The paper introduces RegretBench, a benchmark of 205 tasks that capture moments where users regret not backing up state, and evaluates six advanced coding agents on their backup awareness. While agents complete 86.1% of tasks, they only back up before regret moments 15.2% of the time, revealing a gap between task success and state preservation. To address this, the authors propose BackUpper, a plug‑in that automatically preserves affected state before tool calls, achieving 92.2% similarity to the original state on RegretBench at a cost of $0.014 per task and aligning with user preferences with an 84.5% F1 score.
By Xu Li, Simon Yu, Minzhou Pan, Yiyou Sun, Zhaorun Chen, Bo Li, Weiyan Shi
NormTune introduces a norm‑guided approach to parameter‑efficient fine‑tuning (PEFT) for reasoning‑intensive tasks, addressing a performance gap caused by under‑adaptation in weight‑update norms. By adaptively strengthening layers with insufficient updates, NormTune consistently improves various PEFT methods across challenging benchmarks. Experiments show significant accuracy gains—up to 24.24% with rank‑8 LoRA on S1K‑1.1—while rank‑256 variants match full fine‑tuning performance.
By Zhangming Li, Qinghao Hu, Weifan Guan, Yifan Zhang, Peisong Wang, Jian Cheng
SpatialBrain is a framework that enhances spatial reasoning by retaining experience about when to observe, reconstruct, measure, or change reference frames while keeping its vision-language backbone unchanged. It fuses current observations into queryable spatial relations, offers reusable tool procedures through a Spatial Skill Library, and associates task conditions with experience via Spatial Cognition. The system abstracts completed trajectories into process records, consolidating knowledge across task blocks to inform future decisions without transferring scene coordinates or reference answers, and demonstrates improved performance on four out of five spatial-reasoning benchmarks.
By Yifan Zhou, Ziyang Gong, Xiaojun Ye, Yifei Liu, Donggang Li, Xiaolong Zhou, Zhihang Zhong, Xue Yang
PreCoMem introduces a memory consolidation framework for long‑horizon dialogue agents, inspired by predictive coding. It represents user memory as confidence‑weighted beliefs and uses an Effective Surprisal signal to decide whether to maintain, profile, or correct each belief. Experiments on LoCoMo, LongMemEval‑S, PersonaMem‑v2, and the new DiMoBench demonstrate state‑of‑the‑art accuracy and robust adaptation to non‑stationary belief drift without over‑reacting to noise.
By Jian Zhong, Zeyu Liu, Pingchuan Cao, Rongduo Han, Shunye Tang, Guohuan Xie, Mingyuan Qin, Ran Ji, Xiao Liang, Wei Wang, Haining Zhang
RubricOpt is a framework that allows a policy to self‑revise the semantic rubric guiding its training. The policy diagnoses its own rubric‑free outputs, keeps clauses that are already satisfied, and edits those that fail to address recurring issues. This revised rubric is then used to steer Direct Preference Optimization (DPO) during training, and the rubric is removed at evaluation, with experiments showing mixed but sometimes positive effects on capability and open‑ended generation benchmarks.
By Wei Chen, Yubing Wu, Shigui Li, Delu Zeng, Jingfeng Liu, Junmei Yang, Zhiheng Zhou, Bo Li, Min Chen, Zhou Wang
GuideEvolve is a self‑evolving agent framework that uses expert guidance and three autonomous regulatory mechanisms—Think Fast and Slow, Throwback, and Termination by choice—to address limitations in existing self‑evolving agents. The framework introduces a task‑specific expert‑evaluation‑driven evolutionary pipeline and integrates the 3Ts mechanisms for cognitive optimization, performance recovery, and adaptive termination. Empirical results on MGSM and MMLU show comparable accuracy to state‑of‑the‑art models, reduced variance, a 100% evolution success rate, and about 50% fewer optimization iterations.
By Meihong Jia, Yasemin Timar, Jonathan Taws
REFLEX is a sequence‑conditioned generator that produces RNA backbone‑frame ensembles using a heteroscedastic stochastic bridge on SE(3). It calibrates residue‑wise bridge widths with experimental B‑factors, allowing each observed conformer to be accessed through local perturbation neighborhoods while maintaining sharpness in constrained regions. In inference, REFLEX requires only the input sequence and, on a multi‑conformer RNA benchmark, achieves the best precision‑recall trade‑off for ensemble coverage across evaluation thresholds, with ablation studies showing improved target‑frame recovery under stronger perturbations.
