Artificial Intelligence · Cross-listed from stat.ML
Which Self-Improvements Should We Trust? Reliable Self-Improvement When Agents Reuse Their Benchmarks
Xiaojing Sun, Yuhan Zeng, Zihua She et al. (+1 more)
As recursive self-improvement (RSI) rapidly advances, reliable evaluation becomes critical for guiding adaptive search. RSI typically relies on finite evaluation resources, such as fixed
benchmarks, to determine which modifications are retained and what is proposed next. However, when these finite resources are repeatedly reused, new candidates are proposed based on feedback from the same evaluation set, so the search trajectory can adaptively overfit and empirical improvement may not reflect genuine population improvement on the underlying task distribution. Some existing methods account for multiple comparisons but assume that candidates are chosen independently of the evaluation set, and therefore do not control this adaptive dependence. To address this, we propose REUSE (Risk-controlled Evaluation Under Sequential
Evolution), a certified evaluation and promotion framework that allows a fixed evaluation set to support repeated adaptive decisions while providing statistical guarantees. For a user-specified error level $\alpha$, with probability at least $1-\alpha$, every promoted modification is a genuine population improvement on the underlying task distribution. REUSE achieves this by strictly limiting the evaluation feedback returned to the search process and accounting for possible promotion histories within the error budget. We develop detailed statistical theory for RSI evaluation in this setting, including simultaneous error control, valid lower bounds on cumulative improvement, and a characterization of the fundamental limits of adaptive evaluation reuse. In live self-improvement experiments, REUSE commits substantially fewer false promotions than evaluation frameworks from current RSI systems and error-controlled baselines, reducing the proportion of false promotions from up to 20.7% to 0%, while achieving final true population performance comparable to the best baselines.
Read the full abstract ▾
All authors Xiaojing Sun, Yuhan Zeng, Zihua She, Xiao Wang
Computation and Language
Scoring the Wrong Question: Readout Failures in Constrained-Option Evaluation
Jiaxuan Guo, Kejia Zhang, Shuo Xin et al. (+3 more)
Constrained-option scoring reads a model's probabilities for a fixed set of permitted answers, so it returns a score even when the model is about to write something else. We study a
prompt that quotes a multiple-choice item, ending in the item's own answer instruction, and asks for a forecast of whether a reader model given only a short note will answer it correctly. The model can begin answering the quoted item: on three Qwen3 checkpoints an answer letter is the most probable
token on nearly every passage, and the forecast ranks the reader's correctness indistinguishably from chance. Beyond prior work's argmax check and prefill repair, we contribute a label-free diagnostic of the declared options' support, their first-
token mass in context; a deletion test tracing the Qwen3 answer-letter start to the quoted instruction; and rendering and tokenisation checks for dropped separators and coinciding first
tokens. Prefilling an answer stem lifts the median option mass from below to above one half on all nine checkpoints scored with this
prompt and, with options and renormalisation unchanged, raises the Qwen3-averaged AUC from 0.4929 to 0.6152. lm-polygraph's default P(True)
estimator shows a related failure: it reads True where Qwen3 without thinking favours an answer letter (MMLU) or the
prompt's (A)/(B) label (TriviaQA), and its Qwen3-averaged AUROC is indistinguishable from chance on MMLU and below chance on TriviaQA. Scoring and renormalising the (A)/(B) labels after an answer stem raises it to 0.632 and 0.868, renormalising True against False in place reaches 0.660 and 0.860, and on TriviaQA both exceed all fourteen default single-answer library
estimators. The original forecast is renormalised too, yet stays indistinguishable from chance: option mass flags low support in both settings without labels, and only checking the intended target shows which score still ranks.
Read the full abstract ▾
All authors Jiaxuan Guo, Kejia Zhang, Shuo Xin, Jingxin Yang, Youran Sun, Haizhao Yang
Computer Vision
Can Protein-Derived Knowledge Improve Pathology Foundation Models?
Di Zhang, Zhangpeng Gong, Jiashuai Liu et al. (+10 more)
Molecularly guided pathology foundation models (PFMs) exploit transcriptomic or proteomic information to enrich whole-slide image (WSI) representations, yet effectively leveraging large standalone molecular corpora remains challenging. First, existing molecular foundation models encode
protein sequences or single-
cell states, not the patient-level bulk expression profiles paired with WSIs. Second, because cross-modal supervision is restricted to paired WSI-omics samples, knowledge from standalone molecular corpora reaches the pathology encoder only indirectly, creating a paired-support bottleneck. To address these challenges, we propose a three-stage framework that decouples proteomic knowledge acquisition from cross-modal transfer, yielding ProSlide, a slide-level hierarchical pathology foundation model. First, to close the modality gap, we pretrain a Proteomic Foundation Encoder (PFE) on 12,695 sample-level bulk
protein profiles using virtual profile generation and expression-space multi-view pretraining. Second, we pretrain ProSlide, a patch-region-slide encoder, to predict
protein expression from paired WSI-
protein samples. Third, to relax the paired-support bottleneck, we introduce Prot2Path, a cross-modal relational
distillation objective. For each paired sample, it aligns the similarity distributions of the WSI and its
protein profile over a shared, frozen bank of PFE-encoded paired and standalone profiles. We evaluate ProSlide on 12 downstream tasks across breast, lung, and renal cancers. Despite being pretrained with only 2,229 WSIs and 12,695 sample-level
protein profiles, ProSlide achieves the highest mean accuracy and AUC within each cancer group.
