❌

Normal view

Spatial multi-omics unveils the monoclonal origin, neuroendocrine plasticity, and microenvironment niches in combined small-cell lung cancer

Cell Rep Med. 2026 Apr 10:102741. doi: 10.1016/j.xcrm.2026.102741. Online ahead of print.

ABSTRACT

Combined small-cell lung cancer (cSCLC) is an aggressive subtype of SCLC with mixed histologic components. Despite heterogeneity and poorer prognosis than de novo SCLC, cSCLC is managed as SCLC because molecular insight into biology, lineage plasticity, and tumor microenvironment (TME) is limited. We perform spatial whole-exome sequencing, spatial transcriptomics, and single-nucleus RNA sequencing across 19 treatment-naive cSCLC tumors. Different histologic components share a monoclonal origin, whereas divergence associates with distinct mutation and copy-number alteration patterns. Our results define spatially exclusive or interspersed tumor domains with distinct TME and immune landscapes; fibroblast-rich boundaries enriched for an aggressive fibroblast subtype may shape TME and treatment responses. We identify lineage plasticity, including adenocarcinoma-to-SCLC transdifferentiation and SCLC-subtype coexistence, and develop cSCLC Detector, a sensitive mutation-based assay improving cSCLC detection in tissue and liquid biopsies. These findings illuminate cSCLC evolution and heterogeneity, underscoring the need for tailored diagnostic and therapeutic strategies for this aggressive subtype.

PMID:41966692 | DOI:10.1016/j.xcrm.2026.102741

Spatial multi-omics unveils the monoclonal origin, neuroendocrine plasticity, and microenvironment niches in combined small-cell lung cancer

Cell Rep Med. 2026 Apr 10:102741. doi: 10.1016/j.xcrm.2026.102741. Online ahead of print.

ABSTRACT

Combined small-cell lung cancer (cSCLC) is an aggressive subtype of SCLC with mixed histologic components. Despite heterogeneity and poorer prognosis than de novo SCLC, cSCLC is managed as SCLC because molecular insight into biology, lineage plasticity, and tumor microenvironment (TME) is limited. We perform spatial whole-exome sequencing, spatial transcriptomics, and single-nucleus RNA sequencing across 19 treatment-naive cSCLC tumors. Different histologic components share a monoclonal origin, whereas divergence associates with distinct mutation and copy-number alteration patterns. Our results define spatially exclusive or interspersed tumor domains with distinct TME and immune landscapes; fibroblast-rich boundaries enriched for an aggressive fibroblast subtype may shape TME and treatment responses. We identify lineage plasticity, including adenocarcinoma-to-SCLC transdifferentiation and SCLC-subtype coexistence, and develop cSCLC Detector, a sensitive mutation-based assay improving cSCLC detection in tissue and liquid biopsies. These findings illuminate cSCLC evolution and heterogeneity, underscoring the need for tailored diagnostic and therapeutic strategies for this aggressive subtype.

PMID:41966692 | DOI:10.1016/j.xcrm.2026.102741

Integrated analysis of network pharmacology and multi-omics reveals the mechanisms of Zuogui Jiangtang Qinggan formula ameliorates MASLD via fatty acid metabolic reprogramming

Phytomedicine. 2026 Mar 30;155:158128. doi: 10.1016/j.phymed.2026.158128. Online ahead of print.

ABSTRACT

BACKGROUND: The global prevalence of metabolic dysfunction-associated steatotic liver disease (MASLD) continues to rise, and its pathogenesis is complex, creating an urgent need to discover novel and effective therapeutic strategies. The Zuogui Jiangtang Qinggan formula (ZGJTQGF), an approved in-hospital preparation, has demonstrated significant clinical efficacy in treating diabetes over several decades. However, the mechanisms underlying its potential therapeutic effects on MASLD remain unclear PURPOSE: This study systematically investigates the therapeutic effects and molecular mechanisms of ZGJTQGF on MASLD through the integration of network pharmacology and multi-omics strategies.

