❌

Normal view

Received today — 7 October 2026 ⏭

Chronic Ileitis Ameliorates Hyperglycemia via a 3-HB/NKX6.1 Axis in Mice

✇(Multiomics OR Omics) AND (Pancreatic)
By: Yi Fang · Chang Zheng · Ping Jiang · Jiajing Luo · Ying Xiang · Jinping Yang · Yaoyao Li · Runqiu Jiang · Guifang Xu
24 September 2026 at 18:00

Mol Cell Endocrinol. 2026 Sep 24:112920. doi: 10.1016/j.mce.2026.112920. Online ahead of print.

ABSTRACT

Clinical evidence suggests a complex link between inflammatory bowel disease and systemic glucose homeostasis, yet the underlying molecular mechanisms remain elusive. Here, we report that chronic ileitis, induced by dextran sulfate sodium (DSS) or IL10 deficiency under a high-fat diet(HFD), paradoxically ameliorates systemic glucose intolerance and preserves pancreatic β-cell mass in mice. Multi-omics analysis of ileal contents revealed a specific enrichment of Akkermansia muciniphila (AKK) and elevated levels of the metabolite 3-hydroxybutyrate (3-HB). Mechanistically, 3-HB activated HCAR2/CREB-associated signaling and increased NKX6.1 expression. NKX6.1 loss-of-function markedly attenuated 3-HB-induced insulin gene expression and glucose-stimulated insulin secretion, establishing NKX6.1 as an important functional mediator of the β-cell response to 3-HB. Furthermore, exogenous administration of 3-HB recapitulated these protective effects in diabetic mice. This study identifies a novel gut-islet axis where microbiota-derived 3-HB preserves β-cell functional identity via HCAR2 dependent regulation of NKX6.1, offering a potential therapeutic strategy for type 2 diabetes.

PMID:42785509 | DOI:10.1016/j.mce.2026.112920

Received — 15 September 2026 ⏭

Clonal evolution in gastrointestinal cancers: multi-omics insights into tumor heterogeneity, microenvironmental selection, and translational biomarkers

✇Omics in Gastric
By: Wenyi Fan · Chunhong Zheng
12 September 2026 at 18:00

Front Oncol. 2026 Aug 28;16:1907210. doi: 10.3389/fonc.2026.1907210. eCollection 2026.

ABSTRACT

Clonal evolution in hepatocellular carcinoma (HCC), esophageal squamous cell carcinoma (ESCC), and gastric cancer (GC) reflects the interaction of genetic diversification, cell-state plasticity, and tissue-specific selection. Multi-region and single-cell DNA sequencing resolve truncal and subclonal lineages, whereas single-cell and spatial transcriptomics, proteomics, and serial liquid biopsy characterize cellular states, ecological niches, and temporal dynamics. The three cancers differ in dissemination timing, dominant selective pressures, and biomarker maturity: early seeding is best supported in selected HCC cohorts, ESCC is strongly influenced by field cancerization and epithelial-stromal crosstalk, and GC follows subtype- and ecotype-dependent trajectories. We discuss the assumptions and sampling biases that constrain phylogenetic inference, the causal limits of cross-sectional tumor atlases, clonal hematopoiesis, and the incremental value of broad multi-omics over focused assays. Liquid-biopsy detection of minimal residual disease is prognostic, but treatment benefit from marker-guided intervention remains context dependent. Near-term translation requires standardized, decision-linked assays; adaptive therapy and evolutionary steering remain investigational.

PMID:42729528 | PMC:PMC13563159 | DOI:10.3389/fonc.2026.1907210

Received — 13 September 2026 ⏭

Clonal evolution in gastrointestinal cancers: multi-omics insights into tumor heterogeneity, microenvironmental selection, and translational biomarkers

✇Omics in Hepatocellular
By: Wenyi Fan · Chunhong Zheng
12 September 2026 at 18:00

Front Oncol. 2026 Aug 28;16:1907210. doi: 10.3389/fonc.2026.1907210. eCollection 2026.

