Large Language Models (LLMs) and Evolutionary Computation (EC) are increasingly being combined to support automated optimization, algorithm design, and adaptive decision-making. This survey reviews the bidirectional interaction between these two paradigms and examines how their complementary strengths can be leveraged in hybrid intelligent systems. First, we analyze how EC can enhance LLM-based systems through prompt optimization, hyperparameter tuning, and architecture search. Second, we review how LLMs can improve EC by supporting metaheuristic design, surrogate reasoning, adaptive operator control, and heuristic generation. We further discuss emerging co-adaptive frameworks in which LLMs and EC interact through iterative feedback loops. Beyond summarizing recent developments, the survey provides a structured perspective on interaction mechanisms, application patterns, and methodological challenges, including computational cost, reproducibility, interpretability, benchmarking, and generalization. The paper concludes by outlining open research questions and future directions for developing more robust, transparent, and scalable LLM-EC systems.
PET circularity is often evaluated by recovery volumes, although performance ultimately depends on whether recovered material can be converted into quality-assured outputs and absorbed by viable end markets. Yet the mechanisms connecting policy, markets, technology, and stakeholder behavior remain dispersed across heterogeneous evidence. We developed a source-attributed, time-stamped causal-network approach using 750 Australian government, industry and NGO, corporate, and media documents published during 2010–2025. Causal extraction, semantic normalization, sentiment assignment, and graph construction yielded 2794 factor nodes and 1588 unique causal edges. The network was strongly externalized: policy, market, and social factors were more numerous and highly connected than internal technical and operational factors. Persistent barriers combined cost and price volatility, inconsistent recyclate quality, infrastructure gaps, and weak policy implementation. Positive mechanisms clustered around standards and measurement, design for recyclability, operational capacity, and end-market development; their circular value depended on retained material quality and the end use reached. Source attribution revealed systematic framing differences, with media coverage concentrating negative implementation narratives. Temporal and regional analyses indicated a shift from limited attention to rapid expansion and subsequent consolidation, alongside national structural hubs and differentiated state pathways. A full-text academic shadow corpus preserved the broad problem domains but changed their hierarchy: academic evidence foregrounded material and processing mechanisms, whereas the primary corpus foregrounded institutional coordination and market implementation. The contribution is therefore not a universal ranking of Australian interventions, but an auditable framework for identifying how technical feasibility becomes, or fails to become, operational circularity under different institutional conditions.
Hydrogel-based plant bioelectronics are emerging as promising platforms for real-time monitoring and modulation of plant physiology, stress responses, environmental interactions, and growth. Compared with rigid electrodes and conventional polymer films, hydrogels provide a soft, hydrated, conductive, and tunable interface that reduces mechanical mismatch with growing plant tissues while enabling electrochemical, electrophysiological, optical, and multimodal sensing. This review examines recent advances in hydrogel materials for plant bioelectronics, focusing on how network structure, design requirements, materials strategies including crosslinking chemistry, porosity, swelling, adhesion, conductivity, transparency, gas permeability, and biocompatibility affect plant-device performance. Applications in monitoring plant physiology, hormones, pH, moisture, glucose, and overall plant health are highlighted. Reported hydrogel systems exhibit Young’s moduli from ∼ 1 kPa to several MPa and ionic conductivities of 10−3-10−1 S cm−1. Several plant-interfacing devices sustain strains above 300 %, maintain stable electrical performance over 10,000 loading cycles, and support continuous growth monitoring for up to 14 days. Despite these advances, standardised evaluation under realistic agricultural conditions remains limited. Future research should prioritise standardised testing, biodegradable biomass-derived materials, multimodal sensing integration, and closed-loop bioelectronic systems to advance precision agriculture and bio-regenerative life-support applications.
Osteoarthritis (OA) is a prevalent whole-joint disease that requires effective disease-modifying therapies. Intra-articular platelet-rich plasma (PRP) injections offer a minimally invasive treatment option, but face two coupled challenges: premature ex vivo activation causes rapid growth-factor release before injection, and the inflamed, protease-rich synovial microenvironment accelerates their subsequent degradation. To address these barriers, we report an injectable dual-component hyaluronic acid (HA) hydrogel depot (PRP@Gel) that combines dynamic covalent HA-based delivery with a calcium-containing matrix designed to facilitate PRP activation and sustained immunomodulation. Distinct from conventional HA/PRP hydrogels that mainly improve local retention or deliver pre-activated PRP, PRP@Gel uses a calcium-integrated AHA-Ca backbone to support gradual post-injection PRP activation within the joint cavity, thereby limiting burst release of platelet-derived factors. Sustained calcitriol release concurrently promoted a tolerogenic DC phenotype in vitro and was associated with a shift from Th17-related responses toward Treg-related features. This immune modulation was associated with reduced MMP3 and CTSK expression, which may establish a less proteolytic microenvironment for PRP-derived factors. In a rat OA model, PRP@Gel treatment improved gait symmetry and cartilage integrity. Together, these findings support an integrated strategy that coordinates PRP activation with immune modulation to sustain regenerative signaling in OA joints.
This project addresses the global challenges of an ageing population and rapid urbanisation by exploring how citizen science can support the engagement of older adults in shaping age-friendly green spaces. Conducted in the City of Unley, South Australia, the study engaged 30 older residents (aged 60+) as citizen scientists to trial a multi-format audit tool and co-reflect on its use in practice for creating age-friendly environments, generating practical insights for future research and design practice. Integrating audits into participants’ daily routines and everyday life spaces ensured that findings reflected lived experiences. Citizen science was not merely a data collection tool but a sustained dialogue, with regular workshops and informal café sessions supporting motivation, peer learning, and collaborative analysis. Participants reported challenges such as sustaining long-term motivation, but also highlighted opportunities for empowerment, confidence-building, and strengthened community ties. Importantly, many older adults described shifts in how they experienced their environments—becoming more observant, extending their walking habits, and growing more confident in voicing ideas. Several participants continued their civic engagement beyond the project, illustrating the lasting impact of participation. The study contributes methodological insights into designing inclusive citizen science initiatives, offering guidance on recruitment, tool development, and engagement strategies tailored to older populations. Overall, this study demonstrates the power of citizen science not only to generate grounded data but also to empower older adults and co-produce inclusive urban knowledge. Findings provide process-focused insights into age-friendly engagement and illustrate the broader potential of citizen science in shaping equitable, community led public spaces. Overall, this research demonstrates how citizen science can move beyond data collection to become a co-creative process that empowers older adults and informs age-friendly urban transformation.
