Peer Revenue Past citations are no guarantee of future returns

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science

Sunday 4 October

Machine Learning

TSAE: Structured Sparse Autoencoders for Interpreting Time-Series Forecasting Models

Baoxi Liu and Yi Xie

Time-series forecasting informs critical decisions in energy dispatch, industrial operations, and environmental monitoring; understanding the patterns models rely on is essential for assessing reliability and identifying failures. Input attribution identifies important variables and time segments but offers limited insight into internal features, while standard sparse autoencoder (SAE) objectives do not directly constrain cross-variable structure or temporal continuity. We introduce TSAE, a structured sparse autoencoder for forecasting representations that decomposes hidden states into individually inspectable features. TSAE organizes cross-variable structure through shared and variable-routed private dictionaries, separates feature detection from magnitude estimation with gated encoding, and constrains neighboring sparse-code changes according to raw-segment similarity. These mechanisms support analysis of variable context, activation strength, and temporal evolution. Forecast-consistency fine-tuning further improves preservation of the frozen forecaster's outputs. The accompanying TSEVAL protocol separately audits fidelity, feature coherence, and physical calibration to ground feature interpretation. In three-seed experiments with frozen PatchTST on ETTh1, ETTh2, and ETTm1, TSAE achieves the lowest hidden-state reconstruction error, normalized forecast-reconstruction error (NFRE), and feature transition rate among five SAEs at comparable per-token activity. NFRE decreases by 4.3-26.4% relative to the next-best mean. Dataset-dependent tradeoffs in selectivity, physical correlation, and calibration show that fidelity and temporal-stability gains require independent semantic validation to support feature interpretation.
Read the full abstract

Robotics

Nudge Before You Push: Physics-Aware Navigation via Tactile Probing

Xianyao Li, Fang Xu, Ruitong Tian et al. (+4 more)

Visually identical containers can conceal loads that require different handling decisions. We present TANav, which uses a brief nudge to measure push resistance for navigation under a site-defined handling boundary. TacPhys reads the force sequence, with optional RGB-D and kinematics, into a mass estimate for push authorization. A repeated-patrol planner weighs probe and route costs, requests a second contact when useful, and reuses observations across visits. In simulation, TacPhys approaches a resistance-only Bayes reference and reduces missed pushes from 28.7% to 5.5% relative to peak-force thresholding at comparable low-risk operating points. In repeated-patrol simulation, TANav recovers 90% of the oracle's path saving, more than halves human interventions relative to always-detour, and reduces boundary violations from 4.3% to 2.9% relative to RGB-D-only probing. On a quadruped manipulator with a Hall-array fingertip, offline zero-shot MAE is 0.28-1.07 kg on containers up to 2.82 kg. Force-rise calibration at 3 kg gives 93.5% pooled offline accuracy (86.4% on non-cube episodes); a separate raw-peak rule gives 15 of 20 correct online decisions on unseen boxes.
Read the full abstract

All authors Xianyao Li, Fang Xu, Ruitong Tian, Bowen Sun, Xiao Hu, Yang Ye, Jing Du

Multiagent Systems

Increasing Resilience of Smart Home Agents

Christopher Terrazas and Eduardo Cotilla-Sanchez

Smart homes and smart devices are becoming more prevalent across millions of homes around the world. With the rise of AI, the smart home industry is quickly increasing its integration to manage common smart home tasks. However, existing work in large language models (LLMs) as agents within smart homes have shown minimal resilience due to limited environment scenarios or poor performance in complex tasks. We explore several strategies for LLMs as agents within the popular open-source software (OSS) smart home automation framework HomeAssistant to increase overall smart home resilience. Our approach combines traditional supervised learning techniques and optimized prompting as the core learning process. We use a diverse set of LLMs covering different levels of reasoning and costs in our optimization pipeline and evaluate their performance on a subset of the hardest tasks in a smart home benchmark. We include ReAct and Reflexion agentic paradigms and reveal how both provide marginal return on investment compared to fine-tuned LLMs for multi-device control within HomeAssistant but show promise in resilience tasks such as failure response.
Read the full abstract

Computer Vision

TRACE: Time-Adaptive Residual Attention Control with Content-Style Decomposition for Training-Free Diffusion Style Transfer

