❌

Normal view

Received — 15 September 2026 ⏭

Do Influence-Derived Data Perturbations Enable Machine Unlearning? A Controlled Study of Three Plausible Roles

✇cs.AI, q-bio.NC updates on arXiv.org
By: Chenkai Wu · Chrispine Kambimbi · Qinyang Zeng · Jun Yan
14 September 2026 at 12:00
arXiv:2609.12313v1 Announce Type: new Abstract: We evaluate Deep Perturbation Learning (DPL), which perturbs training images and labels along influence-derived directions, in three roles in which prior work has positioned it for machine unlearning: a direct deletion signal (the strongest claim), a utility-preserving regularizer, and a warm start for adversarial unlearning. Evidence for the weaker roles has been used to support the stronger one, so we test each role separately under a matched protocol with exact-seed retraining baselines. An audit of the public implementation identifies two correctness issues: image directions are computed on augmented, normalized tensors but applied to raw images, and the label perturbation falls below float32 resolution, leaving labels unchanged. After correcting the image-perturbation pipeline, DPL fails the direct-deletion criterion on CIFAR-10/ResNet-18 in all three paired seeds. Its utility effects are inconsistent in sign across seeds, and once direction-computation time is counted it underperforms simple warm-start baselines. A one-seed Tiny ImageNet check likewise does not favor DPL as a regularizer or warm start; preprocessing inconsistencies in the released code make the direct comparison there inconclusive. These results cover random instance deletion only and do not rule out influence-based methods in other deletion regimes. We release a role-matched evaluation protocol and an audit checklist for perturbation-based deletion claims.
Received — 10 September 2026 ⏭

Synchronized latency reversal and immune clearance by a multifunctional fusion protein enables HIV-1 reservoir reduction

✇Molecular Therapy
By: Fei Luo · Yinghui Cao · Na Liu · Xiaowei Wang · Wenjia Hu · Yajun Yan · Xiaoqing Xie · Dongmei Jiang · Yangyang Xu · Jun Wang · Hongyu Wang · Zhenyang Yu · Peng Qian · Shicheng Wan · Zhida Liu · Yan Gong · Tielong Chen · Shihui Song · Yong Xiong · Xiaoping Tang · Linghua Li · Li Wang · Haisheng Yu · Liang Cheng
29 July 2026 at 08:00
Latent HIV reservoirs evade both antiviral therapy and immune surveillance. Luo and colleagues develop a multifunctional fusion protein that couples reservoir reactivation with targeted immune engagement and clearance, offering a coordinated strategy to expose and eliminate persistent HIV-infected cells.

The redox architecture of gestational diabetes mellitus: from cellular stress engine to epigenetic and mitochondrial rewiring

✇(Multiomics OR Omics) AND (Pancreatic)
By: Haijuan Zhang · Shaoxiong Zhang · Yuanhao Liu · Jinjiang Shi · Aijun Yang · Ruirui Jin · Yuxia Jin · Xuya Wang · Yitao Fan · Qian Liu · Yanhua Zhang · Cheng Wang · Jianjun Mao · Zhiyuan Zheng · Ling Lv · Muzhou Teng
9 September 2026 at 18:00

Free Radic Biol Med. 2026 Sep 9;256:441-460. doi: 10.1016/j.freeradbiomed.2026.09.006. Online ahead of print.

ABSTRACT

Gestational diabetes mellitus (GDM) is a common pregnancy complication with a rising global prevalence, posing serious short-term and long-term health threats to both mothers and offspring. This review repositions GDM as a systemic disorder in which oxidative stress acts as a proposed mechanistic hub, linking upstream risk factors to downstream pathophysiology. We first examine how "upstream" factors-including genetic susceptibility, pre-conception status, and environmental exposures-converge to promote a state of pathological redox imbalance. We then examine key mechanistic pathways through which oxidative stress is thought to contribute to systemic insulin resistance and pancreatic β-cell failure, highlighting novel pathways involving intercellular communication via tunneling nanotubes and exosomes. Furthermore, we explore the downstream cascade, where oxidative stress may program maternal accelerated biological aging and multi-organ offspring disease trajectories through nuclear epigenetic programming and mitochondrial dysfunction programming, leaving what has been termed a persistent "metabolic memory". Consequently, this review evaluates emerging strategies that target oxidative stress for early prediction and precision intervention. Early prediction models based on direct redox biomarkers and multi-omics signatures hold potential to shift diagnosis from late-gestation oral glucose tolerance test (OGTT) to first-trimester risk stratification. Current supporting evidence draws from human epidemiological associations, ex vivo placental analyses, and experimental models. However, direct causal and interventional validation in pregnant women remains limited. Integrating targeted redox risk stratification and precision interventions into a life-course clinical framework may help interrupt the intergenerational transmission of metabolic disease initiated by GDM.