METHODS: The model of MASLD was successfully induced in db/db mice by a high-fat diet (HFD), which displayed characteristic dyslipidaemia. Serum biomarkers, histology, and hepatic multi-omics analyses were employed to assess metabolic status, steatosis, targets, and pathways. Ultraperformance liquid chromatography-tandem mass spectrometry (UPLC-MS/MS), molecular docking analysis and in vitro verification were applied to explore the active ingredients of ZGJTQGF.

RESULTS: ZGJTQGF significantly reduced dyslipidemia in HFD-fed mice, inhibited pro-inflammatory cytokines, and restored glucose metabolic balance by lowering levels of glucose, insulin, OGTT, and HOMA-IR. Histopathology showed reduced lipid deposition and hepatocyte damage. Comprehensive multi-omics analysis suggested that regulating the AMPK/PGC-1α/PPARα and FXR-BSEP signaling pathways could be potential targets for ZGJTQGF in reprogramming glucose and lipid metabolism in MASLD treatment. Blood component analysis identified 52 ZGJTQGF-derived compounds. In molecular docking experiments, Wogonin, Naringenin, Quercetin, Tanshinone IIA and Berberine showed high-affinity binding to core targets in AMPK, PPARα, PGC-1α, FXR and FAS. Mechanistically, ZGJTQGF activated AMPK/PPARα /PGC-1α and FXR-BSEP signaling pathway, promotes fatty acid β oxidation and enhances energy consumption in AML-2 and 3T3-L1 cells, downregulates SREBP-1-dependent adipogenesis (reduces ACC1 and FAS expression), alleviates MASLD driven reprogramming of glucose and lipid metabolism, and regulates lipid metabolism and fatty acid synthesis.

CONCLUSIONS: ZGJTQGF activates the AMPK/PPARα /PGC-1α pathway and inhibits abnormal lipid accumulation in diabetic fatty liver by promoting fatty acid β-oxidation, energy consumption, and bile acid metabolism. These findings provide new insights into the mechanism of ZGJTQGF in the treatment of diabetic fatty liver disease.

PMID:41962267 | DOI:10.1016/j.phymed.2026.158128

Integrated analysis of network pharmacology and multi-omics reveals the mechanisms of Zuogui Jiangtang Qinggan formula ameliorates MASLD via fatty acid metabolic reprogramming

Phytomedicine. 2026 Mar 30;155:158128. doi: 10.1016/j.phymed.2026.158128. Online ahead of print.

ABSTRACT

BACKGROUND: The global prevalence of metabolic dysfunction-associated steatotic liver disease (MASLD) continues to rise, and its pathogenesis is complex, creating an urgent need to discover novel and effective therapeutic strategies. The Zuogui Jiangtang Qinggan formula (ZGJTQGF), an approved in-hospital preparation, has demonstrated significant clinical efficacy in treating diabetes over several decades. However, the mechanisms underlying its potential therapeutic effects on MASLD remain unclear PURPOSE: This study systematically investigates the therapeutic effects and molecular mechanisms of ZGJTQGF on MASLD through the integration of network pharmacology and multi-omics strategies.

METHODS: The model of MASLD was successfully induced in db/db mice by a high-fat diet (HFD), which displayed characteristic dyslipidaemia. Serum biomarkers, histology, and hepatic multi-omics analyses were employed to assess metabolic status, steatosis, targets, and pathways. Ultraperformance liquid chromatography-tandem mass spectrometry (UPLC-MS/MS), molecular docking analysis and in vitro verification were applied to explore the active ingredients of ZGJTQGF.