Read the full abstract ▾
All authors Di Zhang, Zhangpeng Gong, Jiashuai Liu, Zhi Zeng, Jiusong Ge, Chunze Yang, Xitong Ling, Kai Yi, Kai He, Weimiao Yu, Mireia Crispin-Ortuzar, Chen Li, Zeyu Gao
Robotics
DeltaWAM: Change-Centric Visual Foresight via Delta Tokens for an Efficient World-Action Model
Tianyun Jiang, Wenrui Bao, Bingxin Xu et al. (+2 more)
World-Action Models (WAMs) offer visual foresight for robotic manipulation, but pixel-space models repeatedly reconstruct entire future scenes, incurring high computational cost and spatio-temporal redundancy. In physical manipulation, consecutive frames often share most of their visual context; the changes between them are what an action policy needs to anticipate. We introduce DeltaWAM, a change-centric WAM that makes a compact delta
token the unit of future prediction. Each
token is a single vector encoding changes between consecutive dense DINO feature maps. DeltaWAM builds on DeltaWorld, a latent world model pretrained on large-scale
videos, to autoregressively predict one delta
token per future frame. A flow-matching action expert then conditions on the predicted transitions and current DINO features, which serve as spatial anchors, to generate action chunks. Trained for 256 GPU hours on two H100 GPUs, DeltaWAM has 0.725B parameters and achieves 92.8% average success on LIBERO. It also shows robust generalization under procedural perturbations on LIBERO-Pro. Inference takes 142.1 ms per action chunk with 3.86 GB peak
memory.
Read the full abstract ▾
All authors Tianyun Jiang, Wenrui Bao, Bingxin Xu, Yu Tian, Yuzhang Shang
Computer Vision
ABO-Med: Accelerated Bilevel Optimization for Few-Shot Medical Image Classification
Ruoxuan Shi, Sheng Yang, Zhengxing Su et al. (+2 more)
In recent years, bilevel optimization has been widely used in a variety of machine learning tasks. However, prior bilevel optimization
algorithms generally require the computation of second-order information, which limits their practical scalability. Only recently has a first-order paradigm for bilevel optimization been established, attaining near-optimal theoretical guarantees for solving bilevel optimization problems. In this paper, we propose ABO-Med, a scalable instantiation of this paradigm for few-shot learning, by incorporating it into the model-agnostic meta-learning (MAML) framework and tailoring it to medical image classification. We also introduce Medical Adaptive RandomAugment (MedRAug), a modality-aware augmentation strategy designed for medical images. Theoretically, ABO-Med establishes the optimality of MAML-type meta-learning approaches. Empirically, ABO-Med outperforms prior baselines on several public medical
datasets, with gains of 1.99% to 18.76%, while MedRAug further improves the average accuracy by 2.20% to 6.34%. Additional cross-domain experiments, augmentation ablation studies, backbone ablation studies, and training efficiency analysis further validate the effectiveness and efficiency of the proposed method.
Read the full abstract ▾
All authors Ruoxuan Shi, Sheng Yang, Zhengxing Su, Xiaoyang Hou, Yating Liu
Robotics
Multi-Terrain Mastery: A Comprehensive Controller for Bipedal Locomotion
Oluwami Dosunmu-Ogunbi and Aayushi Shrivastava
Advancing bipedal
robots to navigate diverse terrains remains a significant challenge in robotics. Traditional locomotion controllers excel on specific surfaces but struggle across varied environments, limiting their practical applications. Given the unpredictable nature of real-world environments, a single controller capable of handling multiple terrains is ideal, eliminating the need for multiple specialized controllers. We propose a multi-terrain controller to enhance the versatility and robustness of bipedal locomotion. Building on previous work with a stance ankle motor for stability on inclined and rough surfaces, this paper extends capabilities to steep wet uneven grassy slopes, and compliant terrains such as sand, gravel, rocks, and constrained terrains like staircases. To address the unique demands of these terrains, we introduce a new impact map that is essential for maintaining performance and robustness against unseen terrains. We also discuss in detail the control structure for real-time deployment on the
robot. We validate our controller on the 20 degree-of-freedom Cassie bipedal
robot.