PMID:42716407 | DOI:10.1016/j.freeradbiomed.2026.09.006

Received — 27 May 2026 ⏭

A visual analysis of the research dynamics of biomarkers for lung cancer screening

✇(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Huange Zhu · Burong Li · Ranran Kong · Jun Yang · Zeqi Guo · Jiafeng Yin
26 May 2026 at 18:00

Clin Epigenetics. 2026 May 26;18(1):90. doi: 10.1186/s13148-026-02084-2.

ABSTRACT

BACKGROUND: Non-invasive biomarkers offer potential to improve risk stratification and early diagnosis of lung cancer, complementing low-dose computed tomography (LDCT) screening. This study employed bibliometric analysis to identify global research trends, collaborative networks, and future directions in lung cancer biomarker research. Publications on lung cancer biomarkers for screening were retrieved from the Web of Science Core Collection (WoSCC). Data processing and visualisation were performed using Citespace, VOSviewer, KH Coder, Latent Dirichlet Allocation (LDA) topic modelling, and the online bibliometric analysis platform. Burst detection analysis was performed to predict emerging research trends.

RESULTS: Analysis of 3636 publications revealed exponential growth in research output since 2014. International collaboration demonstrated a dual-core structure centred on China and the United States, with Chinese institutions showing high publication volumes and American institutions demonstrating greater citation influence. Journal citation mapping revealed three evolutionary phases: basic mechanisms-clinical translation-intelligent integration. LDA topic modelling identified 22 topics grouped into five core research directions: imaging and pathological diagnostic techniques; molecular and omics marker research; liquid biopsy and new detection technologies; clinical and translational medicine research; and tumour biology and treatment mechanisms. Burst detection analysis predicted future four priority areas: epigenetic studies centred on DNA methylation for risk prediction; treatment resistance and invasion mechanisms; liquid biopsy technology development; and targeted therapy clinical trials.

CONCLUSIONS: Lung cancer biomarker research has evolved towards multimodal, intelligent screening approaches. Future research priorities include DNA methylation-based markers, circulating microRNA signatures, and artificial intelligence-assisted diagnostic platforms to improve early detection accuracy and complement LDCT screening.

PMID:42185923 | DOI:10.1186/s13148-026-02084-2

EchoPilot: Training-Free Ultrasound Video Segmentation via Scale-Space Semantic Prompting and Reliability-Gated Memory

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ruiqiang Xiao · Zhaohu Xing · Yijun Yang · Zhenyan Han · Weiming Wang · Kaishun Wu · Lei Zhu
26 May 2026 at 12:00
arXiv:2605.25944v1 Announce Type: cross Abstract: Ultrasound video segmentation is clinically valuable yet difficult due to speckle noise, weak boundaries, and rapid anatomical deformation. Recent promptable foundation models enable point-guided segmentation, but their direct deployment in ultrasound remains unreliable: a single point provides insufficient spatial context to resolve scale ambiguity, and greedy memory updates amplify early errors into severe temporal drift. We present EchoPilot, a training-free framework for ultrasound video segmentation under sparse first-frame interaction, requiring only a single point click and an anatomical category name. EchoPilot orchestrates a frozen medical vision-language model (VLM) for semantic localization, a vision foundation model (VFM) for dense geometric feature extraction, and a promptable video segmentor for mask prediction and propagation. To resolve initialization ambiguity, we propose Scale-Space Semantic Prompting, which first selects an optimal contextual view via a parameter-free S.E.E.D. (Semantic Energy-Entropy Density) criterion, and then synthesizes geometrically precise auxiliary point prompts from dense foundation features without additional user interaction. To reduce propagation drift, a Reliability-Gated Memory update is further introduced to selectively freeze the segmentor's memory bank under uncertain predictions, preventing error accumulation. We also contribute the first dynamic fetal placenta ultrasound video segmentation dataset with 671 annotated frames. Across three ultrasound video datasets, EchoPilot achieves state-of-the-art performance under the sparse-interactive setting, consistently outperforming training-free baselines and finetuned specialists.