Duc Khoan Le, Kim Ngoc Tran, Minh Nhat Le et al. (+5 more)

Reference-guided style transfer aims to preserve the semantic structure of a content image while transferring the visual appearance of a style reference. Recent diffusion-based methods achieve impressive stylization quality by exploiting strong pretrained generative priors. However, training-free approaches still face a difficult trade-off among style fidelity, content preservation, and content leakage. Direct style injection may unintentionally transfer semantic content from the style image, while fixed guidance schedules often ignore the time- and state-dependent nature of diffusion sampling. To address these limitations, we propose TRACE, a training-free diffusion style transfer framework with Time-adaptive Residual Attention Control and Content-Style Decomposition. TRACE first performs offline CLIP-based subspace analysis to separate content and style directions from paired data. During inference, it removes content-related components from the style reference and style-related components from the content reference to reduce leakage. It then injects style information through residual cross-attention and applies uncertainty-aware guidance to adapt the guidance signal at each denoising step. Experiments show that TRACE achieves a favorable trade-off between stylization and preservation. Compared with optimal-control-based baselines, TRACE substantially improves style fidelity (+17.28 CSD and +34.10 SRA). While, compared with stylization methods, it better preserves content structure (+12.80 DINO, +5.52 CLIP-I, and -8.19 LPIPS) and reduces directional semantic leakage by 29.5% in DCL. Our code is publicly available at https://github.com/pixelchemy-research/TRACE.
Read the full abstract

All authors Duc Khoan Le, Kim Ngoc Tran, Minh Nhat Le, Thanh An Tran, Viet Toan Nguyen, Khanh An Lay, Tran Thai Son, Hoang Pham Minh

Software Engineering

Complex Agents, Shallow Tests: Demystifying and Enhancing Test Adequacy of Agent Harness in the Wild

Yifan Xiong, Jingyi Ge, Zhenpeng Chen et al. (+1 more)

LLM-based agentic systems are emerging as a new software paradigm. Modern agents are typically composed of backbone LLMs and a surrounding harness that serves as the operational software infrastructure for agent execution. As agent harnesses grow increasingly complex, agents suffer from diverse harness implementation bugs, raising substantial reliability concerns. In this work, we conduct the first empirical study to systematically investigate the test adequacy of harness in real-world agentic systems. Our analysis reveals that agent harness remains substantially undertested. In particular, LLM-dependent harness (LDH) code, despite its critical role in processing LLM outputs and governing agent behavior, receives limited testing attention, with less than half of its lines and branches covered by existing tests. Motivated by these findings, we further propose HarnessTester, the first harness-oriented test generation technique that incorporates explicit agent-harness contract support to construct contract-faithful test setups and extensively exercise LDH code. Our evaluation shows that HarnessTester substantially outperforms state-of-the-art general-purpose test generation techniques in achieving 75.95%/84.76% larger line/branch coverage gains and 69.89% larger mutation-score gains. Furthermore, HarnessTester detects 122 real-world harness bugs in widely-used agentic systems (e.g., OpenClaw), among which, 88 bugs are previously-unknown bugs and 69 bugs have been confirmed by agent developers. These results highlight the practical effectiveness of HarnessTester in improving test adequacy and assuring the reliability of real-world agentic systems.
Read the full abstract

All authors Yifan Xiong, Jingyi Ge, Zhenpeng Chen, Yiling Lou

Computer Vision

PWM: Personalized World Models with Online Reinforcement Learning

Zhexin Lou, Guancheng Lu, Zeyu Zhang et al. (+3 more)