ABSTRACT

Clonal evolution in hepatocellular carcinoma (HCC), esophageal squamous cell carcinoma (ESCC), and gastric cancer (GC) reflects the interaction of genetic diversification, cell-state plasticity, and tissue-specific selection. Multi-region and single-cell DNA sequencing resolve truncal and subclonal lineages, whereas single-cell and spatial transcriptomics, proteomics, and serial liquid biopsy characterize cellular states, ecological niches, and temporal dynamics. The three cancers differ in dissemination timing, dominant selective pressures, and biomarker maturity: early seeding is best supported in selected HCC cohorts, ESCC is strongly influenced by field cancerization and epithelial-stromal crosstalk, and GC follows subtype- and ecotype-dependent trajectories. We discuss the assumptions and sampling biases that constrain phylogenetic inference, the causal limits of cross-sectional tumor atlases, clonal hematopoiesis, and the incremental value of broad multi-omics over focused assays. Liquid-biopsy detection of minimal residual disease is prognostic, but treatment benefit from marker-guided intervention remains context dependent. Near-term translation requires standardized, decision-linked assays; adaptive therapy and evolutionary steering remain investigational.

PMID:42729528 | PMC:PMC13563159 | DOI:10.3389/fonc.2026.1907210

Clonal evolution in gastrointestinal cancers: multi-omics insights into tumor heterogeneity, microenvironmental selection, and translational biomarkers

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Wenyi Fan · Chunhong Zheng
12 September 2026 at 18:00

Front Oncol. 2026 Aug 28;16:1907210. doi: 10.3389/fonc.2026.1907210. eCollection 2026.

ABSTRACT

Clonal evolution in hepatocellular carcinoma (HCC), esophageal squamous cell carcinoma (ESCC), and gastric cancer (GC) reflects the interaction of genetic diversification, cell-state plasticity, and tissue-specific selection. Multi-region and single-cell DNA sequencing resolve truncal and subclonal lineages, whereas single-cell and spatial transcriptomics, proteomics, and serial liquid biopsy characterize cellular states, ecological niches, and temporal dynamics. The three cancers differ in dissemination timing, dominant selective pressures, and biomarker maturity: early seeding is best supported in selected HCC cohorts, ESCC is strongly influenced by field cancerization and epithelial-stromal crosstalk, and GC follows subtype- and ecotype-dependent trajectories. We discuss the assumptions and sampling biases that constrain phylogenetic inference, the causal limits of cross-sectional tumor atlases, clonal hematopoiesis, and the incremental value of broad multi-omics over focused assays. Liquid-biopsy detection of minimal residual disease is prognostic, but treatment benefit from marker-guided intervention remains context dependent. Near-term translation requires standardized, decision-linked assays; adaptive therapy and evolutionary steering remain investigational.

PMID:42729528 | PMC:PMC13563159 | DOI:10.3389/fonc.2026.1907210

Clonal evolution in gastrointestinal cancers: multi-omics insights into tumor heterogeneity, microenvironmental selection, and translational biomarkers

✇MRD
By: Wenyi Fan · Chunhong Zheng
12 September 2026 at 18:00

Front Oncol. 2026 Aug 28;16:1907210. doi: 10.3389/fonc.2026.1907210. eCollection 2026.

ABSTRACT

Clonal evolution in hepatocellular carcinoma (HCC), esophageal squamous cell carcinoma (ESCC), and gastric cancer (GC) reflects the interaction of genetic diversification, cell-state plasticity, and tissue-specific selection. Multi-region and single-cell DNA sequencing resolve truncal and subclonal lineages, whereas single-cell and spatial transcriptomics, proteomics, and serial liquid biopsy characterize cellular states, ecological niches, and temporal dynamics. The three cancers differ in dissemination timing, dominant selective pressures, and biomarker maturity: early seeding is best supported in selected HCC cohorts, ESCC is strongly influenced by field cancerization and epithelial-stromal crosstalk, and GC follows subtype- and ecotype-dependent trajectories. We discuss the assumptions and sampling biases that constrain phylogenetic inference, the causal limits of cross-sectional tumor atlases, clonal hematopoiesis, and the incremental value of broad multi-omics over focused assays. Liquid-biopsy detection of minimal residual disease is prognostic, but treatment benefit from marker-guided intervention remains context dependent. Near-term translation requires standardized, decision-linked assays; adaptive therapy and evolutionary steering remain investigational.

