Existing multi-agent learning approaches have developed interactive training environments to explicitly promote collaboration among multiple Large Language Models (LLMs), thereby constructing stronger multi-agent systems (MAS). However, during inference, they require re-executing the MAS to obtain final solutions, which diverges from human cognition that individuals can enhance their reasoning capabilities through interactions with others and resolve questions independently in the future. To investigate whether multi-agent interaction can enhance LLMs' independent problem-solving ability, we introduce ILR, a novel co-learning framework for MAS that integrates two key components: Dynamic Interaction and Perception Calibration. Specifically, Dynamic Interaction first adaptively selects either cooperative or competitive strategies depending on question difficulty and model ability. LLMs then exchange information through Idea3 (Idea Sharing, Idea Analysis, and Idea Fusion), an innovative interaction paradigm designed to mimic human discussion, before deriving their respective final answers. In Perception Calibration, ILR employs Group Relative Policy Optimization (GRPO) to train LLMs while integrating one LLM's reward distribution characteristics into another's reward function, thereby enhancing the cohesion of multi-agent interactions. We validate ILR on three LLMs across two model families of varying scales, evaluating performance on five mathematical benchmarks and one coding benchmark. Experimental results show that ILR consistently outperforms single-agent learning, yielding an improvement of up to 5% over the strongest baseline. We further discover that Idea3 can enhance the robustness of stronger LLMs during multi-agent inference, and dynamic interaction types can boost multi-agent learning compared to pure cooperative or competitive strategies.

Much effort has been devoted to accelerate the process.

Real-world optimization problems often involve complex objective functions with costly evaluations. While Bayesian optimization (BO) with Gaussian processes is effective for these challenges, it suffers in high-dimensional spaces due to performance degradation from limited function evaluations. To overcome this, simplification techniques like dimensionality reduction have been employed, yet they often rely on assumptions about the problem characteristics, potentially underperforming when these assumptions do not hold. Trust-region-based methods, which avoid such assumptions, focus on local search but risk stagnation in local optima. In this study, we propose a novel acquisition function, regional expected improvement (REI), designed to enhance trust-region-based BO in medium to high-dimensional settings. REI identifies regions likely to contain the global optimum, improving performance without relying on specific problem characteristics. We provide a theoretical proof that REI effectively identifies optimal trust regions and empirically demonstrate that incorporating REI into trust-region-based BO outperforms conventional BO and other high-dimensional BO methods in medium to high-dimensional real-world problems.

Auction is one of the most representative buying-selling systems. A celebrated study shows that the seller's expected revenue is equal in equilibrium, regardless of the type of auction, typically first-price and second-price auctions. Here, however, we hypothesize that when some auction environments vary with time, this revenue equivalence may not be maintained. In second-price auctions, the equilibrium strategy is robustly feasible. Conversely, in first-price auctions, the buyers must continue to adapt their strategies according to the environment of the auction. Surprisingly, we prove that revenue equivalence can be broken in both directions. First-price auctions bring larger or smaller revenue than second-price auctions, case by case, depending on how the value of an item varies. Our experiments also demonstrate revenue inequivalence in various scenarios, where the value varies periodically or randomly. This study uncovers a phenomenon, the breaking of revenue equivalence by the time-varyingness in auctions, that likely occurs in real-world auctions, revealing its underlying mechanism.

Solutions of bilevel optimization problems tend to suffer from instability under changes to problem data. In the optimistic setting, we construct a lifted, alternative formulation that exhibits desirable stability properties under mild assumptions that neither invoke convexity nor smoothness. The upper- and lower-level problems might involve integer restrictions and disjunctive constraints. In a range of results, we at most invoke pointwise and local calmness for the lower-level problem in a sense that holds broadly. The alternative formulation is computationally attractive with structural properties being brought out and an outer approximation algorithm becoming available.

Binary Classification plays an important role in machine learning. For linear classification, SVM is the optimal binary classification method. For nonlinear classification, the SVM algorithm needs to complete the classification task by using the kernel function. Although the SVM algorithm with kernel function is very effective, the selection of kernel function is empirical, which means that the kernel function may not be optimal. Therefore, it is worth studying how to obtain an optimal binary classifier. In this paper, the problem of finding the optimal binary classifier is considered as a variational problem. We design the objective function of this variational problem through the max-min problem of the (Euclidean) distance between two classes. For linear classification, it can be deduced that SVM is a special case of this variational problem framework. For Euclidean distance, it is proved that the proposed variational problem has some limitations for nonlinear classification. Therefore, how to design a more appropriate objective function to find the optimal binary classifier is still an open problem. Further, it's discussed some challenges and problems in finding the optimal classifier.

We study a model of machine teaching where the teacher mapping is constructed from a size function on both concepts and examples. The main question in machine teaching is the minimum number of examples needed for any concept, the so-called teaching dimension. A recent paper [7] conjectured that the worst case for this model, as a function of the size of the concept class, occurs when the consistency matrix contains the binary representations of numbers from zero and up. In this paper we prove their conjecture. The result can be seen as a generalization of a theorem resolving the edge isoperimetry problem for hypercubes [12], and our proof is based on a lemma of [10].