Read the full abstract ▾
Robotics
Dynamic Manipulation with World-Action Models via Counterfactual Planning
Sunwoo Park, Wonbin Lee, Seonghyun Jin et al. (+3 more)
World-Action models (WAMs) trained on static demonstrations often fail to manipulate moving targets even when they possess the required manipulation skills. We attribute this failure to target-response collapse: as execution advances, the policy becomes increasingly biased toward the learned continuation of its ongoing behavior and less responsive to target relocation. To bridge the gap between what the model has learned and what it can generate from the current context, we formulate dynamic manipulation as counterfactual planning by decoupling the context used for plan generation from the physical state used for execution. Our framework, Dynamic Predictive Planning (DPP), first uses the WAM's predictive rollout to estimate when an interaction is expected to occur, and combines this timing estimate with observed target motion to predict the target's future interaction position. DPP then constructs a counterfactual observation that places this predicted target position in a familiar
robot context, allowing the model to invoke an existing manipulation skill rather than generate a recovery behavior from an unfamiliar
robot-target configuration. The resulting plan is connected to the
robot's actual state during execution. DPP enables real-time dynamic manipulation on a single consumer GPU without additional training on dynamic data. Experiments in simulation and on a real
robot demonstrate consistent improvements across diverse target motions, with simulation performance surpassing all evaluated baselines, including methods additionally trained on dynamic data. Project page: https://methoder00.github.io/DPP/
Read the full abstract ▾
All authors Sunwoo Park, Wonbin Lee, Seonghyun Jin, Youngmin Kim, Jangho Park, Jong Chul Ye
Machine Learning
Perturb-and-Solve: Efficient Learned-Operator Conditioning for Latent Diffusion Inverse Problems
Abduragim Shtanchaev, Arip Asadulaev, Luiza Labazanova et al. (+3 more)
Latent
diffusion models serve as powerful priors for solving inverse problems in image restoration, such as deblurring, inpainting, and super-resolution. Current methods have a trade-off between generality and efficiency. Solvers that are restricted to a fixed set of degradation operators are fast and efficient. Methods that support arbitrary degradation operators are slow and require gradients through the
diffusion network. To break this bottleneck, we introduce PASEO (Perturb-And-Solve for Efficient Operator conditioning), a method that uses a small (1M parameters) learned network to degrade
diffusion model predictions in latent space. PASEO supports learned degradation operators without back-propagating through the
diffusion network. We efficiently sample reconstructions from an approximate posterior by combining the
diffusion model's prediction with the observed image. We do this by adding noise and solving linear equations based on a local linear approximation of the learned network, without building or inverting large covariance
matrices. Across super-resolution, deblurring, and inpainting on FFHQ and COCO, PASEO achieves strong perceptual quality while running up to 9x faster and using up to 34% less peak
memory than the tested baselines, with the same or fewer model evaluations.
Read the full abstract ▾
All authors Abduragim Shtanchaev, Arip Asadulaev, Luiza Labazanova, Aidar Alimbayev, Karim Salta, Eric Moulines
Machine Learning
When Does Backpropagating Through Policy Memory Matter? Separating Representation Credit from Closed-Loop Credit
Xingjian Li, Jianhua Z. Huang and Junli Duan
When a policy with
memory is trained through a differentiable simulator, credit can reach what it stores along two routes: representation credit teaches the network that writes the
memory what to summarize, while closed-loop credit travels back through the physical states that earlier actions produced and that the
memory later stored. Stopping gradients at stored history, as truncated backpropagation and
Transformer-XL do, removes both routes at once. Keeping every forward computation identical and removing one route at a time, we trained
Transformer policies for quadrotor tracking to determine when each route matters. Credit through
memory improved learning only when velocity observations were noisy or hidden. When velocity was hidden, mildly decaying the gradient between consecutive physical states ($\gamma = 0.8$) eliminated the truncation cost of removing closed-loop credit while leaving representation credit essential, a separation that held in 14 of 16 new seeds. Two further systems bound this result: in a fixed-wing aircraft, representation credit could replace closed-loop credit on its own, leaving no cost to separate, and in a cart-pole, training with full state-edge credit was too unstable to compare the routes. In both the quadrotor and a fully observed vessel model, static gradient norms failed to predict which cut cost more, so
memory truncation choices are best guided by short training runs.
Read the full abstract ▾
Computer Vision
FloodDiffusion 2: Efficient and Path Controllable Streaming Motion Generation
Yiyi Cai, Yuhan Wu, Kunhang Li et al. (+6 more)
We present FloodDiffusion 2 (FD2), an efficient and controllable framework that builds upon FloodDiffusion (FD1), a state-of-the-art streaming motion generation model. While FD1 produces plausible motion, it suffers from low efficiency and limited controllability, as its
attention design requires repeated computation over the entire history, and it lacks precise trajectory control for real-world applications. To address these limitations and improve generation quality, FD2 introduces three advances. First, Partial
Attention makes finalized history representations independent of the active window, enabling KV-cached inference and shared-history packing for efficient training. Second, we establish a necessary-and-sufficient Bregman criterion for regression losses to preserve
diffusion's conditional-mean velocity field. This criterion guides an FK-induced quadratic loss that incorporates motion geometry without online FK evaluation. Third, FD2 introduces precise path conditioning to control the character's root trajectory while preserving natural body motion. Experiments show that FD2 reduces training computation by 4.6$\times$ and accelerates denoising by 11.29$\times$, reaching 2.303 ms per update on long sequences. Alongside these efficiency gains, FD2 improves motion quality over FD1 and achieves state-of-the-art FID scores among streaming methods, with 0.048 on SEED and 0.053 on HumanML3D.
Read the full abstract ▾
All authors Yiyi Cai, Yuhan Wu, Kunhang Li, Tu Fangyuan, Xiangyue Zhang, Qiaoge Li, Zhixiang Wang, Kaipeng Zhang, Haiyang Liu
Machine Learning
Downstream-Aware Context Selection for Online In-Context Reinforcement Learning
Ruihan A. Li, Shangtong Zhang and Rohan Chandra
In-context reinforcement learning (ICRL) enables large
language model
agents to adapt to new environments using their interaction history without updating model parameters. However, repeatedly conditioning on growing histories can lead to substantial
token cost. We propose a bounded-history context-management framework that predicts the task-dependent downstream effect of removing historical interactions to guide history selection and determine a decision-dependent context budget. Formally, our framework uses the full rolling history as a reference. The predictor evaluates removal effects, defines a deletion ordering, and applies a shared selection criterion to determine how much history to retain at each decision. We evaluate the method in closed-loop SUMO driving under held-out in-distribution, unseen-domain, and unseen-route settings, and in ScienceWorld under a continual ICRL protocol. Relative to a baseline using the full context, our method reduces total
token usage by 25.7%, 25.8%, and 23.2% across the three driving settings while maintaining comparable closed-loop driving performance. In ScienceWorld, it reduces total
token usage by 52.1% compared to full context and uses 30.2% and 37.8% fewer
tokens than the Recent and Similarity baselines, respectively, while maintaining performance.