PMID:42729528 | PMC:PMC13563159 | DOI:10.3389/fonc.2026.1907210

Received — 10 September 2026 ⏭

Can AI Agents Detect and Repair Artifact Drift in Network Experiments?

✇cs.AI, q-bio.NC updates on arXiv.org
By: Tianzhu Zhang · Weichen Tao · Changgang Zheng · Yusheng Zheng · Long Chen · Xiaoyi Fan · Meikang Qiu
10 September 2026 at 12:00
arXiv:2609.09849v1 Announce Type: cross Abstract: In recent years, AI agents have evolved into capable assistants that carry out multi-step tasks in digital environments. The network systems community is beginning to explore these capabilities in operational and experimental settings. However, an agent operating in network systems should not be judged solely by whether it completes the immediate task. The experiment record it modifies must also remain trustworthy. We call this property artifact integrity: the record's claims must remain supported by the available evidence, confined to the scope established by that evidence, and traceable through the artifacts that encode their support. To make this property measurable, we introduce NetArtifactBench, which tests whether AI agents can repair inconsistent records derived from public network-system artifacts while preserving claims that remain supported. The benchmark contains 52 instances with injected inconsistencies ranging from direct contradictions to unstated relations spread across several artifacts. We evaluate 23 agent configurations across three general-purpose AI agent runtimes using deterministic scoring. The average contract pass rate is 65.3 % across 5,980 outputs, but no agent runtime exceeds 30 % when repair requires recovering implicit relations and propagating changes across artifacts. These results reveal a sharp boundary between local correction and complete record-level repair. Therefore, we argue that artifact integrity should become a first-class design and evaluation requirement for AI agents operating on network systems.

MCAT-mediated mitochondrial fatty acid metabolism regulates Lauren subtype divergence and suppresses gastric cancer progression through ROS/P53-dependent mitophagy and ferroptosis

✇Omics in Gastric
By: Yufei Wang · Meng Zhu · Xin Yin · Tianyi Fang · Lei Zhang · Yujuan Jiao · Hongxin Wang · Zipu Dong · Tengteng Liu · Yingwei Xue
9 September 2026 at 18:00

Cell Death Differ. 2026 Sep 8. doi: 10.1038/s41418-026-01867-7. Online ahead of print.

ABSTRACT

Gastric cancer (GC) displays marked heterogeneity under the Lauren classification, yet the metabolic determinants of subtype divergence remain unclear. Here, we identify Malonyl-CoA:ACP transacylase (MCAT), a Lauren subtype-associated gene encoding a key mitochondrial fatty acid synthesis (mtFAS) enzyme, as a subtype-specific tumor suppressor in GC. Integrative multi-omics profiling revealed that MCAT expression is enriched in intestinal-type GC and correlates with favorable prognosis. Mechanistically, MCAT overexpression drives metabolic reprogramming through mitochondrial free fatty acid overload, suppressing β-oxidation while elevating mitochondrial reactive oxygen species (ROS), which triggers P53 phosphorylation at Ser15. This event concurrently activates PINK1/Parkin-mediated mitophagy and suppresses the SLC7A11/GPX4 axis to induce ferroptosis. Genetic rescue experiments confirmed that P53-Ser15 phosphorylation is essential for both mitophagy and ferroptosis induction. Endogenous MCAT levels are sufficient to determine basal ROS/P53/mitophagy/ferroptosis axis activity, and knockdown in high-expressing cells reverses these phenotypes, supporting a physiological, threshold-dependent role. In vivo, MCAT overexpression suppresses tumor growth and enhances mitophagy and ferroptosis markers. Collectively, these findings establish MCAT as a metabolic switch that links mtFAS to ROS/P53-dependent cell death, providing a potential biomarker and therapeutic target for GC.

PMID:42711380 | DOI:10.1038/s41418-026-01867-7

MCAT-mediated mitochondrial fatty acid metabolism regulates Lauren subtype divergence and suppresses gastric cancer progression through ROS/P53-dependent mitophagy and ferroptosis

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Yufei Wang · Meng Zhu · Xin Yin · Tianyi Fang · Lei Zhang · Yujuan Jiao · Hongxin Wang · Zipu Dong · Tengteng Liu · Yingwei Xue
9 September 2026 at 18:00

Cell Death Differ. 2026 Sep 8. doi: 10.1038/s41418-026-01867-7. Online ahead of print.

