❌

Reading view

Foaming photopolymers as a high-resolution biomimetic printing platform

Nature, Published online: 09 September 2026; doi:10.1038/s41586-026-10968-9

Deep-foam photolithography uses light-controlled polymer foaming to create high-resolution, multifunctional microstructures with tunable optical, wetting and fluid-handling properties for advanced manufacturing applications.
  •  

EchoDistill:Alignment Noisy-to-Clean Self-Distillation for Robust Audio LLMs

arXiv:2605.23954v1 Announce Type: cross Abstract: Audio Large Language Models (ALLMs) are highly vulnerable to real-world noise, which often induces severe semantic drift and hallucinations. Existing robustness methods primarily rely on waveform-level acoustic enhancement, answer-level supervision, or the internal suppression of noise representations. To address these issues, we propose echodistill, an alignment-based noisy-to-clean self-distillation framework. Echodistill leverages a frozen clean-audio teacher to provide semantic references for an inference-time noisy-audio student. Specifically, the student samples candidate responses under noisy conditions to expose its test-time behavior. These trajectories are then optimized via group-relative policy optimization (GRPO), where the token-level consistency with the teacher acts as a reward bonus. By aligning the noisy student's candidate responses with clean semantic evidence, and applying audio-aware reward shaping, our method encourages reasoning trajectories that are both correct and genuinely acoustically grounded. Echodistill significantly improves the semantic reliability and task performance of Audio LLMs under complex noise, without introducing any additional inference costs. Extensive experiments show that: (I) Compared with the strongest baseline, echodistill achieves average improvements of 4.18\%$\uparrow$ in GSR under strong noise. (II) Ablation results on Qwen-Omni further show that echodistill improves over the GRPO-only variant by 3.02\%$\uparrow$ in Acc, 3.89\%$\uparrow$ in Noisy, and 4.53\%$\uparrow$ in GSR on average. Our codes are available at https://anonymous.4open.science/r/echodistill-10DE.
  •  

Parameter Efficient Multi-Class Intelligent Scheduling for Multimodal Online Distributed Industrial Anomaly Detection

arXiv:2605.23984v1 Announce Type: cross Abstract: Industrial anomaly detection has attracted significant attention as a fundamental challenge in industrial systems. The rapid advancement of heterogeneous industrial sensors has driven industrial anomaly detection from unimodal to multimodal paradigms. However, existing methods are primarily designed for centralized and offline settings, overlooking the distributed and continuously generated data characteristic of real-world industrial environments. With the advancement of edge intelligence, modern edge devices are increasingly capable of not only data acquisition but also distributed model training, enabling collaborative intelligence across the system. Industrial anomaly detection represents a critical application in this context. Motivated by these challenges, we propose a novel framework termed Multimodal Online Distributed Industrial Anomaly Detection (MODIAD). We first present a comprehensive workflow for MODIAD and then formulate a Multi-class Intelligent Scheduling (MIS) problem to coordinate cross class model updates by balancing data sufficiency and class update frequency. To efficiently solve this problem, we design a Sequential Marginal Gain Greedy (SMG) algorithm that enables effective multi-class training under resource constraints. Furthermore, to improve the computational and communication efficiency during training, we propose an Resource Efficient Class-Wise Low Rank Adaptation (REC-LoRA) strategy, which significantly reduces system overhead while preserving detection performance. Extensive experiments on two representative multimodal industrial anomaly detection datasets, MVTec 3D-AD and Eyecandies demonstrate that the proposed approach achieves superior performance and efficiency under the MODIAD scenario.
  •  

Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL

arXiv:2605.24001v2 Announce Type: cross Abstract: Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement learning methods for one-step generators combine image-space reward optimization with diffusion noisy-space distribution matching. This paradigm brings challenges due to a mismatch between terminal reward optimization and the underlying generative dynamics. As a result, optimization tends to exploit stochastic degrees of freedom, often improving reward at the expense of image fidelity. To address this issue, we propose Diff-Instruct with Diffused Reward (DIDR), a data-free trajectory-level alignment framework derived from Integral KL minimization. DIDR propagates the RLHF-optimal reward-tilted clean-image distribution across all noise levels along the diffusion trajectory. We show that this objective admits the same minimizer as clean-image RLHF, while naturally inducing the Diffused Reward Score (DRS), which acts as a reward-driven correction to the reference score function. To make this practical, we further introduce the Diffused Reward Proxy (DRP), an efficient estimator of DRS based on differentiable short-step denoising. Extensive experiments demonstrate that DIDR consistently Pareto-dominates existing one-step SDXL baselines. Moreover, when transferred to a 6B DiT backbone (Z-Image), DIDR surpasses its 50-step teacher in preference alignment while requiring only a single generation step.
  •  