A review of organoid-immune co-culture platforms to model the immune microenvironment of hepatocellular carcinoma and guide immunotherapy

✇Omics in Hepatocellular
By: Wen-Wen Liu · Xi-Shuai Xie · Xiao-Jun Yang
21 May 2026 at 18:00

J Transl Med. 2026 May 20. doi: 10.1186/s12967-026-08278-9. Online ahead of print.

ABSTRACT

BACKGROUND: Hepatocellular carcinoma (HCC) is characterized by a highly immunosuppressive and heterogeneous tumor microenvironment that limits the effectiveness of current immunotherapies. Conventional two-dimensional cultures and animal models fail to fully capture patient-specific tumor-immune interactions, creating an urgent need for more physiologically relevant platforms.

MAIN BODY: This review summarizes recent advances in co-culture systems integrating patient-derived HCC organoids with defined immune cell populations to reconstruct essential features of the tumor microenvironment. We describe strategies for organoid establishment and validation, outline immune cell integration approaches, and compare static three-dimensional cultures, microfluidic organ-on-chip systems, and bioengineered multicellular platforms. We further highlight key tumor-immune interaction mechanisms that have been functionally interrogated in these systems, including immune checkpoint-mediated T-cell dysfunction, adenosine-driven metabolic suppression, and chemokine-regulated immune recruitment. Importantly, we critically evaluate current limitations, including immune cell exhaustion artifacts, lack of stromal and vascular complexity, and variability across protocols, which may affect the reproducibility and translational interpretation of these models. While emerging studies suggest potential for predicting immunotherapy responses, robust clinical validation in HCC remains limited.

CONCLUSIONS: Organoid-immune co-culture platforms represent an emerging translational framework that bridges mechanistic tumor immunology with functional precision oncology. With improved standardization and integration of multicellular bioengineering and multi-omics technologies, these systems have strong potential to guide personalized immunotherapy strategies, although further clinical validation is required.

PMID:42163357 | DOI:10.1186/s12967-026-08278-9

Received — 8 April 2026 ⏭

PSY-STEP: Structuring Therapeutic Targets and Action Sequences for Proactive Counseling Dialogue Systems

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jihyun Lee · Yejin Min · Yejin Jeon · SungJun Yang · Hyounghun Kim · Gary Geunbae Lee
7 April 2026 at 12:00
arXiv:2604.04448v1 Announce Type: new Abstract: Cognitive Behavioral Therapy (CBT) aims to identify and restructure automatic negative thoughts pertaining to involuntary interpretations of events, yet existing counseling agents struggle to identify and address them in dialogue settings. To bridge this gap, we introduce STEP, a dataset that models CBT counseling by explicitly reflecting automatic thoughts alongside dynamic, action-level counseling sequences. Using this dataset, we train STEPPER, a counseling agent that proactively elicits automatic thoughts and executes cognitively grounded interventions. To further enhance both decision accuracy and empathic responsiveness, we refine STEPPER through preference learning based on simulated, synthesized counseling sessions. Extensive CBT-aligned evaluations show that STEPPER delivers more clinically grounded, coherent, and personalized counseling compared to other strong baseline models, and achieves higher counselor competence without inducing emotional disruption.
Received — 2 April 2026 ⏭

PAIR-Former: Budgeted Relational MIL for miRNA Target Prediction

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jiaqi Yin · Baiming Chen · Jia Fei · Mingjun Yang
1 April 2026 at 12:00
arXiv:2602.00465v2 Announce Type: replace-cross Abstract: Functional miRNA--mRNA targeting is a large-bag prediction problem: each transcript yields a heavy-tailed pool of candidate target sites (CTSs), yet only a pair-level label is observed. We formalize this regime as \emph{Budgeted Relational Multi-Instance Learning (BR-MIL)}, where at most $K$ instances per bag may receive expensive encoding and relational processing under a hard compute budget. We propose \textbf{PAIR-Former} (Pool-Aware Instance-Relational Transformer), a BR-MIL pipeline that performs a cheap full-pool scan, selects up to $K$ diverse CTSs on CPU, and applies a permutation-invariant Set Transformer aggregator on the selected tokens. On miRAW, PAIR-Former outperforms strong pooling baselines at a practical operating budget ($K^\star{=}64$) while providing a controllable accuracy--compute trade-off as $K$ varies. We further provide theory linking budgeted selection to (i) approximation error decreasing with $K$ and (ii) generalization terms governed by $K$ in the expensive relational component.
Received — 26 March 2026 ⏭