Read the full abstract ▾
Robotics
Beyond Tasks: A Vision for Reproducing an Animal-like Behavioral Substrate Using Modern Robot Learning Techniques
Samiyuru Menik and Hemadri Jayalath
Recent advances in
robot learning have produced increasingly capable
embodied agents. Yet comparatively less
attention has been given to a more basic form of competence that animals exhibit continuously: the ability to remain situated, responsive, and behaviorally coherent as physical, environmental, and social demands change over time. We propose the ethological behavioral substrate as a conceptual lens for studying this form of competence in artificial
agents. Rather than treating these behaviors that animals exhibit as a set of isolated skills, we argue that their continual coordination under competing demands constitutes an important and underexplored target for modern
robot learning. We further propose robotic animal companions as a useful research setting for studying sustained interaction and adaptation in human-centered environments. Such systems provide an opportunity to investigate how social behavior,
memory, and continual learning develop over long periods of interaction. This perspective motivates further investigation of how such persistent behavioral competence may complement higher-level capabilities in
embodied agents.
Read the full abstract ▾
Machine Learning · Cross-listed from math.OC
Notes on Generative Modeling for Feedback Control and Planning
Karthik Elamvazhuthi
In these notes, we view control as a dynamically constrained sampling problem on the state-space of a control system. With this viewpoint, we extend methods from generative modeling, such as flow matching, normalizing flows and denoising
diffusions to control problems. Concepts such as controllability, optimal control and trajectory planning play an important role in guiding the extension and understanding well-posedeness of the corresponding
algorithms, with application to steering systems to target states or distributions and sampling from reachable sets. The notes are intended as an accessible introduction for readers with a background in control theory and robotics.
Read the full abstract ▾
Emerging Technologies
JFS-CryoMem: A Cryogenic Memory with Voltage-Controlled Superconducting Devices and Femtojoule-Scale Write/Read Energies
Md Rahatul Islam Udoy, Md Mazharul Islam, Juan P. Mendez et al. (+7 more)
Scalable cryogenic systems require
memory that combines nonvolatile storage, selective access, low thermal disturbance, and compatibility with superconducting electronics. We present a cryogenic
memory architecture that integrates a voltage-controlled Josephson junction field-effect transistor (JJFET) selector with a ferroelectric superconducting
quantum interference device (FeSQUID) storage element, hereafter termed JFS-CryoMem. The JJFET provides gate-controlled
cell selection, whereas the FeSQUID stores information in stable remanent-polarization states. JFS-CryoMem features separate read and write path mechanisms that support nondestructive readout and independent optimization of programming and sensing conditions. The architecture is evaluated using experimentally calibrated compact models that reproduce the measured electrical characteristics of both constituent devices. We demonstrate selective programming using a half-bias scheme, nonvolatile state retention, and distinguishable readout in a $4 \times 4$ array while accounting for the selected
cell and all unselected parallel branches. We then extend the analysis to arrays up to $16 \times 16$ and examine how array scaling alters current distribution, column-equivalent resistance, readout separation, required bitline current, and read energy. The results reveal the principal sensing and energy tradeoffs associated with larger arrays and identify the operating conditions required to preserve read distinguishability as the array grows. JFS-CryoMem provides a device-to-array framework for cryogenic
memory in
quantum, high-performance, and space-oriented computing systems.
Read the full abstract ▾
All authors Md Rahatul Islam Udoy, Md Mazharul Islam, Juan P. Mendez, Denis Mamaluy, Aaron J. Muhowski, Samuel Hawkins, William M. Martinez, Courtney Sovinec, Wei Pan, Ahmedullah Aziz
Human-Computer Interaction
PDFa11yMut: Measuring Mutation-Specific Detection in PDF Accessibility Checkers
Gauri Jain
Automated PDF accessibility checkers provide useful conformance evidence, but a clean report is not a complete accessibility oracle. PDFa11yMut measures mutation-specific checker behavior by applying paired structure-level transformations to reference-suite baselines, verifying intended deltas and non-target invariants, and recording hash-linked checker evidence. Across 30 conformance-oriented mutants, PAC and veraPDF each produced 30 and 30 direct target findings, respectively, while Acrobat produced 23 direct findings plus 3 prespecified consequence-proxy findings. The 39 semantic/assistive-representation mutants produced no automated target finding in the tested configurations, while Acrobat issued manual-review
prompts for a subset; Class B is interpreted descriptively rather than as a universal checker obligation. A separate convenience-selected exploratory AT sample observed representation differences in 8 of 9 pairs under one fixed NVDA/Acrobat/Windows procedure. The artifact contributes reusable operators, structural and purity oracles, paired baseline/mutant evidence, and reproducible analysis for a scoped mutation-testing study rather than a general checker-accuracy
benchmark.