Pretrained world models can generate diverse environments, yet users often want to explore a particular scene specified by their own video. This requires learning the scene's visual identity while retaining the quality of action-conditioned generation. We introduce Personalized World Models (PWM), a framework for customizing interactive world models from short scene videos through online reinforcement learning. In PWM, the support trajectory and its associated controls provide reward feedback on continuations sampled from the current policy. In the GRPO instantiation, group-relative optimization updates a compact LoRA adapter using a unified reward for scene appearance, visual continuity, and motion, while base-policy anchoring regularizes changes to the pretrained generation prior of a frozen Yume-5B backbone. The same adaptation procedure is applied across real and rendered environments. We also instantiate PWM with DiffusionNFT as an alternative reward-guided optimization method for learning the scene-specific adapter. We also introduce PWM-Bench, comprising 150 customization tasks across Indoor, Outdoor, and Gaming, with paired evaluation on held-out continuations. The GRPO and DiffusionNFT instantiations of PWM improve customization over native Yume in 71.3% and 65.3% of the evaluated scenes, respectively, with positive mean gains across all three domains. For the GRPO instantiation, matched SFT comparisons further demonstrate higher mean customization gains and better mean image-quality scores in every domain, while retaining frame-level visual quality close to the pretrained model.
Read the full abstract

All authors Zhexin Lou, Guancheng Lu, Zeyu Zhang, Yi Zhang, Yang Zhao, Hao Tang

Machine Learning

Residual Visual Credit Optimization: Conserved Evidence Routing for Multimodal Reinforcement Learning

Lin Qiu, Yao Liu, Diyi Hu et al. (+6 more)

Reinforcement learning with verifiable rewards scales multimodal reasoning, but an outcome reward says how much a trajectory is worth, not how that value should be spread over the decisions that produced it. We introduce Residual Visual Credit Optimization (RVCO), which treats token credit as a conserved routing problem. A controlled visual intervention yields a per-token evidence response; robust within-trajectory coordinates remove incidental scale; and a budgeted entropic router distributes a fixed amount of sequence utility according to perceptual dependence. A residual support path guarantees positive credit at every valid position, and an analytic correction restores the prescribed credit mass exactly. The resulting field is selective, bounded, full-support, and invariant to response-local score shifts, and recovers hard token selection as a limiting case. Across four model families and seven reasoning benchmarks, RVCO improves accuracy over strong RLVR baselines while maintaining late-stage optimization stability, corruption robustness, and competitive training cost. Rewards, rollouts, and the group-relative advantage estimator are unchanged; only the geometry of token-level credit differs.
Read the full abstract

All authors Lin Qiu, Yao Liu, Diyi Hu, Hanqing Zeng, Onur Gungor, Chujie Chen, Jiayi Liu, Jianyu Wang, XueLin Zheng

Computational Complexity

W[1]-Hardness of Upper Clique Transversal

J. Pascal Gollin, Tesshu Hanaka, Ekkehard Köhler et al. (+2 more)

A clique transversal of a graph is a set of vertices intersecting every maximal clique. We prove that deciding whether a graph has an inclusion-wise minimal clique transversal of size at least $k$ is W[1]-hard when parameterized by $k$.
Read the full abstract

All authors J. Pascal Gollin, Tesshu Hanaka, Ekkehard Köhler, Martin Milanič, Yushi Uno

Robotics

PreAct-Nav: Agentic Reasoning Before Action for Urban Navigation

Jing Xie, Shouwei Ruan, Yubin Wang et al. (+4 more)

Urban navigation requires embodied agents to pursue long-horizon goals through local decisions based on egocentric observations. However, existing agentic navigation methods often struggle to translate distant goals into coherent local decisions in large-scale physical environments. Their reliance on linguistic reasoning over transient observations or limited history constrains anticipation of the consequences of actions and future conditions, despite the importance of such foresight for navigating long and complex urban routes. To bridge this gap, we propose PreAct-Nav, an agentic navigation framework that equips frozen policies with anticipatory reasoning for robust urban navigation. Our central idea is to anchor local decisions in persistent medium-horizon subgoals, assess the consequences of predicted actions before execution, and continually update the reasoning context using actual outcomes. At its core, a navigation memory module maintains the active subgoal and relevant experience across decisions, translating distant goals into actionable intermediate objectives. We further introduce a predictive world sandbox that uses an action-conditioned world model (AC-WM) to forecast world dynamics conditioned on candidate movements. A vision-language model (VLM) reasoner interprets these predictions under the current subgoal to retain or revise actions. After execution, real observations are used to assess outcomes, correct inconsistent assumptions, and update memory to continue or reformulate the subgoal. Extensive evaluations demonstrate that the proposed PreAct-Nav improves action selection through memory updates and visual prediction, with more pronounced gains on longer routes and routes with more turns.
Read the full abstract