Rethinking Federated Unlearning via the Lens of Memorization

arXiv:2605.24545v1 Announce Type: cross Abstract: Federated learning (FL) increasingly needs machine unlearning to comply with privacy regulations. However, existing federated unlearning approaches may overlook the overlapping information between the unlearning and remaining data, leading to ineffective unlearning and unfairness between clients. In this work, we revisit federated unlearning through the lens of memorization. We argue that unlearning should mainly remove the unique memorized information attributable to the data to be forgotten, while preserving overlapping patterns that are also supported by the remaining data. Specifically, we propose Grouped Memorization Evaluation, an example-level metric that separates memorized knowledge from overlapping knowledge. Building on this metric, we introduce Federated Memorization Pruning (FedMemPrune), a pruning-based unlearning approach that resets redundant parameters responsible for memorization. Extensive experiments show that FedMemPrune closely matches retraining-based unlearning baselines while more effectively eliminating memorization than existing federated unlearning algorithms, yielding strong unlearning performance without sacrificing the utility of retained knowledge.
  •  

CR1(+) tumor-associated macrophages orchestrate an immunosuppressive niche in hepatocellular carcinoma: a genetic and multi-omics dissection

J Transl Med. 2026 May 25. doi: 10.1186/s12967-026-08301-z. Online ahead of print.

ABSTRACT

BACKGROUND: Hepatocellular carcinoma (HCC) remains a major global health burden and a leading cause of cancer-related mortality. Advanced disease is characterized by a profoundly immunosuppressive tumor microenvironment (TME) and limited durable responses to therapy. However, the upstream genetic determinants that drive tumor-associated macrophage (TAM) dysfunction in HCC remain poorly defined. Using an integrative genetic and multi-omics framework, we investigated complement receptor 1 (CR1) as a candidate regulator of this immunosuppressive niche.

METHODS: We combined Mendelian randomization (MR) and metabolite mediation analyses with bulk, single-cell, and spatial transcriptomics to define the role of CR1 in HCC. Public datasets included the TCGA-HCC cohort, a single-cell RNA-sequencing dataset comprising 53,474 high-quality cells from 21 samples, and two spatially profiled HCC sections. Clinical validation was performed in 30 paired HCC and adjacent liver tissues. Functional assays were conducted in THP-1-derived macrophages using CR1 gain- and loss-of-function approaches, phagocytosis assays, and macrophage-CD8+ T-cell co-culture experiments.

RESULTS: MR analyses implicated CR1 in HCC susceptibility at both the protein and transcript levels. pQTL analysis linked genetically predicted circulating CR1 levels to HCC risk (IVW OR = 1.403, p = 0.017), and mediation analysis identified specific metabolites as candidate intermediates. Integrative multi-omics analyses showed that CR1 was preferentially enriched in TAMs, spatially co-localized with the M2 marker CD206, and associated with reduced CD8+ T-cell infiltration, enhanced T-cell exhaustion signatures, advanced clinicopathological features, and poorer survival. In 30 paired clinical samples, CR1-high tumors exhibited increased M2-like macrophage accumulation and reduced CD8+ T-cell infiltration. Functionally, CR1 overexpression drove macrophages toward an M2-like phenotype, enhanced phagocytic activity, increased PD-L1 expression, and suppressed CD8+ T-cell proliferation as well as IFN-gamma and granzyme B production, whereas CR1 knockdown produced the opposite phenotype.

CONCLUSIONS: Our study provides the first integrated genetic, spatial, and functional evidence that CR1+ TAMs constitute a clinically relevant immunoregulatory axis in HCC. These findings extend current understanding of complement-associated immunosuppression beyond canonical complement cascade activity and support CR1 as a candidate biomarker and therapeutic target for macrophage reprogramming, with potential translational relevance for combination strategies involving immune checkpoint blockade.

