Polymer flooding is a widely used technique in enhanced oil recovery (EOR), but its effectiveness is often hindered by the poor viscosity retention of conventional polymers like hydrolyzed polyacrylamide (HPAM) under high-salinity conditions. Although recent advances in molecular engineering have concentrated on modifying polymer architecture and functional groups to address this issue, the complex interplay among polymer topology, charge distribution and hydrophilic-hydrophobic balance renders rational molecular design challenging. In this work, we present an AI-driven inverse design framework that directly maps target viscosity performance back to optimal molecular structures. Guided by practical molecular design strategies, the topological features (grafting density, side-chain length) and functional group-related features (copolymerization ratio, hydrophilic-hydrophobic balance) are encoded into a multidimensional design space. By integrating dissipative particle dynamics simulations with particle swarm algorithm, the framework efficiently explores the design space and identifies non-intuitive, high-performing polymer structure. The optimized polymer achieves a 12% enhancement in viscosity, attributed to the synergistic effect of electrostatic chain extension and hydrophobic aggregation. This study demonstrates the promise of AI-guided inverse design for developing next-generation EOR polymers and provides a generalizable approach for the discovery of functional soft materials.

Polymer informatics faces challenges owing to data scarcity arising from complex chemistries, experimental limitations, and processing-dependent properties. This review presents the recent advances in data-efficient machine learning for polymers. First, data preparation techniques such as data augmentation and rational representation help expand the dataset size and develop useful features for learning. Second, modeling approaches, including classical algorithms and physics-informed methods, enhance the model robustness and reliability under limited data conditions. Third, learning strategies, such as transfer learning and active learning, aim to improve generalization and guide efficient data acquisition. This review concludes by outlining future opportunities in machine learning for small-data scenarios in polymers. This review is expected to serve as a useful tool for newcomers and offer deeper insights for experienced researchers in the field.

Enhancing the mechanical properties is crucial for polyimide films, but the mechanical properties (Young's modulus, tensile strength, and elongation at break) mutually constrain each other, complicating simultaneous enhancement via traditional trial-and-error methods. In this work, we proposed a materials genome approach to design and screen phenylethynyl-terminated polyimides for films with enhanced mechanical properties. We first established machine learning models to predict Young's modulus, tensile strength, and elongation at break to explore the chemical space containing thousands of candidate structures. The accuracies of the machine learning models were verified by molecular dynamics simulations on screened polyimides and experimental testing on three representative polyimide films. The performance advantages of the best-selected polyimides were analyzed by comparing well-known polyimides based on molecular dynamics simulations, and the structural rationale was revealed by "gene" analysis and feature importance evaluation. This work provides a cost-effective strategy for designing polyimide films with enhanced mechanical properties.

The self-assembly of block copolymers serves as an effective approach for fabricating various periodic ordered nanostructures. By employing self-consistent field theory (SCFT) to calculate the phase diagrams of block copolymers, one can accurately predict their self-assembly behaviors, thus providing guidance for the fabrication of various novel structures. However, SCFT is highly sensitive to initial conditions because it finds the free energy minima through an iterative process. Consequently, constructing phase diagrams using SCFT typically requires predefined candidate structures based on the experience of researchers. Such experience-dependent strategies often miss some structures and thus result in inaccurate phase diagrams. Recently, artificial intelligence (AI) techniques have demonstrated significant potential across diverse fields of science and technology. By leveraging AI methods, it is possible to reduce reliance on human experience, thereby constructing more robust and reliable phase diagrams. In this work, we demonstrate how to combine AI with SCFT to automatically search for self-assembled structures of block copolymers and construct phase diagrams. Our aim is to realize automatic construction of block copolymer phase diagrams while minimizing reliance on human prior knowledge.

The optimization of polymer structures aims to determine an optimal sequence or topology that achieves a given target property or structural performance. This inverse design problem involves searching within a vast combinatorial phase space defined by components, sequences, and topologies, and is often computationally intractable due to its NP-hard nature. At the core of this challenge lies the need to evaluate complex correlations among structural variables, a classical problem in both statistical physics and combinatorial optimization. To address this, we adopt a mean-field approach that decouples direct variable-variable interactions into effective interactions between each variable and an auxiliary field. The simulated bifurcation (SB) algorithm is employed as a mean-field-based optimization framework. It constructs a Hamiltonian dynamical system by introducing generalized momentum fields, enabling efficient decoupling and dynamic evolution of strongly coupled structural variables. Using the sequence optimization of a linear copolymer adsorbing on a solid surface as a case study, we demonstrate the applicability of the SB algorithm to high-dimensional, non-differentiable combinatorial optimization problems. Our results show that SB can efficiently discover polymer sequences with excellent adsorption performance within a reasonable computational time. Furthermore, it exhibits robust convergence and high parallel scalability across large design spaces. The approach developed in this work offers a new computational pathway for polymer structure optimization. It also lays a theoretical foundation for future extensions to topological design problems, such as optimizing the number and placement of side chains, as well as the co-optimization of sequence and topology.

