FRACTAL is a self‑similar multi‑agent architecture that recursively decomposes goals using a five‑component pattern—Orchestrator, Ensemble, Knowledge Ledger, Decision Maker, and Meta‑Observer—at every level of a decomposition tree. The paper presents four formal results: a linear communication bound for intra‑node cost under a two‑phase protocol, a two‑mode orchestration criterion based on diversity‑saturation, a supermajority convergence guarantee with explicit probability bounds, and a Bayesian escalation mechanism that unifies hysteresis and contract‑breach signaling. The authors illustrate the architecture qualitatively and acknowledge that quantitative performance validation is deferred to future work.
arXiv:2610.08647v1 Announce Type: new Abstract: LLM-based agents solve complex multi-step tasks, but sequential execution incurs substantial latency. In principle, parallelizing work across multiple...
arXiv:2605. 20173v2 Announce Type: replace Abstract: Production LLM agents combine stochastic model outputs with deterministic software systems, yet the boundary between the two is rarely treated as a first-class architectural object.
arXiv:2607. 25656v1 Announce Type: new Abstract: Complex tasks often decompose into parallelizable yet interdependent subtasks, making orchestration critical to the performance of multi-agent systems (MAS).
Translating natural-language planning intent into verified plans is a longstanding challenge: people communicate goals in language, while classical planners require formal PDDL specifications. Recent agentic frameworks bridge this gap by orchestrating a pool of specialized repair agents inside a verifier-checked refinement loop, but the orchestrator at the centre is itself a prompted frontier LLM, paying a frontier-LLM API call at every refinement step.
MAS-Loop introduces an execution‑grounded framework that couples an Orchestrator with a trajectory‑conditioned Refiner to close the feedback loop in training‑time multi‑agent system design. For each task, the Orchestrator builds and runs a source MAS, then the Refiner uses the resulting trajectory to locate failures, diagnose them, and propose bounded patches to agents or execution settings. The updated MAS is re‑executed, and the pairwise comparison of outcomes provides learning signals that enable both components to co‑evolve, yielding stronger systems and a new dataset, MAS‑JudgeCorpus, for trajectory‑aware MAS research.
The paper introduces a game-theoretic framework for coordinating multi-agent large language model (LLM) systems, modeling orchestrator–worker interactions as a bilevel coordination game. It analyzes textual reflection as stochastic movement over semantic memory states, providing finite-time bounds, lower bounds, and an information-theoretic impossibility result. Building on these insights, the authors propose Stochastic Reflective Memory Ascent (SRMA), a grounded evaluation mechanism that guarantees convergence under certain conditions and demonstrates improved performance on 500 SWE‑bench instances.
arXiv:2606. 06923v1 Announce Type: new Abstract: We study orchestration mechanisms for tool-using AI agents in realistic customer-service workflows over an unstructured knowledge base.
arXiv:2608.25992v2 Announce Type: replace Abstract: Multi-agent large language model (LLM) workflows have emerged as a powerful paradigm for solving complex, open-ended tasks through collaborative re...
The paper introduces POrchestra, a proactive agentic orchestration framework that lets sub‑agents request harness adjustments during execution, enhancing adaptability to dynamic environments. It also proposes On‑Policy Orchestration Distillation (OPOD), which uses hindsight feedback from sub‑agents’ requests to provide targeted improvement signals for training the orchestration policy. Experiments on three long‑horizon benchmarks show that POrchestra boosts task success by about 9.1% over the best baseline, and with OPOD the improvement rises to 10.0%, while also improving cost‑performance trade‑offs.
arXiv:2608. 10504v1 Announce Type: new Abstract: As coding agents increasingly handle implementation, the central challenge shifts from building individual agents to building an infrastructure that systematically improves them.
arXiv:2606. 01351v1 Announce Type: new Abstract: The transition from single-turn models to Multi-Agent Systems (MAS) promises enhanced problem-solving capabilities, yet the centralized orchestration topology remains a critical point of fragility.
Consilience is an inference‑time orchestration framework that steers and certifies communication among multi‑agent large language models in hidden‑profile settings. It summarizes each discussion turn with a compact state of uncertainty, disagreement, evidence gain, redundancy, and premature consensus, then selects a communication intervention (challenge, clarify, seek evidence, or route) and speaker. A round‑wise conformal calibration procedure guarantees that the controller’s proposed action has bounded one‑step regret with high probability, and an acceptance mechanism enforces this guarantee for the executed action. Experiments on HiddenBench‑style tasks show that Consilience improves decision accuracy and communication efficiency over fixed and unstructured protocols, sometimes outperforming a full‑information baseline.