PMID:42185899 | DOI:10.1186/s12967-026-08301-z

  •  

CR1(+) tumor-associated macrophages orchestrate an immunosuppressive niche in hepatocellular carcinoma: a genetic and multi-omics dissection

J Transl Med. 2026 May 25. doi: 10.1186/s12967-026-08301-z. Online ahead of print.

ABSTRACT

BACKGROUND: Hepatocellular carcinoma (HCC) remains a major global health burden and a leading cause of cancer-related mortality. Advanced disease is characterized by a profoundly immunosuppressive tumor microenvironment (TME) and limited durable responses to therapy. However, the upstream genetic determinants that drive tumor-associated macrophage (TAM) dysfunction in HCC remain poorly defined. Using an integrative genetic and multi-omics framework, we investigated complement receptor 1 (CR1) as a candidate regulator of this immunosuppressive niche.

METHODS: We combined Mendelian randomization (MR) and metabolite mediation analyses with bulk, single-cell, and spatial transcriptomics to define the role of CR1 in HCC. Public datasets included the TCGA-HCC cohort, a single-cell RNA-sequencing dataset comprising 53,474 high-quality cells from 21 samples, and two spatially profiled HCC sections. Clinical validation was performed in 30 paired HCC and adjacent liver tissues. Functional assays were conducted in THP-1-derived macrophages using CR1 gain- and loss-of-function approaches, phagocytosis assays, and macrophage-CD8+ T-cell co-culture experiments.

RESULTS: MR analyses implicated CR1 in HCC susceptibility at both the protein and transcript levels. pQTL analysis linked genetically predicted circulating CR1 levels to HCC risk (IVW OR = 1.403, p = 0.017), and mediation analysis identified specific metabolites as candidate intermediates. Integrative multi-omics analyses showed that CR1 was preferentially enriched in TAMs, spatially co-localized with the M2 marker CD206, and associated with reduced CD8+ T-cell infiltration, enhanced T-cell exhaustion signatures, advanced clinicopathological features, and poorer survival. In 30 paired clinical samples, CR1-high tumors exhibited increased M2-like macrophage accumulation and reduced CD8+ T-cell infiltration. Functionally, CR1 overexpression drove macrophages toward an M2-like phenotype, enhanced phagocytic activity, increased PD-L1 expression, and suppressed CD8+ T-cell proliferation as well as IFN-gamma and granzyme B production, whereas CR1 knockdown produced the opposite phenotype.

CONCLUSIONS: Our study provides the first integrated genetic, spatial, and functional evidence that CR1+ TAMs constitute a clinically relevant immunoregulatory axis in HCC. These findings extend current understanding of complement-associated immunosuppression beyond canonical complement cascade activity and support CR1 as a candidate biomarker and therapeutic target for macrophage reprogramming, with potential translational relevance for combination strategies involving immune checkpoint blockade.

PMID:42185899 | DOI:10.1186/s12967-026-08301-z

  •  

CR1(+) tumor-associated macrophages orchestrate an immunosuppressive niche in hepatocellular carcinoma: a genetic and multi-omics dissection

J Transl Med. 2026 May 25. doi: 10.1186/s12967-026-08301-z. Online ahead of print.

ABSTRACT

BACKGROUND: Hepatocellular carcinoma (HCC) remains a major global health burden and a leading cause of cancer-related mortality. Advanced disease is characterized by a profoundly immunosuppressive tumor microenvironment (TME) and limited durable responses to therapy. However, the upstream genetic determinants that drive tumor-associated macrophage (TAM) dysfunction in HCC remain poorly defined. Using an integrative genetic and multi-omics framework, we investigated complement receptor 1 (CR1) as a candidate regulator of this immunosuppressive niche.

METHODS: We combined Mendelian randomization (MR) and metabolite mediation analyses with bulk, single-cell, and spatial transcriptomics to define the role of CR1 in HCC. Public datasets included the TCGA-HCC cohort, a single-cell RNA-sequencing dataset comprising 53,474 high-quality cells from 21 samples, and two spatially profiled HCC sections. Clinical validation was performed in 30 paired HCC and adjacent liver tissues. Functional assays were conducted in THP-1-derived macrophages using CR1 gain- and loss-of-function approaches, phagocytosis assays, and macrophage-CD8+ T-cell co-culture experiments.