RESULTS: ZGJTQGF significantly reduced dyslipidemia in HFD-fed mice, inhibited pro-inflammatory cytokines, and restored glucose metabolic balance by lowering levels of glucose, insulin, OGTT, and HOMA-IR. Histopathology showed reduced lipid deposition and hepatocyte damage. Comprehensive multi-omics analysis suggested that regulating the AMPK/PGC-1α/PPARα and FXR-BSEP signaling pathways could be potential targets for ZGJTQGF in reprogramming glucose and lipid metabolism in MASLD treatment. Blood component analysis identified 52 ZGJTQGF-derived compounds. In molecular docking experiments, Wogonin, Naringenin, Quercetin, Tanshinone IIA and Berberine showed high-affinity binding to core targets in AMPK, PPARα, PGC-1α, FXR and FAS. Mechanistically, ZGJTQGF activated AMPK/PPARα /PGC-1α and FXR-BSEP signaling pathway, promotes fatty acid β oxidation and enhances energy consumption in AML-2 and 3T3-L1 cells, downregulates SREBP-1-dependent adipogenesis (reduces ACC1 and FAS expression), alleviates MASLD driven reprogramming of glucose and lipid metabolism, and regulates lipid metabolism and fatty acid synthesis.

CONCLUSIONS: ZGJTQGF activates the AMPK/PPARα /PGC-1α pathway and inhibits abnormal lipid accumulation in diabetic fatty liver by promoting fatty acid β-oxidation, energy consumption, and bile acid metabolism. These findings provide new insights into the mechanism of ZGJTQGF in the treatment of diabetic fatty liver disease.

PMID:41962267 | DOI:10.1016/j.phymed.2026.158128

Plasmin promotes hepatocellular carcinoma invasion and metastasis via CXCR4-mediated activation of PI3K/AKT/mTOR signaling

Oncogene, Published online: 09 April 2026; doi:10.1038/s41388-026-03775-z

Plasmin promotes hepatocellular carcinoma invasion and metastasis via CXCR4-mediated activation of PI3K/AKT/mTOR signaling

Chuanminshen violaceum (Apiaceae) as a medicinal-and-edible resource: phytochemical diversity, bioactivities, and routes to standardized products

J Ethnopharmacol. 2026 Apr 6:121628. doi: 10.1016/j.jep.2026.121628. Online ahead of print.

ABSTRACT

ETHNOPHARMACOLOGICAL RELEVANCE: Chuanminshen violaceum Sheh et Shan is a medicinal-and-edible Apiaceae plant in China recorded for yin nourishment, lung/spleen tonification, and phlegm resolution, and used for cough and chronic respiratory complaints.

STUDY AIM: To synthesize current evidence on botanical resources, chemistry, pharmacology, and applications of C. violaceum, and to define priorities for standardized and safe development.

MATERIALS AND METHODS: This review integrates studies on resource distribution and ecological adaptability, multi-fraction phytochemistry, extraction-purification and formulation technologies, preclinical pharmacology, and quality, safety, and regulatory considerations.

RESULTS: C. violaceum contains structurally diverse polysaccharides plus volatile oils (often polyacetylene-rich), phenolics (e.g., chlorogenic acid and rutin), PUFA-rich lipids, and newly reported minor constituents. Polysaccharides show variable monosaccharide profiles, molecular-weight ranges, and linkage/branching patterns, strongly influenced by extraction-purification; derivatization (e.g., sulfation/selenization) and delivery systems can further tune physicochemical properties. Preclinical studies report antioxidant, anti-inflammatory, immunomodulatory, cardioprotective, and antiviral effects, commonly linked to Nrf2/Keap1 redox defense, inflammatory signaling control, TLR2/4-related immune regulation, gut-barrier reinforcement with microbiota remodeling, and anti-ferroptotic protection in myocardial ischemia-reperfusion models. Applications span traditional dosage forms and functional foods, but translation is limited by origin/process variability, incomplete long-term safety and ADME data, and regulatory uncertainty.

CONCLUSIONS: C. violaceum is a promising ethnomedicinal resource with clear part-specific features and polysaccharide-centered potential. Future work should combine multi-omics with target validation, fingerprint-guided QC and traceability, greener scalable processing, and regulatory-aligned safety packages to enable reproducible products.