Advancing the integration of artificial intelligence and polymer science requires high-quality, open-source, and large-scale datasets. However, existing polymer databases often suffer from data sparsity, lack of polymer-property labels, and limited accessibility, hindering systematic modeling across property prediction tasks. Here, we present OpenPoly, a curated experimental polymer database derived from extensive literature mining and manual validation, comprising 3985 unique polymer-property data points spanning 26 key properties. We further develop a multi-task benchmarking framework that evaluates property prediction using four encoding methods and eight representative models. Our results highlight that the optimized degree-of-polymerization encoding coupled with Morgan fingerprints achieves an optimal trade-off between computational cost and accuracy. In data-scarce condition, XGBoost outperforms deep learning models on key properties such as dielectric constant, glass transition temperature, melting point, and mechanical strength, achieving R² scores of 0.65–0.87. To further showcase the practical utility of the database, we propose potential polymers for two energy-relevant applications: high temperature polymer dielectrics and fuel cell membranes. By offering a consistent and accessible benchmark and database, OpenPoly paves the way for more accurate polymer-property modeling and fosters data-driven advances in polymer genome engineering.

Large-scale molecular dynamics (MD) simulations of crosslinked epoxy with quantum-level accuracy while capturing complex reactivity is a compelling yet unrealized challenge. In this work, through the construction of a chemical-environment-directing dataset, a reactive machine learning force field that accurately captures both reactive events and thermos-mechanical properties is developed. The force field achieves energy and force root-mean-square errors of 1.3 meV/atom and 159 meV/Å, respectively, and operates approximately 1200 times faster than ab initio molecular dynamics. MD simulations demonstrate excellent predictive capabilities across multiple critical thermos-mechanical properties (radial distribution function, density, and elastic modulus), with results being well consistent with experimental values. In particular, the force field can provide accurate prediction of the bond dissociation energies for typical bonds with a mean absolute error of 7.8 kcal/mol (<8%), which enables the simulation of tensile-induced failure caused by chemical bond breaking. Our work demonstrates the capability of the machine learning force field to handle the extraordinary complexity of crosslinked epoxy systems, providing a valuable blueprint for future development of more generalized reactive force fields applicable to most polymers.

The facile synthesis of high-valued polymers from waste molecules or low-cost common chemicals presents a significant challenge. Here, we develop a series of degradable poly(thiocarbonate)s from the new step-growth polymerization of diols, carbonyl sulfide (COS, or carbon disulfide, CS₂), and dichlorides. Diols and dichlorides are common chemicals, and COS (CS₂) is released as industrial waste. In addition to abundant feedstocks, the method is efficient and performed under mild conditions, using common organic bases as catalysts, and affording unprecedented polymers. When COS, diols, and dihalides were used as monomers, optimized conditions could completely suppress the oxygen-sulfur exchange reaction, enabling the efficient synthesis of well-defined poly(monothiocarbonate)s with melting points ranging from 48 °C to 101 °C. These polymers, which have a structure similar to polyethylene with low-density in-chain polar groups, exhibit remarkable toughness and ductility that rival those of high-density polyethylene (melting point: 90 °C, tensile strength: 21.6±0.7 MPa, and elongation at break: 576%). Moreover, the obtained poly(monothiocarbonate)s can be chemically degraded by alcoholysis to yield small-molecule diols and dithiols. When CS₂ was used in place of COS, a pronounced oxygen-sulfur exchange reaction occurred. By optimizing reaction condition, it was found that polymers with ―S(C＝O)S― and ―S(C＝S)S― as the main repeating units exhibited high thermal stability and crystallinity. Thus, a new approach for regulating the structure of polythiocarbonates via the oxygen-sulfur exchange reaction is developed. Overall, the polymers hold great potential for green materials due to their facile synthesis, readily available feedstocks, excellent performance, and chemical degradability.