All authors Jing Xie, Shouwei Ruan, Yubin Wang, Yuxiang Zhang, Junwei Yang, Songchang Jin, Dianxi Shi

Artificial Intelligence

Are We Measuring Scientific Intelligence? Rethinking the Evaluation of AI Scientists

Kate Zhang and Yuante Li

AI agents can now carry out data-driven scientific analyses end to end, and benchmarks assess them by giving an agent a question and a dataset and scoring its final answer against a fixed key. These benchmarks assume that a correct answer was derived from the supplied data, a property we call evidence grounding. However, an agent can also reach the key from prior knowledge or by ruling out the other options, and a score based on a single run cannot tell these cases apart. We show how to test this assumption and find that it often fails. For each question, we build versions of its data files in which the evidence for the answer is left intact, withdrawn or reversed, check each edit with a pre-registered reference statistic, and run the same agent on every version. We then measure evidence-grounded accuracy, which credits a correct answer only if the agent also responds when the evidence is withdrawn and follows it when it is reversed. We evaluate three agent scaffolds and five models on 18 single-cell questions from BAISBench and four synthetic problems from GeneBench-Pro. On the single-cell questions, the Claude agents are 95% accurate and answer 83% correctly without any data, but their evidence-grounded accuracy is only 41%. Hiding gene names raises the share of runs that follow reversed evidence from 58% to 93% on ten gene tasks, suggesting that prior knowledge competes with the supplied data. The benchmark score and LLM judges can also reward answers that ignore the changed evidence. Measuring scientific intelligence rather than recall therefore requires checking whether answers follow the evidence and whether scores reward them for it.
Read the full abstract

Artificial Intelligence

Monitorability Disposition in Large Reasoning Models

Shahriar Golchin and Marc Wetter

Monitoring the chain-of-thought (CoT) of large reasoning models (LRMs) is a common way to detect misbehavior in real-world practice. However, current monitoring is passive: a separate model inspects the session only after execution. This means harm may already have occurred before it is caught. An active alternative is to have the model self-report its misbehavior as it happens. Whether models are willing to do this, however, is unknown. We introduce "monitorability disposition": a model's willingness to make itself monitorable and stay monitored throughout inference when warranted. We measure it as the fraction of warranted cases in which a model self-reports its own misbehavior via tool calls to available monitoring channels. We evaluate four LRMs on three misbehaviors (sycophancy, reward hacking, and bias) while varying the available monitors (AI and human) and the pressure to use the monitoring tools. We find that when tool use is optional, models self-report in only about 16% of warranted cases on average. Increasing tool-use pressure does not improve reporting where it matters: high-severity misbehavior is never self-reported. Models also systematically select the monitor they perceive as least strict. Overall, we identify monitorability disposition as a new contributing factor to model monitorability: when sufficiently strong, it keeps models seeking monitorability throughout inference.
Read the full abstract

Robotics

$R^2$-WAM: Repair-and-Reject Post-Training for World Action Models

Ruiyan Xu, Haisheng Su, Sixu Lin et al. (+4 more)

World Action Models (WAMs) emerge as a promising foundation for policy refinement by predicting the consequences of sampled actions. However, visually plausible predictions can mislead policy refinement if they fail to reflect the input actions. To address this mismatch, we introduce $R^2$-WAM, a two-stage repair-and-reject post-training framework that first improves the consistency of predicted futures with input actions, then uses these futures to select inferior action samples for negative fine-tuning. The repair stage grounds imagination in observed robot behavior through a kinematic alignment score that measures agreement between predicted and demonstrated motion, enabling the predicted video to faithfully reflect its input actions. Using the repaired video model, the rejection stage compares imagined outcomes of sampled and demonstrated actions, selectively applying negative fine-tuning to samples whose predicted task progress falls below the demonstrated reference by a prescribed margin. Together, the two stages extend video prediction from representation learning to consequence-based policy refinement without additional environment interaction or changes to the inference procedure. $R^2$-WAM achieves 93.8% average success on RoboTwin 2.0 across clean and randomized settings. On the long-horizon real-world Fold Shirt task, it achieves 87.5% average success, compared with 0% for Fast-WAM. Our project page is available at https://r2-wam.github.io/.
Read the full abstract

