This work proposes Socialized Division and Collaboration as a reformulation of continual learning that decomposes session learning across specialized models in response to optimization conflicts, while enabling coordinated collaboration and introduces an energy-based session-model compatibility criterion grounded in Helmholtz free energy.
Abstract
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.
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.
Chen Fang, Jingchen Li, Hong-Zong Li et al.· 0 citations
The rapid integration of artificial intelligence (AI) into society has surfaced systemic risks, particularly deep polarization exacerbated by algorithms optimizing for individual engagement. The dominant alignment paradigm, reliant on unilateral control (e.g., RLHF), is ill-suited to address these emergent collective dynamics. This paper proposes a philosophical and computational shift toward symbiotic alignment (SA), moving beyond top-down constraints to a framework of mutual adaptation and co-evolution. We ground SA in collective predictive coding (CPC), reframing human-AI symbiosis as participation in a symbol emergence system (SES). Mathematically, we formalize this interaction as multi-agent reinforcement learning (MARL) augmented by a collective regularization term, driving agents to minimize collective free energy (CFE) while preserving individual autonomy. Crucially, this formulation reveals that social coherence does not require uniformity; within this framework, we computationally reinterpret "plurality" as a stable multimodal distribution of shared beliefs, where diverse worldviews coexist through mutual negotiation. We conclude by outlining the research agenda for realizing this vision: designing AI agents capable of co-creative learning and social mechanisms ("gardeners") that foster trust, thereby steering our technological future toward a flourishing plurality.
While diffusion-based models have shown remarkable generative capabilities in static settings, their extension to continual learning (CL) scenarios remains fundamentally constrained by Generative Catastrophic Forgetting (GCF). We observe that even with a rehearsal buffer, new generative skills often overwrite previous ones, degrading performance on earlier tasks. Although some initial efforts have explored this space, most rely on heuristics borrowed from continual classification methods or use trained diffusion models as ad hoc replay generators, lacking a principled, unified solution to mitigating GCF and often conducting experiments under fragmented and inconsistent settings. To address this gap, we introduce the Continual Diffusion Generation (CDG), a structured pipeline that redefines how diffusion models are implemented under CL and enables systematic evaluation of GCF. Beyond the empirical pipeline, we propose the first theoretical foundation for CDG, grounded in a cross-task analysis of diffusion-specific generative dynamics. Our theoretical investigation identifies three fundamental consistency principles essential for preserving knowledge in the rehearsal buffer over time: inter-task knowledge consistency, unconditional knowledge consistency, and prior knowledge consistency. Motivated by these insights, we further propose Continual Consistency Diffusion (CCD), a principled training framework that enforces these consistency objectives via hierarchical loss functions: <inline-formula> <tex-math notation="LaTeX">${\mathcal {L}}_{IKC}$ </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX">${\mathcal {L}}_{UKC}$ </tex-math></inline-formula>, and <inline-formula> <tex-math notation="LaTeX">${\mathcal {L}}_{PKC}$ </tex-math></inline-formula>. This framework fosters long-term retention of generative knowledge and stable integration of new capabilities. Experiments show that CCD achieves state-of-the-art continual performance across various benchmarks, especially improving continual generative metrics in overlapping-task scenarios.
Jingren Liu, Zhong Ji, Shuning Xu et al.· IEEE Transactions on Image P...· 2 citations
Aligning large language models (LLMs) with human values remains a major challenge, especially for trustworthy AI. While existing approaches such as RLHF, CAI, and their variants have achieved promising results, they often rely on a single-agent framework and a unified reward system. This limits their ability to capture ethical pluralism, adapt to diverse moral contexts, and reflect the dynamics of multi-agent moral reasoning. In this work, we propose a framework that utilizes multilayer combinatorial fusion for contextual value alignment (MCF-CVA). At the first layer of the framework, it instantiates multiple moral agents, each fine-tuned to represent a distinctive value. Their outputs are then expanded combinatorially using both score- and rank-combinations as well as average and weighted aggregations. These combined models are then reduced to the same number of initial moral agents. This expansion and reduction (EAR) process continues for multi-layers until a stopping criterion is reached. The MCF-CVA framework leverages cognitive diversity between agents to mitigate conflicts and redundancies across multiple agents, producing responses that better reflect contextual human values. The framework using the EAR algorithm is performed on the dual architecture of Euclidean score space and Kemeny rank space. Empirical evaluations demonstrated that the proposed framework outperforms single-agent baselines, multi-agent single-layer results, and previous aggregation approaches on standard metrics, showing that the MCF-CVA framework provides a robust and effective mechanism for advancing contextual value alignment in LLMs.
Yuanhong Wu, Djallel Bouneffouf, D. Hsu· 0 citations
Social intelligence enables agents to read social context, infer intent, and adapt over sustained dialogue. As language models become autonomous collaborators, it is central to building effective and trustworthy human-AI interaction. Existing reinforcement learning methods optimize single-turn utterances and sparse outcome rewards, producing short-sighted policies that struggle to manage goal-relationship tensions across multi-turn interactions. We propose SocialRL, a multi-turn reinforcement learning framework addressing both challenges. First, we apply multi-turn reinforcement learning using PPO that propagates delayed outcome rewards back to each turn, enabling long-horizon planning. Second, we design six process reward dimensions capturing the goal-relationship trade-off, including goal advancement, relational attunement, contextual coherence, etc. A reward model dynamically generates fine-grained scoring criteria for each dimension, while a stage-aware weight schedule prioritizes relationship-building in early turns, goal advancement mid-way, and balanced closure late. Across multiple social-dialogue benchmarks, SocialRL improves Goal Achievement by an average of 9.2 percentage points over the corresponding Base models. These results demonstrate the effectiveness of SocialRL across synthetic and real social scenes, as well as standard and challenging social scenarios.
Jia-Ning Wang, Xin-Tao Wang, Aili Chen et al.· 0 citations
We introduce Personalized and Reliable Popular Science Writing, a novel task that requires adapting scientific explanations to audiences with different cognitive levels while preserving factual accuracy. However, improving personalization often introduces simplifications that increase the risk of hallucination and factual distortion. To address these challenges, we first construct a dataset of 39,134 entries and a reader-centric Personalized Science Communication Benchmark (PSCB) that jointly evaluates audience adaptation and factual accuracy. To reduce data and computational requirements while improving generalization across domains and audiences, we introduce DA-MoE, which explicitly decouples audience adaptation from domain knowledge through separate modeling. To enable robust verification and revision in evidence-scarce scenarios, a multi-agent fact-checking mechanism that augments limited evidence with role-specific agent debate and propagates confidence over a graph is proposed. Experiments on PSCB show that our approach achieves state-of-the-art performance. Our code is open-sourced at https://github.com/DPInnovationWorks/CWF.
Rui-Biao Fu, Di Tang, Yun-Long Yang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
