasks. We conduct controlled case studies to operationalize this idea via a simple protocol. Agents attempt one task, then contribute evidence-grounded insights to a shared knowledge base via task-level and cross-task forums, followed by knowledge distillation. Because self-improvement is contained in the knowledge rather than the agent, improvement can be more inspectable, transferable, and portable. Across abstract reasoning, coding, and terminal benchmarks, this protocol improves solve rates while reducing dollar cost relative to agent-centric baselines. The resulting distilled knowledge also transfers to held-out tasks and across LLM families, indicating that the improvement is not merely an LLM- or run-specific behavior. These results support a new view of self-improving agentic systems: progress can be driven primarily by the curated persistent knowledge. Code is available at https://github.com/recursive-knowledge/KSI.