All authors Ruiyan Xu, Haisheng Su, Sixu Lin, Zhaokun Yue, Chengming Hu, Xin Jin, Guiliang Liu

Cryptography and Security

Static Bootstrap Placement for Encrypted Language Model Decoding

Halil Ibrahim Kanpak and Didem Unat

Language models increasingly serve prompts that carry private data, and secure inference under homomorphic encryption lets a client outsource the computation without revealing the prompt. Existing secure inference systems run a forward pass without consuming a token under encryption, and generating text with them requires a client round trip at every generated token. Keeping the loop on the server instead requires selecting and consuming a token under encryption, and placing bootstraps for a loop body that grows with the context. We build AR-HE, which runs the whole loop on the server, selects each token under encryption, retrieves its embedding, and writes it back into the encrypted state. The client sends one prompt and remains offline until the output. One rule places every bootstrap in the run, without search, so the bootstrap cost of a token is a formula in the context length that is known before the run starts. The schedule skips work whose result cannot reach the output, packs bootstraps that share an operand, and keeps the keys and values of past positions in an encrypted cache. With every optimization applied, generating a GPT-2 small token costs 544 seconds on one NVIDIA H100, down from 4715 seconds without optimization. The prompt step before it costs 4630 seconds. The cache alone takes a generated step from 11751 bootstraps to 1072. The formula predicts every step we measured, including steps of a model it was not derived from.
Read the full abstract

Artificial Intelligence

VideoResearchAgent: Grounded Task Synthesis and Sim-to-Real RL for Open-Web Video Research

Yuhang Zhou, Fei Li, Yuxi Wu et al. (+2 more)

Existing deep research agents are designed primarily for text- and image-based web sources, while video reasoning systems typically assume that relevant videos are provided in advance. We study open-web video research, where an agent must autonomously discover relevant videos, navigate their temporal content, and ground answers in visual evidence. Training such agents at scale is challenging as live video interaction is slow and unreliable, whereas fixed local simulation can induce retrieval-specific shortcuts that fail to transfer to the open web. We introduce VideoResearchAgent, a scalable training framework to address these challenges. First, we introduce controllable task synthesis pipeline to synthesize multi-hop research tasks from timestamped visual evidence while filtering text-only shortcuts. Second, we build a field-aligned local video simulator that preserves deployment-facing search and watch interactions while accelerating video search by a factor of 34.5-64.6. Third, we introduce Retrieval-Domain-Randomized GRPO (RDR-GRPO), which diversifies candidate rankings, distractors, metadata, and result structure during training to reduce overfitting to simulated retrieval. On Video-BrowseComp, the VideoResearchAgent trained using Qwen3.5-4B achieves 40.48% accuracy, comparable to Gemini-3-Flash-Preview, while reducing cumulative API-token consumption by 74.9% relative to the untrained model. Together, these results establish an accurate and efficient training recipe for open-web video research.
Read the full abstract

All authors Yuhang Zhou, Fei Li, Yuxi Wu, Bin Zhu, Jingjing Chen

Robotics

GJK-CBF: Control Barrier Functions for Convex Rigid Body Collision Avoidance on SE(3)

Yi-Hsuan Chen, Shuo Liu, Wei Xiao et al. (+2 more)

Collision avoidance among convex bodies is a fundamental problem in robotics. Control Barrier Functions (CBFs) provide a practical framework for real-time safety filtering due to their computational efficiency. For general convex bodies, exact separation measures, such as distance or scaling factor, are typically computed through optimization. Existing CBF formulations often obtain the required gradient via differentiable optimization (diffOpt), adding computational overhead. In contrast, we leverage the Gilbert-Johnson-Keerthi (GJK) algorithm to obtain the current witness pair—the pair of points realizing the minimum distance or penetration depth—and formulate a CBF, termed GJK-CBF, whose gradient is constructed directly from the relative rigid-body motion of the witness pair, without resorting to diffOpt. This formulation applies to both 2D and 3D environments across a broad class of convex body pairs, provided that at least one in each one-to-one interaction is strictly convex. The proposed GJK-CBF is validated in various scenarios, including multi-robot position swapping in both 2D and 3D, navigation through a vertical slit in 3D, and its applicability to manipulators. The results demonstrate collision-free motion across all scenarios while reducing the conservativeness introduced by geometric approximations, particularly in narrow environments.
Read the full abstract