ABSTRACT

Gastric cancer (GC) displays marked heterogeneity under the Lauren classification, yet the metabolic determinants of subtype divergence remain unclear. Here, we identify Malonyl-CoA:ACP transacylase (MCAT), a Lauren subtype-associated gene encoding a key mitochondrial fatty acid synthesis (mtFAS) enzyme, as a subtype-specific tumor suppressor in GC. Integrative multi-omics profiling revealed that MCAT expression is enriched in intestinal-type GC and correlates with favorable prognosis. Mechanistically, MCAT overexpression drives metabolic reprogramming through mitochondrial free fatty acid overload, suppressing β-oxidation while elevating mitochondrial reactive oxygen species (ROS), which triggers P53 phosphorylation at Ser15. This event concurrently activates PINK1/Parkin-mediated mitophagy and suppresses the SLC7A11/GPX4 axis to induce ferroptosis. Genetic rescue experiments confirmed that P53-Ser15 phosphorylation is essential for both mitophagy and ferroptosis induction. Endogenous MCAT levels are sufficient to determine basal ROS/P53/mitophagy/ferroptosis axis activity, and knockdown in high-expressing cells reverses these phenotypes, supporting a physiological, threshold-dependent role. In vivo, MCAT overexpression suppresses tumor growth and enhances mitophagy and ferroptosis markers. Collectively, these findings establish MCAT as a metabolic switch that links mtFAS to ROS/P53-dependent cell death, providing a potential biomarker and therapeutic target for GC.

PMID:42711380 | DOI:10.1038/s41418-026-01867-7

Received — 27 May 2026 ⏭

Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yuxin Zhang · Mengxue Hu · Zheng Lin · Xiaoyi Fan · Fan Xie · Zihan Fang · Jing Yang · Wenjun Zhu · Zhiwen Chen · Chengfei Lv · Zhe Chen
26 May 2026 at 12:00
arXiv:2605.24598v1 Announce Type: new Abstract: Large language model (LLM) agents excel at solving complex long-horizon tasks through autonomous interaction with environments. However, their real-world deployment faces a fundamental device--cloud dilemma: on-device models are efficient but often brittle, while cloud models are stronger but costly in computation. State-of-the-art LLM device--cloud routers usually make coarse task-level decisions, which cannot adapt to the changing difficulty of multi-step agent interactions. To address this issue, we present Hera, a step-level device--cloud LLM agent coordinator for long-horizon tasks achieving a strong performance--cost Pareto frontier. Hera adopts a novel two-stage training paradigm: (1) imitation learning for cold-start, followed by (2) reinforcement learning that jointly optimizes task success and cloud usage efficiency. The first stage casts step-level routing as a supervised classification problem: the device agent is replayed on cloud trajectories, with each state labeled by the agreement between device and cloud actions. In the second stage, we perform cost-aware reinforcement learning by grouping identical states across trajectories and updating Hera with labels favoring higher expected return and fewer future cloud calls. We evaluate Hera on ALFWorld, WebShop, and AppWorld, where it consistently outperforms prior methods, achieving 92.5% of the cloud-only success rate with cloud use in only 46.3% of steps.

FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization

✇cs.AI, q-bio.NC updates on arXiv.org
By: Minwei Kong · Chonghe Jiang · Ao Qu · Wenbin Ouyang · Zhaoming Zeng · Xiaotong Guo · Zhekai Li · Junyi Li · Yi Fan · Xinshou Zheng · Xi Jing · Yikai Zhang · Zhiwei Liang · Seonghoo Kim · Runqing Yang · Zijian Zhou · Sirui Li · Han Zheng · Wangyang Ying · Ou Zheng · Chonghuan Wang · Jinglong Zhao · Hanzhang Qin · Cathy Wu · Paul Pu Liang · Jinhua Zhao · Hai Wang
26 May 2026 at 12:00
arXiv:2605.25246v2 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for optimization modeling and solver-code generation, yet practical operations research and optimization problems often require a harder capability: designing scalable algorithms that exploit problem structure and outperform direct formulation-and-solve baselines. Existing benchmarks are limited to small or simplified examples far below real-world scale and complexity. We introduce FrontierOR, among the first benchmarks to systematically evaluate LLM-based efficient algorithm design for realistic large-scale optimization problems. FrontierOR includes 180 tasks derived from methodologically diverse papers published in top-tier operations research venues, each with standardized instances and a hidden, expert-verified evaluation suite. We evaluate seven LLMs spanning frontier, cost-effective, and open-source models both in one-shot and test-time evolution settings. The results reveal that frontier models still struggle to move from executable formulations to efficient optimization algorithms: the strongest one-shot model outperforms Gurobi in only 31% of cases in both solution quality and computational efficiency, and even strong coding agents with test-time evolution achieve only 50% on selected hard tasks. FrontierOR establishes a practical evaluation platform for LLM-based optimization algorithm design, which enables future LLMs and agents to be systematically tested on whether they can move beyond correct formulation toward a feasible, high-quality, and efficient algorithm.
Received — 8 April 2026 ⏭

DP-OPD: Differentially Private On-Policy Distillation for Language Models

✇cs.AI, q-bio.NC updates on arXiv.org
By: Fatemeh Khadem · Sajad Mousavi · Yi Fang · Yuhong Liu
7 April 2026 at 12:00
arXiv:2604.04461v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly adapted to proprietary and domain-specific corpora that contain sensitive information, creating a tension between formal privacy guarantees and efficient deployment through model compression. Differential privacy (DP), typically enforced via DP-SGD, provides record-level protection but often incurs substantial utility loss in autoregressive generation, where optimization noise can amplify exposure bias and compounding errors along long rollouts. Existing approaches to private distillation either apply DP-SGD to both teacher and student, worsening computation and the privacy--utility tradeoff, or rely on DP synthetic text generation from a DP-trained teacher, avoiding DP on the student at the cost of DP-optimizing a large teacher and introducing an offline generation pipeline. We propose \textbf{Differentially Private On-Policy Distillation (DP-OPD)}, a synthesis-free framework that enforces privacy solely through DP-SGD on the student while leveraging a frozen teacher to provide dense token-level targets on \emph{student-generated} trajectories. DP-OPD instantiates this idea via \emph{private generalized knowledge distillation} on continuation tokens. Under a strict privacy budget ($\varepsilon=2.0$), DP-OPD improves perplexity over DP fine-tuning and off-policy DP distillation, and outperforms synthesis-based DP distillation (Yelp: 44.15$\rightarrow$41.68; BigPatent: 32.43$\rightarrow$30.63), while substantially simplifying the training pipeline. In particular, \textbf{DP-OPD collapses private compression into a single DP student-training loop} by eliminating DP teacher training and offline synthetic text generation. Code will be released upon publication at https://github.com/khademfatemeh/dp_opd.
Received — 4 April 2026 ⏭

MemRerank: Preference Memory for Personalized Product Reranking

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhiyuan Peng · Xuyang Wu · Huaixiao Tou · Yi Fang · Yu Gong
3 April 2026 at 12:00
arXiv:2603.29247v2 Announce Type: replace-cross Abstract: LLM-based shopping agents increasingly rely on long purchase histories and multi-turn interactions for personalization, yet naively appending raw history to prompts is often ineffective due to noise, length, and relevance mismatch. We propose MemRerank, a preference memory framework that distills user purchase history into concise, query-independent signals for personalized product reranking. To study this problem, we build an end-to-end benchmark and evaluation framework centered on an LLM-based \textbf{1-in-5} selection task, which measures both memory quality and downstream reranking utility. We further train the memory extractor with reinforcement learning (RL), using downstream reranking performance as supervision. Experiments with two LLM-based rerankers show that MemRerank consistently outperforms no-memory, raw-history, and off-the-shelf memory baselines, yielding up to \textbf{+10.61} absolute points in 1-in-5 accuracy. These results suggest that explicit preference memory is a practical and effective building block for personalization in agentic e-commerce systems.
Received — 2 April 2026 ⏭