Read the full abstract ▾
Computer Vision
FOCUS: Benchmarking Retinal Model Generalization from Foundation Vision Encoders to Multimodal LLMs
David Restrepo, Chenwei Wu, Luis Filipe Nakayama et al. (+4 more)
Progress in AI-based retinal image analysis has accelerated with the adoption of foundation models, yet evaluating their real-world reliability remains challenging. Performance reported on a single
dataset does not capture how models behave under
dataset shift, across clinical definitions, or for different patient subgroups. This limitation is particularly critical in medical imaging, where robustness, calibration, and
fairness are essential for safe deployment. We introduce FOCUS (Foundation Ophthalmic Cross-
Dataset Understanding under Shift), a cross-
dataset benchmark evaluating retinal fundus models across
vision-only encoder models (VM),
vision-
language dual-encoder models (VLM), and
multimodal large
language models (MLLM). FOCUS harmonizes binary diabetic retinopathy, referable diabetic retinopathy, and glaucomatous optic neuropathy tasks across ten public
datasets spanning diverse geographies, acquisition conditions, and label protocols. The
benchmark evaluates models through a unified analysis layer that measures ranking performance, calibration, subgroup disparities, and image-quality robustness. We present a large-scale evaluation covering 532 base configurations and 228 MLLM configurations adapted via LoRA fine-tuning. Results show no model family consistently dominates across tasks and
datasets: general VM encoders achieve the strongest average ranking performance, medical MLLMs are competitive but variable, and dual-encoder VLMs benefit substantially from lightweight adaptation. Fine-tuning improves in-domain performance but exhibits heterogeneous transfer to external
datasets, particularly in calibration. FOCUS provides a practical framework and public
benchmark to assess generalization, reliability, and robustness beyond single-
dataset leaderboards.
Read the full abstract ▾
All authors David Restrepo, Chenwei Wu, Luis Filipe Nakayama, Miguel L. Martins, Stergios Christodoulidis, Maria Vakalopoulou, Enzo Ferrante
Robotics
TimelyDAgger: Timing-Aware Expert Querying for VLA Policy Improvement
Zhixuan Zhao, Peiyan Li, Enhao Zhang et al. (+10 more)
DAgger improves
robot policies by aggregating expert supervision from states visited during policy execution.
Robot-gated DAgger automates expert queries, allowing the
robot to decide when to request expert takeover. While existing gates emphasize detecting the need for assistance, takeover timing also shapes the content of these demonstrations and their value for policy learning. We propose TimelyDAgger, combining Bridge-PCA monitoring of internal
vision-
language-action (VLA) features with Feedback-guided Threshold Adaptation based on expert behavior to improve takeover timing. We introduce an evaluation framework linking failure detection, takeover timing, and policy improvement, including Target-Aligned Supervision Ratio (TASR) for assessing supervision quality without retraining. Experiments show that takeover timing affects policy learning, with TimelyDAgger achieving competitive failure detection and higher post-training success in most evaluated settings under matched expert-action budgets. Project website: https://seen-e.github.io/TimelyDagger/.
Read the full abstract ▾
All authors Zhixuan Zhao, Peiyan Li, Enhao Zhang, Yueran Tao, Hao Wang, Chenghao Yue, Lei Lv, Wentao Zhao, Jiahao Chen, Xin Liu, Kangyao Huang, Yu Luo, Huaping Liu
Data Structures and Algorithms
On Diverse Solutions to Max-k-CSP and Bounded Degree k-SAT
Mayank Goswami and Adarsh Srinivasan
We study the problem of generating diverse solutions to Max-$k$-CSP and bounded-degree $k$-SAT, focusing on two distinct metrics: constraint diversity and variable diversity. For constraint diversity, the goal is to output $s \geq 2$ assignments to the CSP such that each assignment satisfies a $c$-fraction of the constraints, while maximizing the diversity among the $0$-$1$ indicator vectors of satisfied constraints in the Hamming metric. By reducing this to a multi-criteria optimization problem, we design $poly(n,s)$ time approximation
algorithms that return s assignments achieving provable bi-criteria guarantees on both the fraction of satisfied constraints and diversity of the constraint vectors. For variable diversity, the objective is to maximize the Hamming distance between the assignments, while also maximizing the number of constraints satisfied. For Max-$k$-CSP instances when the desired number of solutions is $s=2^{O(n)}$, we implicitly represent these diverse approximate solutions by constructing linear codes within the solution space. Finally, we investigate variable diversity for $k$-SAT in the Lovász Local Lemma regime. In this setting, we establish NP-hardness for the exact diversity problem (computing the diameter of the solution space) and provide a
polynomial-time approximation
algorithm to efficiently generate diverse satisfying assignments.
Read the full abstract ▾
Computation and Language
Where Do Test-Time Scaling and Training Fall Short in Individual Stance Prediction?
Yuyang Zhao, Xuan Liu, HaoYang Shang et al. (+1 more)
Test-time scaling and post-training have improved LLM performance in coding and mathematical
reasoning, but their effectiveness for individual stance prediction remains unclear. We study this question by predicting a person's stance in a new discussion from their history. We evaluate widely used test-time scaling strategies and post-training methods, such as supervised fine-tuning and reinforcement learning, and identify four failure modes across generation, selection, and learning: (1) incorrect consensus, where repeated samples agree on the wrong stance; (2) selection failure, where generation covers the observed stance but selection misses it; (3) response overfitting, where supervised fine-tuning improves imitation but harms prediction; and (4) early plateau, where reinforcement learning shows modest initial gains followed by limited further improvement. We expose these failures using STANCE-BENCH, which contains 2499 prediction tasks from 500 Hacker News users. Guided by this analysis, we explore a simple approach that combines direct scores for all candidate stances with explicit assessments of support from the individual's history. On the 781-task test set, this approach achieves 21.83 discussion-specific Macro F1 with Qwen3-8B, compared with 19.27 for direct scoring. Our results motivate evaluating candidate generation, final selection, and person-specific evidence use separately. Our data is available at https://github.com/stance-bench/Stance-Bench.