PMID:41951195 | DOI:10.1016/j.jep.2026.121628

Multiomics and multi-region spatial transcriptome analysis reveal cellular networks and pathways associated with HCC recurrence

JHEP Rep. 2026 Feb 18;8(5):101790. doi: 10.1016/j.jhepr.2026.101790. Online ahead of print.

ABSTRACT

BACKGROUND & AIMS: Hepatocellular carcinoma (HCC) exhibits diverse aetiologies and molecular heterogeneity, with a median 5-year overall survival of <70% due to high recurrence rates following curative-intent surgery. This study investigated the complex tumour microenvironment (TME) in HCC and explored interactions between various cell types and their roles in disease recurrence.

METHODS: Using a multi-omics approach on multi-region samples of surgically resected HCC from the PLANet 1.0 cohort (NCT03267641), we performed spatial transcriptomics on 17 tissue samples from four patients and bulk RNA sequencing on 329 sectors from 90 patients. Findings were validated using immunofluorescence and multiplex immunohistochemistry.

RESULTS: Our analysis revealed extensive intra- and intertumour gene expression heterogeneity and identified a specific subset of endothelial cells (ECs), INTS6+ ECs, enriched and spatially colocalised with tumour cells in primary tumours from patients with recurrence (p = 0.021, n = 49). A significant ANGPTL4-SDC1 ligand-receptor interaction was identified between INTS6+ ECs and tumour cells. Notably, INTS6+ ECs were enriched in microvascular invasion regions and spatially colocalised with tumour cells in patients with recurrence (p = 0.036, n = 53). These findings highlight endothelial-tumour cell interactions within the TME as potential therapeutic targets.

CONCLUSIONS: INTS6+ ECs are enriched in microvascular invasion regions and spatially colocalised with tumour cells in recurrent HCC, suggesting a potential role in disease recurrence and representing a promising therapeutic target within the TME.

IMPACT AND IMPLICATIONS: The spatial co-localisation of cell types plays a significant role in the recurrence of hepatocellular carcinoma. In this study, we have pinpointed a particular group of endothelial cells, known as INTS6+ endothelial cells, which are spatially colocalised with tumour cells and enriched in microvascular invasion regions in patients experiencing recurrence. These discoveries highlight novel therapeutic targets that focus on endothelial cell interactions within the tumour microenvironment to prevent recurrence and enhance overall patient survival.

PMID:41950768 | DOI:10.1016/j.jhepr.2026.101790

Multiomics and multi-region spatial transcriptome analysis reveal cellular networks and pathways associated with HCC recurrence

JHEP Rep. 2026 Feb 18;8(5):101790. doi: 10.1016/j.jhepr.2026.101790. Online ahead of print.

ABSTRACT

BACKGROUND & AIMS: Hepatocellular carcinoma (HCC) exhibits diverse aetiologies and molecular heterogeneity, with a median 5-year overall survival of <70% due to high recurrence rates following curative-intent surgery. This study investigated the complex tumour microenvironment (TME) in HCC and explored interactions between various cell types and their roles in disease recurrence.

METHODS: Using a multi-omics approach on multi-region samples of surgically resected HCC from the PLANet 1.0 cohort (NCT03267641), we performed spatial transcriptomics on 17 tissue samples from four patients and bulk RNA sequencing on 329 sectors from 90 patients. Findings were validated using immunofluorescence and multiplex immunohistochemistry.

RESULTS: Our analysis revealed extensive intra- and intertumour gene expression heterogeneity and identified a specific subset of endothelial cells (ECs), INTS6+ ECs, enriched and spatially colocalised with tumour cells in primary tumours from patients with recurrence (p = 0.021, n = 49). A significant ANGPTL4-SDC1 ligand-receptor interaction was identified between INTS6+ ECs and tumour cells. Notably, INTS6+ ECs were enriched in microvascular invasion regions and spatially colocalised with tumour cells in patients with recurrence (p = 0.036, n = 53). These findings highlight endothelial-tumour cell interactions within the TME as potential therapeutic targets.