UAV-DETR: DETR for Anti-Drone Target Detection

✇cs.AI, q-bio.NC updates on arXiv.org
By: Jun Yang · Dong Wang · Hongxu Yin · Hongpeng Li · Jianxiong Yu
25 March 2026 at 12:00
arXiv:2603.22841v1 Announce Type: cross Abstract: Drone detection is pivotal in numerous security and counter-UAV applications. However, existing deep learning-based methods typically struggle to balance robust feature representation with computational efficiency. This challenge is particularly acute when detecting miniature drones against complex backgrounds under severe environmental interference. To address these issues, we introduce UAV-DETR, a novel framework that integrates a small-target-friendly architecture with real-time detection capabilities. Specifically, UAV-DETR features a WTConv-enhanced backbone and a Sliding Window Self-Attention (SWSA-IFI) encoder, capturing the high-frequency structural details of tiny targets while drastically reducing parameter overhead. Furthermore, we propose an Efficient Cross-Scale Feature Recalibration and Fusion Network (ECFRFN) to suppress background noise and aggregate multi-scale semantics. To further enhance accuracy, UAV-DETR incorporates a hybrid Inner-CIoU and NWD loss strategy, mitigating the extreme sensitivity of standard IoU metrics to minor positional deviations in small objects. Extensive experiments demonstrate that UAV-DETR significantly outperforms the baseline RT-DETR on our custom UAV dataset (+6.61% in mAP50:95, with a 39.8% reduction in parameters) and the public DUT-ANTI-UAV benchmark (+1.4% in Precision, +1.0% in F1-Score). These results establish UAV-DETR as a superior trade-off between efficiency and precision in counter-UAV object detection. The code is available at https://github.com/wd-sir/UAVDETR.

When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal Reasoning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zhengxian Wu · Kai Shi · Chuanrui Zhang · Zirui Liao · Jun Yang · Ni Yang · Qiuying Peng · Luyuan Zhang · Hangrui Xu · Tianhuang Su · Zhenyu Yang · Haonan Lu · Haoqian Wang
25 March 2026 at 12:00
arXiv:2603.21289v2 Announce Type: replace-cross Abstract: Recent progress in multimodal large language models has led to strong performance on reasoning tasks, but these improvements largely rely on high-quality annotated data or teacher-model distillation, both of which are costly and difficult to scale. To address this, we propose an unsupervised self-evolution training framework for multimodal reasoning that achieves stable performance improvements without using human-annotated answers or external reward models. For each input, we sample multiple reasoning trajectories and jointly model their within group structure. We use the Actor's self-consistency signal as a training prior, and introduce a bounded Judge based modulation to continuously reweight trajectories of different quality. We further model the modulated scores as a group level distribution and convert absolute scores into relative advantages within each group, enabling more robust policy updates. Trained with Group Relative Policy Optimization (GRPO) on unlabeled data, our method consistently improves reasoning performance and generalization on five mathematical reasoning benchmarks, offering a scalable path toward self-evolving multimodal models. The code are available at https://github.com/OPPO-Mente-Lab/LLM-Self-Judge.

Inactivating <i>SnRK1β1A</i> promotes broad-spectrum disease resistance in rice

✇Nature - Issue - nature.com science feeds
By: Guixin Yuan · Xunli Lu · Xingbin Wang · Mengfei Li · Shiwei Wang · Zhaoxiang Huang · Zhigang Li · Fengrui Zhang · Xin Zhang · Jun Yang · Hailong Guo · Vijai Bhadauria · Wang-Sheng Zhu · Wensheng Zhao · Meng Yuan · Jian-Min Zhou · You-Liang Peng
25 March 2026 at 08:00

Nature, Published online: 25 March 2026; doi:10.1038/s41586-026-10273-5

SnRK1β1A in rice promotes susceptibility to multiple fungal diseases, and disrupting this infection-inducible gene confers broad-spectrum resistance without compromising growth or yield under normal field conditions.
Received — 17 March 2026 ⏭