All authors Yi-Hsuan Chen, Shuo Liu, Wei Xiao, Michael Otte, Calin Belta

Machine Learning

Why Subliminal Learning Needs So Much Data: A Noisy Inverse View through Steering Vector Recovery

Luoyu Chen, Xiaoyu Ding, Weiqi Wang et al. (+4 more)

Subliminal learning lets a student inherit a teacher's behavioral trait from semantically unrelated data, yet published demonstrations typically require tens of thousands of carrier examples. We ask where this data requirement comes from. Our testbed is subliminal steering: the teacher trait is a known residual-stream vector $\Delta_T$, so transfer can be measured directly as parameter recovery. On identical carrier prefixes, we compare token-level (hard) NLL supervision with full-distribution (soft) KL supervision. At initialization the two objectives give nearly collinear gradients, and both align poorly with $\Delta_T$. Under iterative optimization, however, they diverge: soft supervision recovers $\Delta_T$ almost exactly from a few hundred carriers, while hard supervision stays well below it even with tens of thousands. We explain this gap by casting steering-vector distillation as a noisy linear inverse problem. Locally, the carrier task maps the trait through its Fisher matrix $F$, so gradients point toward $F\Delta_T$ rather than $\Delta_T$. Gradient descent then acts as a progressively less-damped inverse of $F$. With soft targets, this inverse restores low-curvature directions. With hard labels, it also amplifies the sampling noise in those same directions. The result is an optimal inversion depth that grows with the number of independent carriers. Experiments on Qwen2.5-7B and Gemma-2-9B confirm four predictions: the Fisher distortion of the initial gradient, recovery ordered from steep to flat directions, an optimal depth that shifts with data scale, and the finding that resampling completions from a fixed prompt pool works as well as adding new prompts. In this setting, large carrier datasets are needed less to reveal the trait than to suppress label noise amplified by Fisher inversion. Code is available at \url{https://github.com/luoyuchenmlcv/subliminal-data}.
Read the full abstract

All authors Luoyu Chen, Xiaoyu Ding, Weiqi Wang, Chenhan Zhang, Zhiyi Tian, Jianhuan Huang, Shui Yu

Computation and Language

Scaling Verifiable Environments for Long-horizon Work Agents

Jiazheng Zhang, Long Ma, Yunxian Yang et al. (+23 more)

Work agents operate over digital artifacts to execute professional knowledge-intensive work, requiring training environments that support long-horizon interaction and trustworthy verification. However, hand-crafted environments incur prohibitive engineering overhead that prevents environment scaling, whereas synthesis methods sacrifice workspace complexity, realism, or grounded verifiability. To bridge this gap, we introduce WorkForge, a scalable synthesis framework for constructing verifiable work-agent environments from real-world resources. Starting from expert workflows, WorkForge first identifies the resources, decisions, and deliverables required by each workflow. It then retrieves relevant real-world files and organizes them into a workspace. WorkForge inspects the workspace to extract concrete, checkable facts about its content. These factual anchors fix which task types the workspace can support and how their outcomes can be verified. Therefore, WorkForge derives each task's instructions, solution plan, and complementary programmatic and semantic verifiers directly from these factual anchors, keeping verification traceable to observable workspace evidence. Furthermore, we construct 16.7K verifiable environments across 40 professional domains, with workspaces collectively covering 60 file types. Post-training Qwen3.5-35B-A3B-Base improves GDPVal from 45.5 to 73.6 and APEX Score from 5.0 to 21.3, while enabling Qwen3.5-27B to achieve highly competitive performance and outperform strong competitors. Our analyses confirm the efficacy of the proposed method and reveal consistent scaling behaviors across both data volume and interaction horizons.
Read the full abstract

