The Emergent Modular Atomic Network (EMAN), an optimization-driven framework for exposing an antisymmetric growth direction through latent relative phases without instantiating a second path, and for monitoring multiple decision signals during training to transform local optimization evidence into a structural decision is proposed.
Abstract
Existing multi-task learning methods rely on hard sharing, multiple paths or experts, adaptive sharing, and dynamic expansion. However, their capacity changes are usually constrained by predefined structures or triggered by task boundaries and conflict signals. This raises a fundamental question: can a network start from exact single-path computation and grow a new independent path only when persistent optimization evidence appears? We propose the Emergent Modular Atomic Network (EMAN), an optimization-driven framework for exposing an antisymmetric growth direction through latent relative phases without instantiating a second path, and for monitoring multiple decision signals during training to transform local optimization evidence into a structural decision. EMAN materializes two equal-capacity independent paths only after certification. EMAN adaptively allocates shared and task-specific representation capacity to accommodate varying task requirements. Extensive experiments on controlled rank settings, PASCAL-Context, and NYUv2 validate its effectiveness, achieving improved performance at a competitive computational cost.
Class-incremental learning is commonly instantiated as a single-model paradigm, where a unified model sequentially adapts to an unbounded stream of sessions. While effective under mild distributional shifts, this formulation becomes strained when successive sessions induce incompatible optimization directions, leading to destructive interference and catastrophic forgetting. We argue that such forgetting reflects a structural limitation of enforcing heterogeneous learning dynamics within a single parameter space. Motivated by social solidarity theory, we propose Socialized Division and Collaboration (SDC) as a reformulation of continual learning that decomposes session learning across specialized models in response to optimization conflicts, while enabling coordinated collaboration. To support this formulation with a principled allocation mechanism, we introduce an energy-based session-model compatibility criterion grounded in Helmholtz free energy, which guides adaptive session allocation and model evolution under conflicting objectives. This framework integrates session assignment, model evolution, and collaborative inference into a unified pipeline, offering an alternative to monolithic continual learning formulations and highlighting a broader design principle for learning under persistent optimization conflicts.
Xinjie Yao, Zhihe Fan, Yunqi Zhu et al.· 0 citations
A graph attention network-enhanced multi-agent proximal policy optimization (GAT-MAPPO) framework is proposed for cooperative guidance in adversarial engagement scenarios. A dynamic heterogeneous interaction graph is formulated over interceptors and targets at every decision epoch. Through a multi-head graph attention encoder, relational features capturing both inter-interceptor cooperation and target threat dynamics are adaptively aggregated. These graph-enriched observations are processed by a Centralized-Training, Decentralized-Execution (CTDE) MAPPO architecture, guided by a hierarchical reward function that mandates miss distance minimization, simultaneity of arrival consensus, multi-directional encirclement, and smooth control effort. Furthermore, the integration of a three-stage curriculum learning strategy allows for robust cooperative policy derivation across transitions from rectilinear to highly adaptive evasion patterns, eliminating the need for explicit rule engineering. Extensive Monte Carlo simulations confirm GAT-MAPPO’s superior performance: achieving >95% interception success rate in 4-vs.-4 scenarios and reducing mean simultaneity error by 41.4% compared to the MAPPO baseline. Comprehensive ablation and sensitivity studies validate the critical roles played by graph attention encoding, reward hierarchy design, and progressive curriculum staging.