CONCLUSIONS: INTS6+ ECs are enriched in microvascular invasion regions and spatially colocalised with tumour cells in recurrent HCC, suggesting a potential role in disease recurrence and representing a promising therapeutic target within the TME.

IMPACT AND IMPLICATIONS: The spatial co-localisation of cell types plays a significant role in the recurrence of hepatocellular carcinoma. In this study, we have pinpointed a particular group of endothelial cells, known as INTS6+ endothelial cells, which are spatially colocalised with tumour cells and enriched in microvascular invasion regions in patients experiencing recurrence. These discoveries highlight novel therapeutic targets that focus on endothelial cell interactions within the tumour microenvironment to prevent recurrence and enhance overall patient survival.

PMID:41950768 | DOI:10.1016/j.jhepr.2026.101790

Engineered immunosuppressive dendritic cells protect against cardiac remodelling

Nature, Published online: 08 April 2026; doi:10.1038/s41586-026-10346-5

Lesion-targeted immune modulation is a feasible strategy to control cardiac fibrosis, and engineered dendritic cells are a promising therapeutic platform for treating cardiac remodelling and heart failure.

High-precision measurement of the W boson mass with the CMS experiment

Nature, Published online: 08 April 2026; doi:10.1038/s41586-026-10168-5

The CMS experiment at CERN reports one of the highest-precision measurements of the W boson mass, finding it in line with standard model predictions and at odds with recent anomalous measurements.

UBTF-HSP90A-MIF stress circuit drives lenvatinib resistance and immune exclusion in hepatocellular carcinoma

J Adv Res. 2026 Apr 5:S2090-1232(26)00280-8. doi: 10.1016/j.jare.2026.04.002. Online ahead of print.

ABSTRACT

INTRODUCTION: The clinical benefit of combining lenvatinib with PD-1 blockade in HCC is frequently constrained by adaptive resistance and the development of an immune-cold tumor microenvironment.

OBJECTIVES: This study aimed to elucidate the molecular mechanisms underlying adaptive resistance and immune exclusion during lenvatinib-PD-1 therapy in HCC, with a particular focus on a UBTF/HSP90A/MIF regulatory circuit. We examined whether genetic or pharmacologic targeting of macrophage migration inhibitory factor (MIF) could restore lenvatinib sensitivity, remodel the tumor immune microenvironment, and serve as a predictive biomarker in clinical cohorts.

METHODS: Paired lenvatinib-sensitive and -resistant HCC models were interrogated using integrated multi-omic and functional approaches, including RNA sequencing, promoter pull-down assays, ChIP, luciferase reporter assays, PLA, and flow cytometry. Key findings were validated in patient-derived organoids and xenografts, as well as in an immunocompetent hydrodynamic HCC mouse model. Clinical relevance was evaluated in independent cohorts treated with lenvatinib plus anti-PD-1 therapy.

RESULTS: UBTF directly bound to and transcriptionally activated the HSP90A promoter, resulting in increased HSP90A expression and stabilization of MIF. MIF signaling through CD74 co-activated the PI3K-AKT and MAPK pathways, sustaining tumor cell proliferation under lenvatinib pressure. Single-cell RNA sequencing and multiplex immunohistochemistry revealed macrophage enrichment and CD8+ T-cell exclusion in resistant tumors. Genetic ablation of Mif (Alb-Cre; Mifflox/flox) or pharmacologic inhibition with 4-IPP (4-Iodo-6-phenylpyrimidine) restored lenvatinib sensitivity, reprogrammed the tumor immune microenvironment, and, when combined with PD-1 blockade, achieved superior tumor control and prolonged survival. In clinical datasets, low pretreatment MIF expression was associated with improved responses to lenvatinib plus PD-1 therapy.

CONCLUSIONS: These findings define a UBTF/HSP90A/MIF axis linking proteostasis and cytokine signaling to immune-metabolic dysfunction and lenvatinib resistance in HCC. MIF emerges as both a mechanistic driver and a predictive biomarker, supporting prospective evaluation of therapeutic strategies combining lenvatinib-PD-1 with MIF- or HSP90A-targeted interventions to personalize TKI-ICI therapy.