Read the full abstract ▾
All authors Yuyang Zhao, Xuan Liu, HaoYang Shang, Haojian Jin
Machine Learning · Cross-listed from math.OC
Sharp Critical Minimax Laws and No-Learning Thresholds in Continuous-Time Adaptive Control
Chen Jia
We study episodic continuous-time control with an unknown vector control gain, scalar state, quadratic action cost, and smooth convex terminal cost. In the scalar Gaussian experiment, let $\Delta(H)$ denote the minimax improvement over zero control and set $\delta=\sqrt2H^2-1$. We prove the critical law $$ \Delta(H)\asymp \delta^4\sqrt{\log(1/\delta)} \qquad (\delta\downarrow0), $$ with a matching lower and upper bound. The lower bound follows from a uniform deficit–energy inequality valid for fully adaptive controls with unbounded amplitudes, while a moving soft-threshold feedback attains the rate. For local parameters $\theta=N^{-1/4}h$, $|h|\le H$, we show that the normalized minimax regret over $N$ episodes is within $O(N^{-1/2})$ of a fixed-horizon Gaussian sequential control problem, without an additional dimension factor. The terminal task enters the limit only through $c_g=\operatorname{Var}(g(Z))$. The Gaussian problem exhibits an exact no-learning phase transition: $$ C_d^T(H)=TH^2/2 \iff H^4T\le d^2/2, $$ yielding the asymptotic task boundary $c_gH^4=d^2/2$.
Read the full abstract ▾
Software Engineering
What Does a Skill Actually Do? Estimands and Evaluation Validity for Tool and Skill Use in LLM Agents: A Critical Review
Shuyang Zhang
Reported improvements from tools and reusable skills in large
language model
agents refer to different comparisons. This critical narrative review examines what these evaluations estimate and which conclusions their designs support. The review checks the roles of one hundred cited papers and extracts focal evaluation designs in detail from thirty-five studies. Targeted readings of thirty-five additional published or accepted studies broaden coverage of tool creation,
memory, interactive
benchmarks, reliability, and risk. Designs are characterized by treatment contrast, target population, outcome, budget constraint, summary measure, and identification assumptions. Analytic decompositions and counterexamples show that pairing runs on the same task does not itself identify an invocation effect when evaluation conditions on a trigger within the treated run. Paired gain and regression counts describe discordance under the coupling protocol rather than the share of tasks whose expected outcomes worsen. Total effects of deploying a module answer a different question from efficiency under a common budget. Comparisons across studies distinguish curated skill provision from retriever replacement, task populations from triggered subsets, and preparation costs from marginal usage costs. Publication status and reading depth are recorded. The review provides a methodological synthesis and a reporting checklist to help align claims about tools and skills with the comparisons their evaluation designs support.
Read the full abstract ▾
Machine Learning
Convergence of Practical Muon
Haonan Wang, Yu Wu, Minghui Liwang et al. (+2 more)
Muon is emerging as a promising alternative to AdamW for large-scale neural network training, yet theoretical understanding of its practical implementation remains incomplete, as existing analyses often simplify or omit two key components: (i) practical Newton–Schulz iterations with empirically tuned
polynomial coefficients $(3.4445,-4.7750,2.0315)$; and (ii) decoupled weight decay for regularization. In this paper, we provide an optimization interpretation and establish convergence for practical
Muon, jointly accounting for both components. Specifically, we interpret practical
Muon as right-preconditioned optimization of the original loss with a dynamic weighted $\ell_2$ regularizer that vanishes as stationarity is approached, so that the optimization target remains the original objective. We then establish, to our best knowledge, the first convergence guarantee for practical
Muon in the
stochastic nonconvex setting, with an $\mathcal{O}(T^{-1/4})$ convergence rate in terms of the expected Frobenius norm of the gradient, improving the dimension dependence of the best known AdamW's convergence rate by a factor of $\sqrt{d}$, where $T$ is the iteration horizon and $d$ is the parameter dimension. Experiments further support the theoretical convergence results.
Read the full abstract ▾
All authors Haonan Wang, Yu Wu, Minghui Liwang, Xinlei Yi, Yiguang Hong
Computation and Language
Generalization Dynamics of LM Pre-training
Jiaxin Wen, Zhengxuan Wu, Dawn Song et al. (+1 more)
People typically assume that LMs stably mature from pattern-matching parrots to generalizable intelligence during pre-training. We build a toy eval suite and show this mental model is wrong: throughout pre-training, LMs frequently and suddenly hop between parrot-like and intelligence-like computations. We call this mode-hopping. Across our suite, LMs suddenly latch onto memorized or in-context patterns instead of in-context learning, use System 1 instead of System 2 thinking, pick up what sounds true instead of what is true, fail at multi-hop persona QA, out-of-context
reasoning, and emergent misalignment – then just as suddenly revert and generalize. Mode-hopping is not explained by standard optimization dynamics: it is locally stable and cannot be fixed by checkpoint averaging. We instead think of it as a capacity allocation problem: in a capacity-bounded model, generalizable
circuits must compete with the shallow ones learned early in training, and the data in each pre-training window may decide which
circuits win. Our suite provides a new efficient lens on generalization. We demonstrate two concrete applications: (i) select intermediate pre-training checkpoints that strongly generalize
reasoning and
alignment, better than the final pre- or mid-training checkpoints, and (ii) select pre-training data that controls and stabilizes generalization dynamics.