RESULTS: MR analyses implicated CR1 in HCC susceptibility at both the protein and transcript levels. pQTL analysis linked genetically predicted circulating CR1 levels to HCC risk (IVW OR = 1.403, p = 0.017), and mediation analysis identified specific metabolites as candidate intermediates. Integrative multi-omics analyses showed that CR1 was preferentially enriched in TAMs, spatially co-localized with the M2 marker CD206, and associated with reduced CD8+ T-cell infiltration, enhanced T-cell exhaustion signatures, advanced clinicopathological features, and poorer survival. In 30 paired clinical samples, CR1-high tumors exhibited increased M2-like macrophage accumulation and reduced CD8+ T-cell infiltration. Functionally, CR1 overexpression drove macrophages toward an M2-like phenotype, enhanced phagocytic activity, increased PD-L1 expression, and suppressed CD8+ T-cell proliferation as well as IFN-gamma and granzyme B production, whereas CR1 knockdown produced the opposite phenotype.

CONCLUSIONS: Our study provides the first integrated genetic, spatial, and functional evidence that CR1+ TAMs constitute a clinically relevant immunoregulatory axis in HCC. These findings extend current understanding of complement-associated immunosuppression beyond canonical complement cascade activity and support CR1 as a candidate biomarker and therapeutic target for macrophage reprogramming, with potential translational relevance for combination strategies involving immune checkpoint blockade.

PMID:42185899 | DOI:10.1186/s12967-026-08301-z

  •  

Machine learning-based identification of key genes underlying sex differences in hepatocellular carcinoma and targeted drug screening

Biomed Rep. 2026 Apr 24;24(6):74. doi: 10.3892/br.2026.2147. eCollection 2026 Jun.

ABSTRACT

Hepatocellular carcinoma (HCC) shows a marked predominance in men, yet the molecular basis for this sex disparity remains unclear. The present study leveraged multi-omics data and machine learning algorithms to identify key genes associated with sex-specific differences in HCC and to screen for putative candidate compounds, aiming to provide new insights for sex-specific therapy. The mRNA expression data of male and female patients with HCC and paracancerous tissues were obtained from the GEO and TCGA databases. To mitigate overfitting, data were partitioned into independent training and testing sets. Candidate genes were screened by differential expression analysis and weighted gene co-expression network analysis. A total of four complementary algorithms, random forest, support vector machines, generalized linear models and extreme gradient boosting were used to identify key genes with high predictive capability. CYP17A1 and IRX3 were identified as the top differentially expressed core genes associated with HCC in men. Pan-cancer analysis showed that CYP17A1 was lowly expressed in the majority of tumors, but significantly highly expressed in HCC, rectal adenocarcinoma and gastric cancer (P<0.001). Functional cell-based assays showed that knockout of CYP17A1 inhibited the proliferation, migration and invasion ability of HCC cells (P<0.001). Immunohistochemistry showed that CYP17A1 protein expression was significantly increased in HCC tissues from male patients when compared with that in paracancerous tissues (P<0.001), whereas there was no significant difference in female patient tissues (P>0.05). Notably, while IRX3 was identified computationally, its functional role remains to be experimentally validated. Molecular docking predicted a potential interaction between the natural compound Saikosaponin A and the CYP17A1 protein, and cellular assays revealed that it dose-dependently inhibits HCC cell malignant phenotypes. The present study suggests that CYP17A1 is associated with sex differences in HCC, potentially via the androgen signaling axis. Furthermore, IRX3 emerges as a novel hypothesis-generating candidate gene. Finally, the findings of the present study highlight Saikosaponin A as a putative therapeutic candidate for male patients with HCC, warranting further target-dependency investigations.