PMID:41946392 | DOI:10.1016/j.jare.2026.04.002

Hume's Representational Conditions for Causal Judgment: What Bayesian Formalization Abstracted Away

arXiv:2604.03387v1 Announce Type: new Abstract: Hume's account of causal judgment presupposes three representational conditions: experiential grounding (ideas must trace to impressions), structured retrieval (association must operate through organized networks exceeding pairwise connection), and vivacity transfer (inference must produce felt conviction, not merely updated probability). This paper extracts these conditions from Hume's texts and argues that they are integral to his causal psychology. It then traces their fate through the formalization trajectory from Hume to Bayesian epistemology and predictive processing, showing that later frameworks preserve the updating structure of Hume's insight while abstracting away these further representational conditions. Large language models serve as an illustrative contemporary case: they exhibit a form of statistical updating without satisfying the three conditions, thereby making visible requirements that were previously background assumptions in Hume's framework.

TABQAWORLD: Optimizing Multimodal Reasoning for Multi-Turn Table Question Answering

arXiv:2604.03393v1 Announce Type: new Abstract: Multimodal reasoning has emerged as a powerful framework for enhancing reasoning capabilities of reasoning models. While multi-turn table reasoning methods have improved reasoning accuracy through tool use and reward modeling, they rely on fixed text serialization for table state readouts. This introduces representation errors in table encoding that significantly accumulate over multiple turns. Such accumulation is alleviated by tabular grounding methods in the expense of inference compute and cost, rendering real world deployment impractical. To address this, we introduce TABQAWORLD, a table reasoning framework that jointly optimizes tabular action through representation and estimation. For representation, TABQAWORLD employs an action-conditioned multimodal selection policy, which dynamically switches between visual and textual representations to maximize table state readout reliability. For estimation, TABQAWORLD optimizes stepwise reasoning trajectory through table metadata including dimension, data types and key values, safely planning trajectory and compressing low-complexity actions to reduce conversation turns and latency. Designed as a training-free framework, empirical evaluations show that TABQAWORLD achieves state-of-the-art performance with 4.87% accuracy improvements over baselines, with 5.42% accuracy gain and 33.35% inference latency reduction over static settings, establishing a new standard for reliable and efficient table reasoning.

PRAISE: Prefix-Based Rollout Reuse in Agentic Search Training

arXiv:2604.03675v1 Announce Type: new Abstract: In agentic search, large language models (LLMs) are trained to perform multi-turn retrieval and reasoning for complex tasks such as multi-hop question answering (QA). However, current search-based Reinforcement Learning (RL) methods suffer from two core limitations: expensive long-horizon rollouts are under-utilized during training, and supervision is typically available only at the final answer, resulting in severe reward sparsity. We present Prefix-based Rollout reuse for Agentic search with Intermediate Step rEwards (PRAISE), a framework for improving both data efficiency and credit assignment in agentic search training. Given a complete search trajectory, PRAISE extracts prefix states at different search turns, elicits intermediate answers from them, and uses these prefixes both to construct additional training trajectories and to derive step-level rewards from performance differences across prefixes. Our method uses a single shared model for both search policy learning and prefix answer evaluation, enabling joint optimization without extra human annotations or a separate reward model. Experiments on multi-hop QA benchmarks show that PRAISE consistently improves performance over strong baselines.