MemRerank: Preference Memory for Personalized Product Reranking

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhiyuan Peng · Xuyang Wu · Huaixiao Tou · Yi Fang · Yi Gong
1 April 2026 at 12:00
arXiv:2603.29247v1 Announce Type: cross Abstract: LLM-based shopping agents increasingly rely on long purchase histories and multi-turn interactions for personalization, yet naively appending raw history to prompts is often ineffective due to noise, length, and relevance mismatch. We propose MemRerank, a preference memory framework that distills user purchase history into concise, query-independent signals for personalized product reranking. To study this problem, we build an end-to-end benchmark and evaluation framework centered on an LLM-based \textbf{1-in-5} selection task, which measures both memory quality and downstream reranking utility. We further train the memory extractor with reinforcement learning (RL), using downstream reranking performance as supervision. Experiments with two LLM-based rerankers show that MemRerank consistently outperforms no-memory, raw-history, and off-the-shelf memory baselines, yielding up to \textbf{+10.61} absolute points in 1-in-5 accuracy. These results suggest that explicit preference memory is a practical and effective building block for personalization in agentic e-commerce systems.
Received — 25 February 2026 ⏭

Proximity-Based Multi-Turn Optimization: Practical Credit Assignment for LLM Agent Training

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yangyi Fang · Jiaye Lin · Xiaoliang Fu · Cong Qin · Haolin Shi · Chang Liu · Peilin Zhao
24 February 2026 at 13:00
arXiv:2602.19225v1 Announce Type: new Abstract: Multi-turn LLM agents are becoming pivotal to production systems, spanning customer service automation, e-commerce assistance, and interactive task management, where accurately distinguishing high-value informative signals from stochastic noise is critical for sample-efficient training. In real-world scenarios, a failure in a trivial task may reflect random instability, whereas success in a high-difficulty task signifies a genuine capability breakthrough. Yet, existing group-based policy optimization methods rigidly rely on statistical deviation within discrete batches, frequently misallocating credit when task difficulty fluctuates. To address this issue, we propose Proximity-based Multi-turn Optimization (ProxMO), a practical and robust framework engineered specifically for the constraints of real-world deployment. ProxMO integrates global context via two lightweight mechanisms: success-rate-aware modulation dynamically adapts gradient intensity based on episode-level difficulty, while proximity-based soft aggregation derives baselines through continuous semantic weighting at the step level. Extensive evaluations on ALFWorld and WebShop benchmarks demonstrate that ProxMO yields substantial performance gains over existing baselines with negligible computational cost. Ablation studies further validate the independent and synergistic efficacy of both mechanisms. Crucially, ProxMO offers plug-and-play compatibility with standard GRPO frameworks, facilitating immediate, low-friction adoption in existing industrial training pipelines. Our implementation is available at: \href{https://anonymous.4open.science/r/proxmo-B7E7/README.md}{https://anonymous.4open.science/r/proxmo}.

How to Allocate, How to Learn? Dynamic Rollout Allocation and Advantage Modulation for Policy Optimization

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yangyi Fang · Jiaye Lin · Xiaoliang Fu · Cong Qin · Haolin Shi · Chaowen Hu · Lu Pan · Ke Zeng · Xunliang Cai
24 February 2026 at 13:00
arXiv:2602.19208v1 Announce Type: cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for Large Language Model (LLM) reasoning, yet current methods face key challenges in resource allocation and policy optimization dynamics: (i) uniform rollout allocation ignores gradient variance heterogeneity across problems, and (ii) the softmax policy structure causes gradient attenuation for high-confidence correct actions, while excessive gradient updates may destabilize training. Therefore, we propose DynaMO, a theoretically-grounded dual-pronged optimization framework. At the sequence level, we prove that uniform allocation is suboptimal and derive variance-minimizing allocation from the first principle, establishing Bernoulli variance as a computable proxy for gradient informativeness. At the token level, we develop gradient-aware advantage modulation grounded in theoretical analysis of gradient magnitude bounds. Our framework compensates for gradient attenuation of high-confidence correct actions while utilizing entropy changes as computable indicators to stabilize excessive update magnitudes. Extensive experiments conducted on a diverse range of mathematical reasoning benchmarks demonstrate consistent improvements over strong RLVR baselines. Our implementation is available at: \href{https://anonymous.4open.science/r/dynamo-680E/README.md}{https://anonymous.4open.science/r/dynamo}.
There are no more articles
❌