Multi-agent AI systems powered by large language models (LLMs) are increasingly applied to solve complex tasks. However, these systems often rely on fragile, manually designed prompts and heuristics, making optimization difficult. A key challenge in optimizing multi-agent systems is acquiring suitable training data for specialized agents. We introduce SIRIUS, a self-improving, reasoning-driven optimization framework for multi-agent systems. Central to our approach is the construction of an experience library: a repository of high-quality reasoning trajectories. The library is built by retaining reasoning steps that lead to successful outcomes, providing a robust training set for optimizing multi-agent system. Additionally, we introduce a library augmentation procedure that refines unsuccessful trajectories, further enriching the library. SIRIUS boosts performance by 2.86% to 21.88% on reasoning and biomedical QA and enhances agent negotiation in competitive settings. Our results show that SIRIUS enhances multi-agent performance while generating reusable data for self-correction and self-play enhancement in the future.

This study presents a conditional flow matching framework for solving physics-constrained Bayesian inverse problems. In this setting, samples from the joint distribution of inferred variables and measurements are assumed available, while explicit evaluation of the prior and likelihood densities is not required. We derive a simple and self-contained formulation of both the unconditional and conditional flow matching algorithms, tailored specifically to inverse problems. In the conditional setting, a neural network is trained to learn the velocity field of a probability flow ordinary differential equation that transports samples from a chosen source distribution directly to the posterior distribution conditioned on observed measurements. This black-box formulation accommodates nonlinear, high-dimensional, and potentially non-differentiable forward models without restrictive assumptions on the noise model. We further analyze the behavior of the learned velocity field in the regime of finite training data. Under mild architectural assumptions, we show that overtraining can induce degenerate behavior in the generated conditional distributions, including variance collapse and a phenomenon termed selective memorization, wherein generated samples concentrate around training data points associated with similar observations. A simplified theoretical analysis explains this behavior, and numerical experiments confirm it in practice. We demonstrate that standard early-stopping criteria based on monitoring test loss effectively mitigate such degeneracy. The proposed method is evaluated on several physics-based inverse problems. We investigate the impact of different choices of source distributions, including Gaussian and data-informed priors. Across these examples, conditional flow matching accurately captures complex, multimodal posterior distributions while maintaining computational efficiency.

Let (x0,y0) in M beanaugmentedg.

Specifically, we derive equivariance constraints from the time-independent symmetries ofODEs.

We thank R2 for pointing out the important issue. Accordingly, we will elaborate on the details of model architectures, including the matricesQ and M, in8 Section 3.2.2ofthemaintextrather Wedeeply acknowledge the valuable suggestion. B2: Whereasincluding29 intra-particle attention inB2 already notably improvestheperformance compared toB1,including population-based30 features and inter-particle attention inB3 presents the largest performance boost. This confirms that our method to31 majorly "benefit from the attention mechanisms"; iii)Proposed v.s.

Humans diminishes weightF ( ), theeventE = I {, i.e.

Are Labels Requiredfor Improving Adversarial Robustness?

However,evenwhentheprior is useful for generalization, distilling it to RL agent often interferes with RL training and degenerates sample efficiency.

Summation overi I decouples i from j and allows reuse of computation overj.