Photothermal therapy has been renowned for its non-invasive and highly precise approach in cancer treatment. Therefore, the synthesis of suitable photothermal agent has attracted wide attention. In this study, a non-covalent method for modifying carbon nanotube by hyaluronic acid based azo polymer was proposed. Hyaluronic acid based azo polymer was attached to the surface of carbon nanotube via the π-π interaction and hydrophobic interaction between azo moiety and the wall of carbon nanotube. After the self-assembly process, the modification was demonstrated with transmission electron microscopy, infrared spectra and thermal gravimetric analysis. The modified carbon nanotube (HA-MWCNT) was endowed with both the tumor cell targeting property of hyaluronic acid and the excellent photothermal effect of carbon nanotube, enabling it to serve as photothermal agent for eliminating tumor cells. Upon co-culture with HeLa cells, HA-MWCNT was proved to exhibit low cytotoxicity without irradiation. After being irradiated with infrared laser light, the HeLa cells cultured with HA-MWCNT perished due to the heat generated by the endocytosed HA-MWCNT, which attested to the potential of HA-MWCNT as a photothermal agent for cancer treatment.

Fluorescent polyurea-carbon dots (PU-CD) were successfully achieved through a co-pyrolysis technique, combining polyurea (PU) with carboxyl-containing carbon dots (PCD) at a temperature of 220 ºC. The PU was fabricated via a simple precipitation polymerization process using toluene diisocyanate in a water/acetone binary solvent system. PCD was generated by thermal treatment of poly(ethylene glycol) (PEG) at the same elevated temperature. To elucidate the structural characteristics of PU-CD, as well as its precursor components PU and PCD, a comprehensive suite of analytical techniques was employed, including transmission electron microscopy (TEM), Fourier transform infrared spectroscopy (FTIR), nuclear magnetic resonance (NMR), dynamic light scattering (DLS) and X-ray photoelectron spectroscopy (XPS). These analyses confirmed the formation of amide bonds resulting from the reaction between the terminal amines of PU and the carboxyl groups of PCD. An in-depth comparison of the fluorescence properties of PU-CD revealed marked enhancements in fluorescence intensity when contrasted with PU, PEG, and the individual PCD. The research explored the impact of various factors such as concentration, pH in aqueous solutions, and solvent type on the fluorescence emission of these materials, providing valuable insights into their emission mechanisms. It was particularly noteworthy that both PCD and PU-CD exhibited a confined-domain crosslink-enhanced emission effect. Utilizing the aqueous dispersion of PU-CD as a fluorescent probe, the detection of doxycycline (DOX), a long-acting, broad-spectrum, semi-synthetic tetracycline antibiotic, was achieved with a detection limit of 2.9×10^–7 mol/L. This study introduces a simple, green, and cost-effective fluorescent probe for the detection of DOX, which has significant potential for application in the realms of analytical chemistry and food safety monitoring in the future.

Dielectric films are critical components in the fabrication of capacitors. However, their reliance on petroleum-derived polymers presents significant environmental challenges. To address this issue, we report on a high-performance biomass-based dielectric material derived from vanillin (VA), a renewable aromatic aldehyde. Vanillin was first esterified to synthesize vanillin methacrylate (VMA), which was then copolymerized with methyl methacrylate (MMA) via free-radical polymerization to yield P(VMA-MMA). By crosslinking the aldehyde groups in VMA with the amine groups in the polyether amine D400 (PEA), we fabricated a series of P(VMA-MMA)@PEA dielectric films with precisely tunable crosslinking densities. The unique molecular structure of vanillin, featuring both a benzene ring and an ester group, facilitates strong δ-π interactions and dipolar polarization, synergistically enhancing energy storage density while minimizing dielectric loss. At an optimal P(VMA-MMA) ratio of 1:10 and 80% theoretical crosslinking degree, the dielectric constant reaches 3.4 at 10³ Hz, while the breakdown strength reaches 670.2 MV/m. Furthermore, the film exhibits an energy storage density of 7.1 J/cm³ at 500 MV/m while maintaining a charge-discharge efficiency exceeding 90%. This study demonstrates a green and reliable strategy for designing biomass-based dielectric materials and opens new avenues for the development of eco-friendly energy-storage technologies.

