Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
AgensFlow is introduced as an open-source framework that formulates multi-agent coordination as an online policy-learning problem, enabling dynamic adaptation of skill protocols, agent roles, and model bindings. By treating coordination decisions as observable and learnable from repeated trajectories, AgensFlow moves beyond static pipelines in multi-agent system design. Evaluations on distributed-systems incident and security-advisory tasks demonstrate that learned routing achieves higher quality than fixed pipelines, topology compression is meaningful, and warm-started policy graphs reduce exploration costs.
Stop hard-coding your multi-agent coordination logic: AgensFlow learns how to route tasks, assign roles, and choose models on the fly, outperforming static pipelines.
Multi-agent systems built on large language models (LLMs) require many coordination choices that are difficult to fix a priori: which skill protocol to invoke, which agent role should perform a subtask, which model to bind to each role, how roles should interact, when to use retrieval or verification, and when to omit a step entirely. These choices interact with task regime and operational constraints, so static pipelines and one-off model comparisons provide only a limited view of the design space. This paper introduces AgensFlow, an open-source framework that treats multi-agent coordination as an online policy-learning problem under partial observability. The framework makes coordination decisions observable and learnable from repeated trajectories, rather than treating skill, role, model, topology, and evaluation choices as fixed pipeline design. AgensFlow is evaluated on two corpora: distributed-systems incident tasks and security-advisory tasks. The evaluation shows three main results: learned routing reaches a higher-quality operating point than a fixed pipeline baseline on coordination-heavy classes; skip:X isolates topology compression as a meaningful part of the substrate; and warm-started policy graphs can reduce exploration cost while preserving plateau quality. Overall, the results support that learned, auditable routing can improve coordination-heavy multi-agent workflows over static wiring.