PMID:42125766 | PMC:PMC13158723 | DOI:10.3892/br.2026.2147

  •  

EBV strain interacts with host HLA to drive nasopharyngeal carcinoma risk

Nature, Published online: 15 April 2026; doi:10.1038/s41586-026-10416-8

A genome-to-genome association study identifies host and viral risk factors that interact to drive nasopharyngeal carcinoma endemicity in southern China.
  •  

FCGR2B (+) Macrophages as a Critical Node Linking Ferroptosis and Immunosuppression: A Multiomics Framework for Prognosis and Therapy in High-Grade Serous Ovarian Cancer

Hum Mutat. 2026 Apr 6;2026:8027584. doi: 10.1155/humu/8027584. eCollection 2026.

ABSTRACT

BACKGROUND: High-grade serous ovarian cancer (HGSOC) is characterized by a complex tumor microenvironment and poor prognosis, yet the roles of specific tumor-associated macrophages (TAMs) subpopulations in driving disease progression remain elusive.

METHODS: This study evaluated the prognostic relevance of FCGR2B in HGSOC. Single-cell RNA sequencing identified FCGR2B + TAMs as a distinct macrophage subpopulation with unique transcriptional features. Integrative analyses combining single-cell and bulk differentially expressed genes, macrophage-associated modules, and ferroptosis-related gene sets identified 26 candidate prognostic genes, from which a four-gene signature (CRYAB, PLAUR, EREG, and C5AR1) was derived to construct the prognostic risk model. The model was validated in an independent cohort. Immune infiltration, single-cell trajectory, copy number variation, and drug-gene associations were analyzed to explore the molecular and therapeutic implications of risk stratification.

RESULTS: HGSOC patients classified as high risk exhibited poorer survival outcomes, increased infiltration of M2-like macrophages, elevated expression of immune checkpoints, and enrichment of immune- and ferroptosis-related pathways. Trajectory and copy number variation analyses revealed stage-specific gene expression patterns and amplification-associated regulation. Drug-gene association analyses further suggested that high-risk patients may be more responsive to targeted therapies and proteasome inhibitors, whereas low-risk patients may benefit from conventional chemotherapy.

CONCLUSION: FCGR2B + TAMs are closely linked to HGSOC progression, and the proposed prognostic model based on FCGR2B + TAMs provides predictive value and potential therapeutic insights for patient stratification.

PMID:41953398 | PMC:PMC13054137 | DOI:10.1155/humu/8027584

  •  

Unmasking FCGR2B as a high-grade serous ovarian cancer specific marker of immune suppression and tumor progression through multi-omics mining

Transl Oncol. 2026 Apr 3;67:102748. doi: 10.1016/j.tranon.2026.102748. Online ahead of print.

ABSTRACT

BACKGROUND: Epithelial ovarian cancer (EOC) encompasses five major histological subtypes with marked genetic, immunological, and clinical heterogeneity. While genome-wide association studies (GWAS) have identified subtype-specific risk loci, a critical gap remains in understanding how plasma proteins influence immune-cell traits and contribute to EOC pathogenesis.

METHODS: We integrated subtype-stratified GWAS data from two EOC cohorts with plasma proteomics and immune-cell traits to construct protein-immune-EOC regulatory landscapes using a three-stage Mendelian randomization framework. Single-cell RNA-seq and multiplex immunofluorescence were employed to delineate the cellular distribution and spatial context of causal proteins. Subsequent analyses characterized immune infiltration, macrophage polarization, and clinicopathological associations. Drug-gene correlations were used to identify potential therapeutic targets, and transcriptomic analyses were applied to delineate the underlying transcriptional landscape.

RESULTS: We identified 20 subtype-specific protein-immune-EOC regulatory axes, with FCGR2B emerging as a causal plasma protein in immune regulation and high-grade serous ovarian cancer (HGSOC) progression. FCGR2B was highly expressed in tumor-associated macrophages and was associated with an M2-like polarization phenotype. Functional characterization revealed that FCGR2B was associated with shorter progression-free survival and an immunosuppressive tumor microenvironment. Transcriptomic analyses revealed altered NF-κB signaling upon FCGR2B knockdown, and drug-response data suggested a potential association between high FCGR2B expression and sensitivity to NF-κB inhibitors.

CONCLUSIONS: These findings delineate subtype-specific genetically informed protein-immune regulatory landscapes in EOC and identify FCGR2B as a key immunoregulatory and prognostic biomarker in HGSOC, suggesting FCGR2B as a potential therapeutic vulnerability that warrants further investigation.