Towards AI Search Paradigm

✇cs.AI, q-bio.NC updates on arXiv.org
By: Yuchen Li · Hengyi Cai · Rui Kong · Xinran Chen · Jiamin Chen · Jun Yang · Haojie Zhang · Jiayi Li · Jiayi Wu · Yiqun Chen · Changle Qu · Wenwen Ye · Lixin Su · Xinyu Ma · Lingyong Yan · Long Xia · Daiting Shi · Junfeng Wang · Xiangyu Zhao · Jiashu Zhao · Haoyi Xiong · Shuaiqiang Wang · Dawei Yin
16 March 2026 at 12:00
arXiv:2506.17188v2 Announce Type: replace-cross Abstract: In this paper, we introduce the AI Search Paradigm, a comprehensive blueprint for next-generation search systems capable of emulating human information processing and decision-making. The paradigm employs a modular architecture of four LLM-powered agents (Master, Planner, Executor and Writer) that dynamically adapt to the full spectrum of information needs, from simple factual queries to complex multi-stage reasoning tasks. These agents collaborate dynamically through coordinated workflows to evaluate query complexity, decompose problems into executable plans, and orchestrate tool usage, task execution, and content synthesis. We systematically present key methodologies for realizing this paradigm, including task planning and tool integration, execution strategies, aligned and robust retrieval-augmented generation, and efficient LLM inference, spanning both algorithmic techniques and infrastructure-level optimizations. By providing an in-depth guide to these foundational components, this work aims to inform the development of trustworthy, adaptive, and scalable AI search systems.
Received — 5 March 2026 ⏭

xLLM Technical Report

✇cs.AI, q-bio.NC updates on arXiv.org
By: Tongxuan Liu · Tao Peng · Peijun Yang · Xiaoyang Zhao · Xiusheng Lu · Weizhe Huang · Zirui Liu · Xiaoyu Chen · Zhiwei Liang · Jun Xiong · Donghe Jin · Minchao Zhang · Jinrong Guo · Yingxu Deng · Xu Zhang · Xianzhe Dong · Siqi Wang · Siyu Wu · Yu Wu · Zihan Tang · Yuting Zeng · Yanshu Wang · Jinguang Liu · Meng Kang · Menxin Li · Yunlong Wang · Yiming Liu · Xiaolong Ma · Yifan Wang · Yichen Zhang · Jinrun Yin · Keyang Zheng · Jiawei Yin · Jun Zhang · Ziyue Wang · Xiaobo Lin · Liangyu Liu · Liwei Lan · Yang Liu · Chunhua Peng · Han Liu · Songcheng Ren · Xuezhu Wang · Yunheng Shen · Yi Wang · Guyue Liu · Yitao Hu · Hui Chen · Tong Yang · Hailong Yang · Jing Li · Guiguang Ding · Ke Zhang
4 March 2026 at 13:00
arXiv:2510.14686v2 Announce Type: replace-cross Abstract: We introduce xLLM, an intelligent and efficient Large Language Model (LLM) inference framework designed for high-performance, large-scale enterprise-grade serving, with deep optimizations for diverse AI accelerators. To address these challenges, xLLM builds a novel decoupled service-engine architecture. At the service layer, xLLM-Service features an intelligent scheduling module that efficiently processes multimodal requests and co-locates online and offline tasks through unified elastic scheduling to maximize cluster utilization. This module also relies on a workload-adaptive dynamic Prefill-Decode (PD) disaggregation policy and a novel Encode-Prefill-Decode (EPD) disaggregation policy designed for multimodal inputs. Furthermore, it incorporates a distributed architecture to provide global KV Cache management and robust fault-tolerant capabilities for high availability. At the engine layer, xLLM-Engine co-optimizes system and algorithm designs to fully saturate computing resources. This is achieved through comprehensive multi-layer execution pipeline optimizations, an adaptive graph mode and an xTensor memory management. xLLM-Engine also further integrates algorithmic enhancements such as optimized speculative decoding and dynamic EPLB, collectively serving to substantially boost throughput and inference efficiency. Extensive evaluations demonstrate that xLLM delivers significantly superior performance and resource efficiency. Under identical TPOT constraints, xLLM achieves throughput up to 1.7x that of MindIE and 2.2x that of vLLM-Ascend with Qwen-series models, while maintaining an average throughput of 1.7x that of MindIE with Deepseek-series models. xLLM framework is publicly available at https://github.com/jd-opensource/xllm and https://github.com/jd-opensource/xllm-service.
Received — 25 February 2026 ⏭