By Wanli Ma, Tianmeng Hu, Ke Li
The paper investigates how phylogenetic leakage can inflate performance estimates for protein classifiers, particularly in venom ion‑channel target prediction. By treating cross‑species prediction as a structured distribution shift, the authors compare five structural inductive biases using a multimodal graph neural network that fuses ESM‑2 embeddings with a disulfide‑aware attention mechanism. Persistent‑homology representations, which capture backbone geometry through topological descriptors, outperform other biases under a leave‑one‑taxon‑out protocol, achieving 63.4% accuracy versus 54‑55% for other geometric priors and 30% for a sequence‑only baseline.
By Arezoo Bybordi, Favour Achimba, Mariam Gelashvili, Jessy Ramirez, Weigang Qiu, Mand\"e Holford, Anita Raja
The paper surveys recent advances in time series anomaly detection (TSAD), highlighting new architectures such as diffusion models, state space models, and large language models. It introduces a refined anomaly taxonomy, evaluates existing metrics through extensive experiments, and releases an open-source benchmark with algorithms, datasets, and evaluation tools. The authors also identify open research challenges, including dynamic thresholding, interpretability, zero‑shot transfer, multi‑modal alignment, and foundational models for time series.
By Zhijie Zhong, Zhiwen Yu, Pengyu Li, Liujian Zhang, Qiaoli Ni, Jiang Jun, Jianming Lv, Kaixiang Yang, C. L. Philip Chen
The paper introduces FlowGDA, a flow‑matching framework for gradual domain adaptation that models adaptation as continuous transport on a statistical manifold. FlowGDA learns time‑dependent velocity fields to generate smooth domain trajectories, avoiding adversarial Min–Max optimization by using a simulation‑free regression objective. The method incorporates source‑anchored transport, semantic consistency loss, and a two‑stage optimization scheme to prevent semantic drift, achieving superior performance over state‑of‑the‑art techniques.
By Yubo Huang, Yushe Cao, Zixi Wang, Jingzehua Xu, Xin Lai, Xiongyu Hu, Shuai Zhang
Trace2World is a framework that decouples global behavior reconstruction from implementation to create executable GUI environments from real interaction traces. It reconciles traces into a shared, source‑linked app model, compiles an executable environment, and uses independent replay of source workflows to localize mismatches for bounded implementation repair. In experiments, Trace2World built 50 environments from 1,570 traces and reproduced 91.1% of 200 workflows across ten apps, outperforming a task‑local baseline and improving benchmark success and external GUI benchmark scores.
By Zezhou Wang, Hanzhang Zhou, Panrong Tong, Quyu Kong, Pengxiang Li, Steven Hoi, Zhuzhong Qian, Yue Wang
The paper introduces Jev-GAD, a training‑free generalist graph anomaly detection framework that combines complementary structural, attribute, and neighborhood evidence with a single frozen pretrained language model for anomaly assessment. It transforms heterogeneous statistics into graph‑relative percentiles and uses a semantic Graph‑to‑State (G2S) transformation to feed evidence into a non‑generative decision readout, fusing the resulting scores with four statistical measures. Experiments on seven benchmark datasets show Jev‑GAD achieving high AUROC (89.18%) and AUPRC (52.40%) scores, demonstrating the effectiveness of pretrained decision readout and semantic evidence grounding.
By Xinyu Zhao, Qingyun Sun, Ziwei Zhang, Tianchen Zhu, Daqing Li, Jianxin Li
The paper introduces Monte Carlo Privileged Distillation (MCPD) to address reference-induced target instability in on-policy self-distillation (OPSD). MCPD models privileged context as a distribution over partial reference views and averages teacher distributions across these views, yielding a target that matches the expected KL divergence minimization. Experiments on mathematical and scientific reasoning benchmarks show that MCPD provides more reference-consistent supervision and consistently outperforms full-reference OPSD.