PMID:41934917 | DOI:10.1016/j.tranon.2026.102748

  •  

LLM-Meta-SR: In-Context Learning for Evolving Selection Operators in Symbolic Regression

arXiv:2505.18602v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have revolutionized algorithm development, yet their application in symbolic regression, where algorithms automatically discover symbolic expressions from data, remains limited. In this paper, we propose a meta-learning framework that enables LLMs to automatically design selection operators for evolutionary symbolic regression algorithms. We first identify two key limitations in existing LLM-based algorithm evolution techniques: lack of semantic guidance and code bloat. The absence of semantic awareness can lead to ineffective exchange of useful code components, while bloat results in unnecessarily complex components; both can hinder evolutionary learning progress or reduce the interpretability of the designed algorithm. To address these issues, we enhance the LLM-based evolution framework for meta-symbolic regression with two key innovations: a complementary, semantics-aware selection operator and bloat control. Additionally, we embed domain knowledge into the prompt, enabling the LLM to generate more effective and contextually relevant selection operators. Our experimental results on symbolic regression benchmarks show that LLMs can devise selection operators that outperform nine expert-designed baselines, achieving state-of-the-art performance. Moreover, the evolved operator can further improve a state-of-the-art symbolic regression algorithm, achieving the best performance among 28 symbolic regression and other machine learning algorithms across 116 regression datasets. This demonstrates that LLMs can exceed expert-level algorithm design for symbolic regression.
  •  

Generalizing Dynamics Modeling More Easily from Representation Perspective

arXiv:2603.22655v1 Announce Type: cross Abstract: Learning system dynamics from observations is a critical problem in many applications over various real-world complex systems, e.g., climate, ecology, and fluid systems. Recently, neural dynamics modeling method have become a prevalent solution that embeds the object's observations into a latent space before learning dynamics using neural methods such as neural Ordinary Differential Equations (ODE). Existing dynamics modeling methods induce a specific model for each observation of different complex systems, resulting in poor generalization across systems. Inspired by the great success of pre-trained models, we conduct a generalized Pre-trained Dynamics EncoDER (PDEDER) which can embed the original state observations into a latent space where the dynamics can be captured more easily. To conduct the generalized PDEDER, we pre-train any Pre-trained Language Model (PLM) by minimizing the Lyapunov exponent objective, which constrains the chaotic behavior of governing dynamics learned in the latent space. By penalizing the divergence of embedded observations, our PDEDER promotes locally stable and well-structured latent dynamics, thereby facilitating more effective dynamics modeling than in the original observation space. In addition, we incorporate reconstruction and forecasting objectives to mitigate the risk of obtaining an over-smoothed latent space. Specifically, we collect 152 sets of real-world and synthetic observations from 23 complex systems as pre-training corpora and employ them to pre-train PDEDER. Given any future dynamic observation, we can fine-tune PDEDER with any specific dynamics modeling method. We evaluate PDEDER on 12 dynamic systems by short/long-term forecasting under both in-domain and cross-domain settings, and the empirical results indicate the effectiveness and generalizability of PDEDER.
  •  

How Long Can Unified Multimodal Models Generate Images Reliably? Taming Long-Horizon Interleaved Image Generation via Context Curation

arXiv:2603.07540v1 Announce Type: cross Abstract: Unified multimodal models hold the promise of generating extensive, interleaved narratives, weaving text and imagery into coherent long-form stories. However, current systems suffer from a critical reliability gap: as sequences grow, generation quality rapidly collapses. In this work, we investigate the mechanism behind this failure and argue that it is distinct from standard long-context challenges. We reveal that in generation, accumulated visual history acts as a source of active pollution, a decay governed specifically by the number of image events rather than raw token count. We identify a structural vulnerability where dense visual tokens overwhelm the attention mechanism, creating noise that distorts future synthesis. Guided by these mechanistic insights, we propose UniLongGen, a training-free inference strategy that prioritizes safe conditioning over total recall. Instead of retaining all history, UniLongGen dynamically curates the model's memory, identifying and discarding interfering visual signals based on the model's own internal relevance rankings. Extensive experiments demonstrate that this active forgetting approach is essential for stability: UniLongGen significantly outperforms baselines in long-horizon fidelity and consistency, while simultaneously reducing memory footprint and inference time.
  •  