Sustained antigen release from delivery systems is a pivotal strategy to enhance vaccine-induced immune responses, primarily by mimicking the antigen exposure kinetics of natural infections to synchronously boost humoral and cellular immunity. However, the absence of an "antigen boost" effect in current approaches stands as a critical bottleneck, limiting the intensity and durability of immune responses. To address the critical gap of insufficient antigen boosting in sustained-release vaccine platforms, we engineered an ultrasound-responsive hydrogel (URH) with diselenide-functionalized 4-arm PEG-ONH₂ (4-arm PEG-Se-Se-ONH₂) , 4-arm PEG-ONH₂ and ODEX. Leveraging its exceptional ultrasonic sensitivity, the URH enables timely controlled, multiple-boost antigen release both in vitro and in vivo, overcoming the limitations of conventional sustained-release systems. With the multiple boost release mode triggered by ultrasound, the immune response in lymph nodes was significantly stronger than that in sustained release group without ultrasonic trigger. At the same time, it also greatly improved the humoral immunity level, URH+US-OVA elicited 7.5×10⁴-fold higher anti-OVA IgG titers over commercial Al-OVA vaccines and 440-fold higher than URH-OVA vaccines at day 40 post-vaccination, while the levels of blood routine and inflammatory factors were within the normal range, which proved that the safety of URH vaccines. The results support that the antigen release mode is a key factor affecting the immunological efficacy of vaccines, and URH can be modularized to regulate the multiple boost antigen release mode.

As a naturally occurring terpenoid that is abundant in essential oils, citronellal remains largely unexplored in polymer science. Herein, we present a novel strategy for converting bio-based citronellal into the diene monomer 6,10-dimethyl-1,3,9-undecatriene (DMUT), which undergoes neodymium-catalyzed coordination polymerization to yield poly(6,10-dimethyl-1,3,9-undecatriene) (PDMUT), a bio-derived polydiene polymer. This provides a facile and sustainable route for transforming renewable citronellal into functional polymers. The effects of polymerization conditions on the catalytic performance and polymer characteristics, including molecular weight, polydispersity, and microstructure, were systematically investigated. In addition, DMUT was successfully copolymerized with isoprene (IP) and 1,3-butadiene (BD), yielding copolymers with tunable compositions and microstructures. These results demonstrate the versatility of DMUT as a renewable building block for both homopolymers and copolymers, paving the way toward bio-based elastomeric materials with customizable properties.

Poly(vinylidene fluoride) (PVDF) foam has received widespread attention due to its high strength, and excellent combination of flame-retardancy, antibacterial performance, and chemical stability. However, the foaming ability of conventional PVDF is severely limited by its rapid crystallization kinetics and poor melt strength. Although ultra-high molecular weight PVDF (H-PVDF) theoretically offers prolonged melt elasticity favorable for foaming, the extremely high melt viscosity poses substantial processing challenges, and its foaming behavior has remained largely unexplored. To address these issues, this study proposes a novel fabrication strategy combining solvent casting with microcellular foaming to prepare H-PVDF foams. Dynamic mechanical analysis and differential scanning calorimetry reveal that extensive chain entanglements in H-PVDF impose constraints on crystallization and significantly enhance melt strength. By tuning the processing parameters, the distinctive foaming behavior of H-PVDF under various conditions is systematically elucidated. Remarkably, a record-high expansion ratio of 55.6-fold is achieved, accompanied by a highly uniform and fine cellular structure. The resulting H-PVDF foams exhibit a low thermal conductivity of 31.8 mW·m^–1·K^–1, while retaining excellent compressive strength, flame-retardancy, and hydrophobicity. These outstanding properties highlight the great potential of H-PVDF foams as the thermal insulation materials for applications in aerospace, energy infrastructure, and other extreme environments.

We report a general method for the synthesis of polymer-decorated metal-organic frameworks (MOFs) for the fabrication of superhydrophobic materials through photoinduced metal-free atom transfer radical polymerization (ATRP). Firstly, an MOF material, ZIF-8-NH₂, was synthesized through the self-assembly of metal ions and organic ligands at room temperature. ZIF-8-NH₂ was then reacted with glycidyl methacrylate (GMA) to form ZIF-8@GMA. Finally, ZIF-8@GMA-PHFBA was prepared by grafting fluorinated monomer 2,2,3,4,4,4-hexafluorobutyl acrylate (HFBA), from the ZIF-8@GMA surface via photoinduced ATRP under 365 nm UV light. The structural evolution during the metal-free ATRP modification of ZIF-8-NH₂ was characterized by Fourier transform infrared spectroscopy (FTIR), X-ray powder diffraction (XRD), X-ray photoelectron spectroscopy (XPS), scanning electron microscopy (SEM), and thermogravimetry analysis (TGA). The test results verified that ZIF-8-NH₂ and ZIF-8@GMA-PHFBA were successfully synthesized, and that the surface graft polymerization did not change the structure and morphology of ZIF-8-NH₂. After anchoring the ZIF-8@GMA-PHFBA hybrid material on the fabric surface, the water contact angle (WCA) of the ZIF-8@GMA-PHFBA hybrid material-modified fabric surface reached 154.2^o, which achieved a superhydrophobic state. In addition, the oil-water separation experiment and self-cleaning test demonstrated that the ZIF-8@GMA-PHFBA hybrid material-modified fabric has an excellent oil-water separation effect and self-cleaning performance. This material shows promising potential for applications in self-cleaning and oil-water separation technologies.