By Khouloud Saadi, Di Wang
The paper introduces a ground‑truth‑first benchmarking framework for reinforcement learning that uses converse optimality to construct tasks with certified optimal value functions and policies. It unifies sensitivity benchmarking—sampling certified environments from continuous‑time generators—and oracle‑referenced comparison—using native discrete‑time generators to evaluate policies via optimality gap, regret, and policy error. The methodology extends to non‑smooth, non‑affine, and partially observed settings, and the authors provide code and diagnostics on a public project page.
By Gr\'egoire Ouerdane, Sinan Ibrahim, Stefan Streif, Pavel Osinenko
The paper introduces Kernel-Anticipated Unlearning (KAU), a method for approximate unlearning of knowledge-graph embeddings that accounts for relearning during continued training. KAU uses the tangent kernel to model how forgotten facts’ scores change, expressing this response in closed form and guiding edits to minimize future leakage. Experiments show KAU reduces leakage by 46‑63% on FB15k-237 and 50‑82% on CoDEx-L compared to the strongest existing unlearner, while preserving higher utility.
By Parnian Fazel, Mohammad M Maheri, Hamed Haddadi
The paper introduces nnInteractive Agent, an open‑source system that lets general‑purpose AI agents perform 3D image annotation tasks by interacting with the nnInteractive segmentation model. Users issue plain‑language requests, and the agent automatically identifies targets, places prompts, evaluates and corrects the resulting volumetric masks, and can even generate code for additional processing. On a diverse benchmark of CT, MRI, PET, micro‑CT, and insect scans, agents such as Claude Code and Codex achieve mean Dice scores of 0.81–0.84 from the request alone, matching near‑oracle performance when given target locations.
By Fabian Isensee, Constantin Ulrich Harsy, Maximilian Rokuss, Benjamin Hamm, Philipp Vollmuth, Klaus H. Maier-Hein
The paper introduces Evolving Federated Density Peak Clustering (eFDPC), a one‑shot federated clustering method that merges evolving fuzzy data‑stream clustering with density peak clustering. Each client independently updates micro‑clusters from private mini‑batches, and only selected density peaks are sent to the server, reducing communication. A shuffler‑based anonymization layer protects client contributions, and two variants—eFDPC‑P and eFDPC‑G—are evaluated on synthetic and real datasets, outperforming recent federated clustering baselines in one‑shot settings and handling high‑dimensional, non‑IID data.
By Miha O\v{z}bot, Seiichi Ozawa, Igor \v{S}krjanc
The paper introduces a post‑hoc Feature Selection Layer (FSL) that can be added to frozen pre‑trained neural networks on tabular data to highlight the most important features. This lightweight, trainable module fine‑tunes feature weights based on the original model’s outputs without altering its architecture or parameters. Experiments on synthetic and real‑world datasets show that the post‑hoc FSL preserves predictive performance while improving interpretability, outperforming other post‑hoc methods such as Integrated Gradients and SHAP.
By Jo\~ao Kenji Suwa, Jo\~ao Pedro Silveira e Silva, Bruno Iochins Grisci
The paper investigates how performance predictors can improve model routing for large language models (LLMs). It shows that a predictor only outperforms a model’s self‑confidence when the candidate model is suboptimal or the predictor adds significant capacity. The authors provide theoretical bounds, extend the analysis to two‑model cascades, and confirm their findings experimentally across 16 LLMs on four benchmarks, noting that the advantage diminishes as models are fine‑tuned.
By Guanhua Zhang, Moritz Hardt
The paper investigates how well common large‑language‑model (LLM) inference optimizations perform on Apple Silicon compared to server‑class NVIDIA GPUs. Four optimization families—KV‑cache pruning, speculative decoding, ported GPU kernels, and post‑training quantization—are evaluated on four Apple machines under a single‑request decode workload, with matched RTX 4090 comparisons where possible. Results show that KV‑cache pruning can boost Apple throughput up to 1.75×, while speculative decoding actually reduces throughput on Apple; CUDA kernel designs transfer only partially, and quantization gains vary by machine, indicating that speedups depend on the specific technique, runtime, hardware, and workload regime.
By Kyrylo Yemets, Andrii Yaroshevych, Victor Muryn, Ostap Khomenko, Pavlo Kryven, Maksym Kmet, Maksym Shamrai, Mariya Hirna