FOR-Prompting: From Objection to Revision via an Asymmetric Prompting Protocol

arXiv:2510.01674v2 Announce Type: replace-cross Abstract: Reasoning protocols such as Chain of Thought (CoT) and Tree of Thought (ToT) organize internal deliberation but lack an explicit mechanism for external questioning that elicits self-revision. We present FOR-Prompting (From Objection to Revision Prompting), an asymmetric protocol where a Defender proposes an answer, an Debater (Questioner) raises question-style objections with no direct fixes, and a Host optionally synthesizes the final output. Across GSM8K, FOR-Prompting matches the accuracy of CoT and consistently improves over single-prompting when evaluated under identical model backbones. On small-scale open-source models (e.g., LLaMA-3.2-1B), FOR-Prompting yields substantial gains over direct prompting and performs comparably to lightweight reasoning baselines, highlighting its promise for low-resource and on-device settings. Cross-model role-swapping further shows that performance is primarily determined by the Defender, enabling small models to act effectively as Questioners. Beyond structured math tasks, FOR-Prompting supports refinement in open-ended and multi-stage tasks: qualitative analysis shows improved exploration, coverage, and specificity, and a blind study of human preferences found that participants preferred FOR-Prompting outputs over strong LLM baselines in an itinerary-planning scenario. The protocol is model-agnostic and operates purely through role-structured prompting, requiring no training, access to model internals, or symmetrically strong agents. FOR-Prompting therefore enables scalable study of objection-driven reasoning and offers a practical mechanism for automated iterative refinement across both hosted and local LLMs.
  •  

Contextualized Privacy Defense for LLM Agents

arXiv:2603.02983v1 Announce Type: cross Abstract: LLM agents increasingly act on users' personal information, yet existing privacy defenses remain limited in both design and adaptability. Most prior approaches rely on static or passive defenses, such as prompting and guarding. These paradigms are insufficient for supporting contextual, proactive privacy decisions in multi-step agent execution. We propose Contextualized Defense Instructing (CDI), a new privacy defense paradigm in which an instructor model generates step-specific, context-aware privacy guidance during execution, proactively shaping actions rather than merely constraining or vetoing them. Crucially, CDI is paired with an experience-driven optimization framework that trains the instructor via reinforcement learning (RL), where we convert failure trajectories with privacy violations into learning environments. We formalize baseline defenses and CDI as distinct intervention points in a canonical agent loop, and compare their privacy-helpfulness trade-offs within a unified simulation framework. Results show that our CDI consistently achieves a better balance between privacy preservation (94.2%) and helpfulness (80.6%) than baselines, with superior robustness to adversarial conditions and generalization.
  •  

LaDiR: Latent Diffusion Enhances LLMs for Text Reasoning

arXiv:2510.04573v5 Announce Type: replace-cross Abstract: Large Language Models (LLMs) demonstrate their reasoning ability through chain-of-thought (CoT) generation. However, LLM's autoregressive decoding may limit the ability to revisit and refine earlier tokens in a holistic manner, which can also lead to inefficient exploration for diverse solutions. In this paper, we propose LaDiR (Latent Diffusion Reasoner), a novel reasoning framework that unifies the expressiveness of continuous latent representation with the iterative refinement capabilities of latent diffusion models for an existing LLM. We first construct a structured latent reasoning space using a Variational Autoencoder (VAE) that encodes text reasoning steps into blocks of thought tokens, preserving semantic information and interpretability while offering compact but expressive representations. Subsequently, we utilize a latent diffusion model that learns to denoise a block of latent thought tokens with a blockwise bidirectional attention mask, enabling longer horizon and iterative refinement with adaptive test-time compute. This design allows efficient parallel generation of diverse reasoning trajectories, allowing the model to plan and revise the reasoning process holistically. We conduct evaluations on a suite of mathematical reasoning and planning benchmarks. Empirical results show that LaDiR consistently improves accuracy, diversity, and interpretability over existing autoregressive, diffusion-based, and latent reasoning methods, revealing a new paradigm for text reasoning with latent diffusion.
  •  
❌