Semicrystalline polymers usually undergo multilevel microstructural evolutions with annealing and stretching processes, which is essential to tailor the physical properties of the polymer. Here, poly(butylene carbonate) (PBC) sheets were prepared via isothermal annealing and unidirectional pre-stretching processes, then the changes of PBC in crystallinity, mechanical properties, thermal properties and microscopic changes before and after annealing and stretching were measured, as well as the relationship between microstructure and macroscopic properties before and after stretching. The strengthening mechanism of PBC was also described. It was demonstrated that shish-kabab structure emerged under the pre-stretching process. With the increase of the tensile ratio, the crystallinity, structure and mechanical properties are increased differently. Among them, the crystallinity and tensile strength after annealing-stretching treatment increased to 24.45% and 104.5 MPa, respectively, which were about 1.55 times and 3.4 times of those without any treatment.

An inverse vulcanized polymer, SZIM combining Zn²⁺-imidazole coordination bonds and polysulfide bonds was synthesized and incorporated into bio-based Eucommia ulmoides gum (EUG) to generate EUG-SZIM-xs. The residual crystallinity of the EUG matrix synergistically interacted with the dual cross-linking networks to establish reversible deformation domains, providing EUG-SZIM-xs with quick shape memory capability at moderate temperatures. The damping properties were also investigated, and EUG-SZIM-xs displayed high tanδ values (>0.3) when the SZIM dosage was higher than 5.5 phr, which showed a positive correlation with SZIM concentration. Such good damping performance endowed the EUG-SZIM-xs with broadband low-frequency sound absorption. In addition, the dual cross-linking networks endowed the materials with reprocessability under different catalytic systems, and the 1,8-diazobicyclic[5.4.0]undeca-7-ene (DBU)-catalyzed samples exhibited better mechanical properties than EUG-SZIM-xs.

The phenomena of thermal runaway and accidental deformation due to external stresses in lithium batteries or film capacitors constitute their primary failure mechanisms. Therefore, monitoring and early warning of overheating or localized strain are of great value for the safe use of lithium batteries or film capacitors; however, this function usually requires a system of multiple complex sensors. The realization of the above multiple hazards using a single sensor for monitoring and alarm functions has not been reported. Here, we exploit the thermally induced conductivity and modulus change during solid-liquid conversion of low melting point polyalloys to modulate the electronic relaxation polarization and interfacial polarization in the composites for dielectric switching, and the reduction of alloy particle spacing during bending/compressive strain can be used to generate switchable tunneling effects for insulator-conductor transition. By synergizing dielectric switching and insulator-conductor transition, the final flexible thermoplastic polyurethane elastomer/low-melting-point polyalloy composite film achieves the functional integration of multi-level overheating warning and small deformation monitoring.

Eutectogels are considered to have immense application potential in the field of flexible wearable ionotronic devices because of their excellent ionic conductivity, thermal and electrochemical stability, and non-volatility. However, most existing technologies still struggle to achieve synergistic optimization of key performance indicators, such as high mechanical strength and ionic conductivity. To address this challenge, this study successfully prepared a green eutectogel material with outstanding comprehensive properties by leveraging the high solubility of glycerol in a polymerizable deep eutectic solvent (DES) composed of acrylic acid and choline chloride. The resulting eutectogels exhibited a high transparency (89%), high mechanical strength (up to 2.8 MPa), and exceptional tensile performance (up to 1385%). The fabricated flexible sensor demonstrated ideal linear sensitivity (gauge factor: 0.88), a broad response range (1%–100%), and reliable stability (over 1000 cycles), enabling the precise monitoring of human motion (e.g., finger bending and wrist rotation). The flexible strain sensor based on this eutectogel is expected to show promising prospects for medical monitoring, human-machine interaction, and industrial sensing applications.