Read the full abstract ▾
All authors Jiaxin Wen, Zhengxuan Wu, Dawn Song, Lijie Chen
Artificial Intelligence
Not Too Hard, Not Too Easy: Learning from Intermediate States for LLM Structured Reasoning
Hongbo Chen, Guohua Lu, Ting Dang et al. (+1 more)
A common principle of effective learning is to practice material that is neither already mastered nor too difficult to permit progress. We ask how to apply this principle to structured
reasoning tasks such as Sudoku and maze solving. In these tasks, a model can repeatedly revise an incomplete or incorrect candidate solution until it satisfies the problem's constraints. The intermediate candidate solutions along this trajectory provide natural training examples: some are already solved, some cannot yet be repaired by the model, and others lie at its current frontier of achievable progress. We therefore investigate whether pretrained
language models can learn to revise such states and whether training on states at this frontier improves
reasoning more broadly. To achieve this, we couple a pretrained
language-model backbone with a recurrent updater that repeatedly revises an explicit solution state, using the same parameters at every update step. We further introduce Frontier-Oriented Curation Using Self-trajectories (FOCUS), which selects training states from trajectories generated by the current model. FOCUS measures how much the model improves each state within a fixed number of recurrent updates and prioritizes states from which it can make substantial progress. With Qwen3-1.7B, FOCUS achieves 64.4% exact solve accuracy on Sudoku-Extreme and 91.1% on Maze-Hard, with similar gains observed across five Qwen and Llama backbones spanning 1.7B to 8B parameters. We further observe zero-shot transfer in the adapted LLM to mathematical
reasoning and code execution, even when the recurrent updater is disabled and no downstream fine-tuning is performed.
Read the full abstract ▾
All authors Hongbo Chen, Guohua Lu, Ting Dang, Hong Jia
Computer Vision
DroneWAM: Efficient World Action Model for Drone Visual Navigation
Liang Yao, Fan Liu, Hongbo Lu et al. (+5 more)
World-action models give visual
navigation agents a way to anticipate how candidate actions will change future observations and to act from the predicted consequences. For drones, this capability must operate under tight accuracy and efficiency constraints. We present DroneWAM, an efficient world-action model for drone visual
navigation. DroneWAM adopts a JEPA-based architecture to model future states directly in representation space, avoiding the cost of explicit future image generation. A pretrained Resampler further compresses dense encoder features into fewer latent
tokens, reducing the computation repeated at each imagined step. We also introduce adaptive rollout, where a preference-trained Gate adaptively allocates prediction depth according to the current scene. To support learning under richer aerial motion, we construct DroneNav-6D, a simulated visual
navigation dataset with synchronized RGB observations, 6-DoF flight trajectories, control commands, and randomized wind disturbances. On DroneNav-6D, DroneWAM achieves the best trajectory accuracy among the compared methods. Adaptive rollout further reduces the average prediction depth from 8 to 4.58 while improving trajectory accuracy, demonstrating that predictive computation can be allocated more effectively across scenes. \href{https://github.com/1e12Leon/DroneWAM}{Codes and data} will be released.
Read the full abstract ▾
All authors Liang Yao, Fan Liu, Hongbo Lu, Wei Xu, Jianyu Jiang, Yijun Shen, Chuanyi Zhang, Pai Peng
Machine Learning
CFLoRA: Federated Fine-tuning of LLMs with Complementary Factors for Error-free Aggregation
Yanan Ma, Qiyuan Chen, Zihan Fang et al. (+2 more)
Federated low-rank adaptation (LoRA) enables collaborative fine-tuning of large
language models without centralizing private client data. Its factorized update, however, creates a structural mismatch in
federated averaging: averaging the two LoRA factors separately does not equal averaging their products. Existing exact methods resolve this issue mainly by freezing an entire factor or alternating factors across rounds, but none can update factors simultaneously without aggregation errors or expanding communication ranks. To address this fundamental problem, we present CFLoRA, a
federated LoRA scheme that partitions latent LoRA channels into two complementary sets in every communication round. By ensuring that columns and rows are complementary across factors, we eliminate bilinear terms in
matrix multiplications, making
federated aggregation exact. Crucially, our framework also supports clients with heterogeneous rank budgets. Convergence analysis validates CFLoRA achieves $\mathcal{O}(1/\sqrt{T})$ convergence rate of the original LoRA objective in homogeneous-rank cases. Extensive experiments with RoBERTa on the GLUE
benchmark and with LLaMA-3.2-3B-Instruct on commonsense
reasoning tasks demonstrate that CFLoRA achieves superior performance and training efficiency compared to state-of-the-art
federated LoRA baselines.