Diffusion models have strong generative capabilities. However, their maximum likelihood training objective only focuses on reconstructing the data distribution, making it difficult to align with specific preferences. Reinforcement learning (RL) for preference alignment in diffusion models is promising but limited by reward sparsity. Since a single reward cannot support optimization, existing RL methods usually backpropagate the final reward to all previous steps. However, denoising is stage-wise, with distinct semantics and controllability. Repeating the final reward across all steps creates a temporal objective mismatch, encouraging reward shortcuts that lead to reward hacking. At the same time, due to reward backfilling, each time step receives the same reward, making it impossible to distinguish between actions, thereby weakening the optimization process. To resolve this issue, we propose Stage-Guided Per-Step Optimization (SGPO) for diffusion models, which jointly leverages signal-to-noise ratio and semantic changes to identify generation stages and adaptively assign stage-specific objectives. Early denoising is chaotic and far from the final reward, resulting in weak reward-behavior correlation. This stage should prioritize exiting the chaotic state. In the mid stage, the latent transitions to a stable structure, where the final reward better corresponds to generative behavior. Therefore, this stage optimizes the final reward while exploring diversity to avoid early convergence to a single mode. In the late stage, the latent's core structure is largely fixed, and preference optimization mainly amplifies local details, risking overfitting. Therefore, stable convergence is preferred to avoid quality degradation. Results from 16 comparative experiments validate SGPO. Our method achieves 26.7% average gains in generative quality and 36.7% higher convergence speed.
Renye Yan, Jikang Cheng, You Wu et al.· 0 citations
Click-through rate (CTR) prediction is a pivotal component in large-scale industrial systems. Historically, CTR prediction paradigms have been confined to monolithic architectures governed by a single-policy optimization process. However, such isolated learning paths lack the intrinsic evolutionary mechanisms necessary for optimal convergence. Without policy diversity and internal competition, models tend to get trapped in local optima as performance reaches saturation, hindering further breakthroughs in modeling capacity. In this paper, we propose DPEO (Dynamic Preference Evolution Optimization), a co-evolutionary framework that transforms CTR modeling into a dynamic policy contention task. DPEO decouples the monolithic architecture into dual sub-learners to induce policy diversity, constructing an internal preference landscape without external rewards. A performance-driven Role Arbiter then dynamically designates the superior sub-learner as the Reference Policy and the other sub-learner as the Target Policy per batch, driving continuous model evolution. Through an asymmetric gradient flow, the target policy is optimized to surpass the reference policy in both probability and logit spaces. This process drives a co-evolution, enabling the sub-learners to serve as alternating evolutionary benchmarks and 'self-evolve' toward the global optimum. Extensive experiments on public benchmarks and a massive industrial dataset with over 10 billion samples demonstrate that DPEO significantly outperforms state-of-the-art models.
Kun Yao, Congcong Liu, Ziheng Ni et al.· Annual International ACM SIG...· 0 citations
Large language models (LLMs) are increasingly deployed in enterprise settings, yet individual models remain bounded by model-specific capability limitations. These heterogeneous boundaries pose a deployment challenge, but also create an opportunity: strategically coordinating multiple LLMs may unlock collective intelligence exceeding any single model. Existing approaches fix how models are combined in advance, overlooking the dynamic, state-dependent role of complementarity in complex problem solving. Drawing on the wisdom-of-crowds paradigm, we reconceptualize collective LLM intelligence as relay-style complementarity: a sequential process in which each successor model is selected to address the specific bottleneck identified in its predecessor's output. To operationalize this, we propose WILC (Wisdom Integration of LLM Crowds), a framework grounded in two design principles. First, iterative reflection-and-refinement establishes a state-preserving workflow through which models diagnose and refine prior outputs. Second, complementarity-driven model selection governs transitions via a dual-gate mechanism: prospective complementarity fit (PCF) identifies the worker most suited to the current bottleneck, while posterior complementarity gain (PCG) evaluates whether the selected transition improves the evolving solution. Experiments across four diverse benchmarks show that WILC outperforms existing approaches, including single-model self-refinement, ensemble methods, and query-routing methods. Under standardized pricing assumptions, WILC matches the average benchmark performance of GPT-5.2 at roughly 7 times lower estimated per-query cost, while facilitating data sovereignty through self-hosted deployment. This study extends wisdom-of-crowds theory from static aggregation to sequential AI complementarity and provides transferable design principles for multi-AI coordination.