FactReview: Evidence-Grounded Reviews with Literature Positioning and Execution-Based Claim Verification

arXiv:2604.04074v2 Announce Type: new Abstract: Peer review in machine learning is under growing pressure from rising submission volume and limited reviewer time. Most LLM-based reviewing systems read only the manuscript and generate comments from the paper's own narrative. This makes their outputs sensitive to presentation quality and leaves them weak when the evidence needed for review lies in related work or released code. We present FactReview, an evidence-grounded reviewing system that combines claim extraction, literature positioning, and execution-based claim verification. Given a submission, FactReview identifies major claims and reported results, retrieves nearby work to clarify the paper's technical position, and, when code is available, executes the released repository under bounded budgets to test central empirical claims. It then produces a concise review and an evidence report that assigns each major claim one of five labels: Supported, Supported by the paper, Partially supported, In conflict, or Inconclusive. In a case study on CompGCN, FactReview reproduces results that closely match those reported for link prediction and node classification, yet also shows that the paper's broader performance claim across tasks is not fully sustained: on MUTAG graph classification, the reproduced result is 88.4%, whereas the strongest baseline reported in the paper remains 92.6%. The claim is therefore only partially supported. More broadly, this case suggests that AI is most useful in peer review not as a final decision-maker, but as a tool for gathering evidence and helping reviewers produce more evidence-grounded assessments. The code is public at https://github.com/DEFENSE-SEU/Review-Assistant.

GUIDE: Interpretable GUI Agent Evaluation via Hierarchical Diagnosis

arXiv:2604.04399v1 Announce Type: new Abstract: Evaluating GUI agents presents a distinct challenge: trajectories are long, visually grounded, and open-ended, yet evaluation must be both accurate and interpretable. Existing approaches typically apply a single holistic judgment over the entire action-observation sequence-a strategy that proves unreliable on long-horizon tasks and yields binary verdicts offering no insight into where or why an agent fails. This opacity limits the utility of evaluation as a diagnostic tool for agent development. We introduce GUIDE (GUI Understanding and Interpretable Diagnostic Evaluation), a framework that decomposes trajectory assessment into three sequential stages mirroring the compositional structure of GUI tasks. Trajectory Segmentation partitions the full trace into semantically coherent subtask units. Subtask Diagnosis evaluates each unit in context, assigning a completion verdict and generating a structured error analysis with corrective recommendations. Overall Summary aggregates per-subtask diagnoses into a task-level judgment. By operating on bounded subtask segments rather than full trajectories, GUIDE mitigates the context overload that degrades existing evaluators as task complexity grows. We validate GUIDE on three benchmarks: an industrial e-commerce dataset of 932 trajectories, AGENTREWARDBENCH spanning five web agent tasks with 1302 trajectories, and AndroidBench for mobile device control. Across all settings, GUIDE substantially outperforms existing evaluators-achieving up to 5.35 percentage points higher accuracy than the strongest baseline-while producing structured diagnostic reports that directly inform agent improvement.

QED-Nano: Teaching a Tiny Model to Prove Hard Theorems

arXiv:2604.04898v1 Announce Type: new Abstract: Proprietary AI systems have recently demonstrated impressive capabilities on complex proof-based problems, with gold-level performance reported at the 2025 International Mathematical Olympiad (IMO). However, the training pipelines behind these systems remain largely undisclosed, and their reliance on large "internal" models and scaffolds makes them expensive to run, difficult to reproduce, and hard to study or improve upon. This raises a central question: can small, open models also be trained to achieve competitive reasoning performance on difficult Olympiad-level math? In this paper, we answer this question by building QED-Nano, a 4B model post-trained for Olympiad-level proofs. Our training recipe has three stages: (1) supervised fine-tuning to imbue good proof-writing styles by distilling from DeepSeek-Math-V2, (2) reinforcement learning (RL) with rubric-based rewards, and (3) expanding RL with a reasoning cache, which decomposes long proofs into iterative summarize-and-refine cycles and enables stronger test-time reasoning. QED-Nano surpasses the proof-generation performance of much larger open models, including Nomos-1 and GPT-OSS-120B, and approaches the performance of proprietary models like Gemini 3 Pro, at a fraction of the inference cost. To support further research on open mathematical reasoning, we release the full QED-Nano pipeline, including the QED-Nano and QED-Nano-SFT models, the FineProofs-SFT and FineProofs-RL datasets, and the training and evaluation code.
❌