Read the full abstract ▾
All authors Yanan Ma, Qiyuan Chen, Zihan Fang, Xianhao Chen, Yuguang Fang
Artificial Intelligence
LiteEvo: Automated, Cost-Efficient Harness Evolution for Generalization to Unseen Tasks
Euntae Choi, Sumin Song and Sungjoo Yoo
An LLM
agent is defined by two things: the weights inside its model and the harness of components assembled around it. Harnesses are still handcrafted, and HarnessX, which evolves them automatically, starts each
benchmark from a handcrafted harness, reports gains on the tasks it evolved on, and budgets 100 to 175 million meta-
agent tokens per
benchmark. We propose LiteEvo, a lightweight harness-
evolution algorithm whose tool-free meta-
agents mine
agent trajectories for reusable components, curate them into a versioned library, and compose each round's harness from it, starting every
benchmark from the same neutral harness and never naming the
benchmark. Evolving on the graded tasks of five agentic
benchmarks with a frozen Qwen3.5-9B, LiteEvo lifts pass@2 by 10.5 to 67.7pp and reaches comparable or higher pass@2 than a reproduction of HarnessX (71.0 against 67.3 on average) at 13.0 lower mean API cost. Harnesses evolved on train tasks keep their gains on unseen test tasks of four
benchmarks, and LiteEvo also lifts Claude Code with Sonnet 4.6 by 1.2 to 71.4pp.
Read the full abstract ▾
Robotics
Beyond State-as-Action: Exploiting Command-State Discrepancy for Robot Imitation Learning
Peiyan Li, Yueran Tao, Enhao Zhang et al. (+10 more)
Constructing action targets from measured
robot motion is an established approach in imitation learning. Under interaction constraints, however, command-state discrepancy may reflect control demands that motion alone does not capture. We investigate when this information matters and how to exploit it. Across three real-
robot tasks, task and phase analyses reveal larger supervision gaps under constrained interaction, while selective command retention provides evidence of locally useful command information. Building on these findings, we propose Command-State Discrepancy Weighting (CSDW), which accounts for
robot response times and combines subsequent progress, persistent unmet demand, and demand changes into continuous weights for command supervision. The method requires no task-phase annotations or changes to policy architecture or inference. CSDW improves over uniform command supervision on constrained tasks, while methods perform similarly in the less constrained task. Project page: https://seen-e.github.io/CSDW/.
Read the full abstract ▾
All authors Peiyan Li, Yueran Tao, Enhao Zhang, Zhixuan Zhao, Chenghao Yue, Hao Wang, Lei Lv, Wentao Zhao, Jiahao Chen, Xin Liu, Kangyao Huang, Yu Luo, Huaping Liu
Machine Learning
Beyond the Training Horizon: Mechanisms and Limits of Length Generalization in Looped Transformers
Jia Liang, Xi Jin and Liangming Pan
Looped
Transformers can generalize to
reasoning chains longer than those encountered during training, but the computations enabling this behavior and limiting its extent remain unclear. We mechanistically compare two looped-
Transformer configurations, which we call the Matched-Recurrence Looped
Transformer (MR-Loop) and Decoupled-Recurrence Looped
Transformer (DR-Loop), reflecting their respective recurrence-training schemes. We evaluate
polynomial iteration, finite-state composition, and knowledge-graph traversal using detailed mechanistic analysis.
Attention analysis, intermediate-state decoding, and causal interventions reveal distinct mechanisms learned under final-answer supervision. MR-Loop updates an intermediate state at a fixed readout while advancing relation selection through adjacent-
token interactions and a transferable progress cue. DR-Loop instead propagates intermediate states across relation positions, forming an advancing computational frontier. However, both mechanisms become unreliable at greater depths: MR-Loop exhibits degradation of its readout state and progress cues, while DR-Loop exhibits declining reliability of state propagation. Limited self-correction allows local errors to persist and compound. Across both models, we uncover a common representational principle: recurrent states encode not only task-relevant content but also its computational status, whether that content remains in a form that can support subsequent computation. Transferable live-consumed and fresh-aged residual directions causally control whether represented information can participate in subsequent computation, including beyond the training horizon. We further show that length generalization need not rely on faithful step-by-step
reasoning, as Looped
Transformers can exploit task structure without explicitly representing every intermediate state.
Read the full abstract ▾
Computation and Language
CAME: Company-Aware Evidence-Memory Experts for Interpretable Quarter-Ahead Revenue Forecasting
Ya-Wen Wu, Meng-Fen Chiang, Kuang-Da Wang et al. (+1 more)
Quarter-ahead revenue
forecasting requires company-scale numerical accuracy, strict temporal validity, and company-specific interpretation of narrative disclosures. LLMs can distill textual evidence but can produce scale-misaligned forecasts, whereas history-based anchors are stable but miss forecast-time signals such as product transitions, supply constraints, and management guidance. We introduce CAME (Company-Aware Evidence-
Memory Experts), a residual-
forecasting framework that refines a no-leakage statistical anchor when current semantic evidence and prior error patterns justify an adjustment. On a development-inclusive rolling backtest of 336 company-quarters from 12 large public technology and platform firms, CAME achieves the lowest aggregate point-estimate error among the reported methods, with statistically supported macro-sMAPE gains over the matched Statistical Anchor, and outperforms History + Guidance on all six aggregate metrics. CAME also links adjustments to source-linked evidence cards and guarded
memory traces, supporting forecast inspection, provenance, and failure localization.
Read the full abstract ▾
All authors Ya-Wen Wu, Meng-Fen Chiang, Kuang-Da Wang, Wen-Chih Peng