Analysis of approximate linear programming solution to Markov decision problem with log barrier function

✇cs.AI, q-bio.NC updates on arXiv.org
By: Donghwan Lee · Hyukjun Yang · Bum Geun Park
24 February 2026 at 13:00
arXiv:2509.19800v3 Announce Type: replace Abstract: There are two primary approaches to solving Markov decision problems (MDPs): dynamic programming based on the Bellman equation and linear programming (LP). Dynamic programming methods are the most widely used and form the foundation of both classical and modern reinforcement learning (RL). By contrast, LP-based methods have been less commonly employed, although they have recently gained attention in contexts such as offline RL. The relative underuse of the LP-based methods stems from the fact that it leads to an inequality-constrained optimization problem, which is generally more challenging to solve effectively compared with Bellman-equation-based methods. The purpose of this paper is to establish a theoretical foundation for solving LP-based MDPs in a more effective and practical manner. Our key idea is to leverage the log-barrier function, widely used in inequality-constrained optimization, to transform the LP formulation of the MDP into an unconstrained optimization problem. This reformulation enables approximate solutions to be obtained easily via gradient descent. While the method may appear simple, to the best of our knowledge, a thorough theoretical interpretation of this approach has not yet been developed. This paper aims to bridge this gap.

Verifying Chain-of-Thought Reasoning via Its Computational Graph

✇cs.AI, q-bio.NC updates on arXiv.org
By: Zheng Zhao · Yeskendir Koishekenov · Xianjun Yang · Naila Murray · Nicola Cancedda
24 February 2026 at 13:00
arXiv:2510.09312v2 Announce Type: replace-cross Abstract: Current Chain-of-Thought (CoT) verification methods predict reasoning correctness based on outputs (black-box) or activations (gray-box), but offer limited insight into why a computation fails. We introduce a white-box method: Circuit-based Reasoning Verification (CRV). We hypothesize that attribution graphs of correct CoT steps, viewed as execution traces of the model's latent reasoning circuits, possess distinct structural fingerprints from those of incorrect steps. By training a classifier on structural features of these graphs, we show that these traces contain a powerful signal of reasoning errors. Our white-box approach yields novel scientific insights unattainable by other methods. (1) We demonstrate that structural signatures of error are highly predictive, establishing the viability of verifying reasoning directly via its computational graph. (2) We find these signatures to be highly domain-specific, revealing that failures in different reasoning tasks manifest as distinct computational patterns. (3) We provide evidence that these signatures are not merely correlational; by using our analysis to guide targeted interventions on individual transcoder features, we successfully correct the model's faulty reasoning. Our work shows that, by scrutinizing a model's computational process, we can move from simple error detection to a deeper, causal understanding of LLM reasoning.

Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning

✇cs.AI, q-bio.NC updates on arXiv.org
By: Ran Xu · Jingjing Chen · Jiayu Ye · Yu Wu · Jun Yan · Carl Yang · Hongkun Yu
24 February 2026 at 13:00
arXiv:2510.23038v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are widely used as judges to evaluate response quality, providing a scalable alternative to human evaluation. However, most LLM judges operate solely on intrinsic text-based reasoning, limiting their ability to verify complex constraints or perform accurate computation. Motivated by the success of tool-integrated reasoning (TIR) in numerous tasks, we propose TIR-Judge, an end-to-end RL framework for training LLM judges that integrates a code executor for precise evaluation. TIR-Judge is built on three principles: (i) diverse training across verifiable and non-verifiable domains, (ii) flexible judgment formats (pointwise, pairwise, listwise), and (iii) iterative RL that bootstraps directly from the initial model without distillation. On seven public benchmarks, TIR-Judge surpasses strong reasoning-based judges by up to 6.4% (pointwise) and 7.7% (pairwise), and achieves listwise performance comparable to Claude-Opus-4 despite having only 8B parameters. Remarkably, TIR-Judge-Zero - trained entirely without distilled judge trajectories, matches the performance of distilled variants, demonstrating that tool-augmented judges can self-evolve through iterative reinforcement learning.
There are no more articles
❌