Flexible wearable electronic devices based on hydrogels have immense potential in a wide range of applications. However, many existing strain sensors suffer from significant limitations including poor mechanical properties, low adhesion, and insufficient conductivity. To address these challenges, this study successfully developed an organic-inorganic double-network conductive hydrogel using acrylic-modified bentonite (AABT) as a key component. The incorporation of AABT significantly enhanced the mechanical properties of the ATHG@LiCl hydrogel, achieving an impressive stretchability of 4000% and tensile strength of 250 kPa. Moreover, it improved the electrical conductivity of the hydrogel to a maximum of 1.53 mS/cm. The catechol structure of tannic acid (TA) further augmented the adhesive properties of the ATHG@LiCl hydrogel toward various substrates such as copper, iron, glass, plastic, wood, and pigskin. The addition of lithium chloride (LiCl) and dimethyl sulfoxide (DMSO) endowed the hydrogel with exceptional freezing resistance and flexibility, even at low temperatures of −20 °C. Remarkably, the hydrogel maintained a conductivity of 0.53 mS/cm under these conditions, surpassing the performance of many other reported hydrogels. Furthermore, the ATHG@LiCl hydrogel demonstrated outstanding characteristics, such as high sensitivity (gauge factor GF=4.50), excellent transparency (90%), and reliable strain-sensing capabilities, indicating that the ATHG@LiCl hydrogel is a highly promising candidate for flexible wearable soft materials, offering significant advancements in both functionality and performance.

The flocculation behavior of carbon black (CB)-filled isoprene rubber (IR) nanocomposites was systematically investigated under both dynamic and static conditions to unravel the distinct mechanisms governing filler network evolution. Under dynamic conditions, small oscillatory shear strains (0.1%) significantly enhanced filler particle motion, leading to pronounced agglomeration and a flocculation degree of about 4.3 MPa at 145 °C. In contrast, static flocculation exhibited a fundamentally different mechanism dominated by polymer chain dynamics, which is driven mainly by thermal activation. Radial distribution function (RDF) analysis of transmission electron microscopy (TEM) images revealed a slight decrease (2 nm) in the interparticle distance peak after static annealing at 100 °C for 7 h, indicating localized motion of CB particles. However, the overall filler network remained stable, with no significant agglomeration observed. The increase in bound rubber content from about 23% to 28% with rising temperature further confirmed the dominant role of polymer chain adsorption and interfacial reinforcement in static flocculation. These findings highlight the critical influence of external strain on filler network formation and provide new insights into the polymer-dominated mechanism of static flocculation. The results offer practical guidance for optimizing the storage and processing of rubber nanocomposites, particularly in applications where static flocculation during prolonged storage is a concern.

Stimuli-responsive polymers capable of rapidly altering their chain conformation in response to external stimuli exhibit broad application prospects. Experiments have shown that pressure plays a pivotal role in regulating the microscopic chain conformation of polymers in mixed solvents, and one notable finding is that increasing the pressure can lead to the vanishing of the co-nonsolvency effect. However, the mechanisms underlying this phenomenon remain unclear. In this study, we systematically investigated the influence of pressure on the co-nonsolvency effect of single-chain and multi-chain homopolymers in binary mixed good-solvent systems using molecular dynamics simulations. Our results show that the co-nonsolvency-induced chain conformation transition and aggregation behavior significantly depend on pressure in all single-chain and multi-chain systems. In single-chain systems, at low pressures, the polymer chain maintains a collapsed state over a wide range of co-solvent fractions (x-range) owing to the co-nonsolvency effect. As the pressure increases, the x-range of the collapsed state gradually narrows, accompanied by a progressive expansion of the chain. In multichain systems, polymer chains assemble into approximately spherical aggregates over a broad x-range at low pressures owing to the co-nonsolvency effect. Increasing the pressure reduces the x-range for forming aggregates and leads to the formation of loose aggregates or even to a state of dispersed chains at some x-range. These findings indicate that increasing the pressure can weaken or even offset the co-nonsolvency effect in some x-range, which is in good agreement with the experimental observations. Quantitative analysis of the radial density distributions and radial distribution functions reveals that, with increasing pressure, (1) the densities of both polymers and co-solvent molecules within aggregates decrease, while that of the solvent molecule increases; and (2) the effective interactions between the polymer and the co-solvent weaken, whereas those between the polymer and solvent strengthen. This enhances the incorporation of solvent molecules within the chains, thereby weakening or even suppressing the chain aggregation. Our study not only elucidates the regulatory mechanism of pressure on the microscopic chain conformations and aggregation behaviors of polymers, but also may provide theoretical guidance for designing smart polymeric materials based on mixed solvents.