All authors Jiazheng Zhang, Long Ma, Yunxian Yang, Zhiheng Xi, Zhikai Lei, Yajie Yang, Chenyang Liao, Enyu Zhou, Yang Nan, Yuchen Tian, Senjie Jin, Yibo Wang, Wei He, Boyang Liu, Jixuan Huang, Xin Guo, Shutong Jiang, Zhezheng Hao, Xinbing Liang, Zhihao Zhang, Changzhi Zhou, Wiggin Zhou, Tao Gui, Qi Zhang, Xuanjing Huang, Clarenceai

Machine Learning

ScopeSAE: Model-Scope Feature Discovery with Interpretable Layer Selection

Qingwen Zeng, Zehao Fu, Shuyu Meng et al. (+5 more)

Sparse autoencoders (SAEs) are a central tool in mechanistic interpretability. However, existing SAEs are primarily trained per layer. The modeling subspace is therefore fixed by layer identity, independent of which token-layer states actually drive each prediction. We argue that this constraint contributes to several limitations observed in layer-wise SAEs, including low feature utilization, high dictionary redundancy, and features that lack direct behavioral grounding. In this paper, we propose ScopeSAE, which selects the modeling subspace per token by attributing each prediction to its most influential token-layer state via normalized gradient-based attribution, and learns features over the resulting prediction-relevant subspace. Empirically, ScopeSAE yields an effect we term reconstruction-better-than-original. Written-back reconstructions of the SAE produce lower next-token cross-entropy than the original activations, an outcome that, to our knowledge, has not previously been reported for SAEs. Through interventional analyses and a KL fine-tuning counter-experiment, we show that this effect is attributable to ScopeSAE's prediction-relevant subspace itself rather than to architectural changes. ScopeSAE further improves effective feature count, interpretability, utilization, and dictionary redundancy over existing layer-based baselines, suggesting that choosing the SAE modeling subspace by predictive relevance leads to more useful and behaviorally meaningful features.
Read the full abstract

All authors Qingwen Zeng, Zehao Fu, Shuyu Meng, Linghan Huang, Jiayi Zhang, Chenglin Wu, Ling Chen, Huaming Chen

Information Retrieval

ModelLakeFishing: Efficient Retrieval over Million-Scale Model Lakes

Xiaoyang Liu, Zhengyuan Dong and Renée J. Miller

Open model lakes may contain millions of reusable models, making it costly to identify suitable models for a new dataset. We present ModelLakeFishing, a model-retrieval framework for queries specifying a target dataset, prediction task, and evaluation metric. It consolidates metadata and historical evaluations into a model-dataset-task evidence graph, learns model and query embeddings with a relation-aware graph encoder, and indexes model embeddings using Hierarchical Navigable Small World (HNSW) search. At query time, HNSW retrieves 1,000 candidates without scoring every model, after which a training-side task prior reranks candidates for the requested metric and returns the top 10. We evaluate on a lake of 3,016,439 models and 247,803 observed model-dataset performance pairs using three root-aware splits that hold test performance edges out of representation learning and retrieval. ModelLakeFishing achieves a mean eligible-query gold@10 of 0.2968, recovering the observed-best model in the top 10 for 29.68% of eligible queries and retaining 93.47% of the gold@10 of an exhaustive baseline using the same scoring and reranking procedure. Given precomputed query embeddings, retrieval and reranking take 0.747 ms median and 1.102 ms at the 95th percentile. These results demonstrate efficient retrieval over million-model lakes from sparse relational evidence.
Read the full abstract

Artificial Intelligence

Self-Evaluating Recursive Agents

TianYi Lyu, Xiaozhe Li, Yang Li et al. (+7 more)

Recursive language-model agents decompose tasks and delegate subtasks to child instances of the same policy, forming a tree of work. Training them, however, is hard: the final outcome is verifiable, but the self-invented intermediate subtasks are numerous and carry no ground truth. Existing methods score each node with a verifier or judge, which is costly at scale and blind to decomposition quality. We argue that a recursive agent must learn three coupled capabilities within one set of weights: decomposing problems into subtasks, solving them, and evaluating the outcomes, each requiring its own training signal. SERA (Self-Evaluating Recursive Agents) turns evaluation into a learned capability of the policy itself. Before delegating, the parent writes a rubric of weighted success criteria for each child subtask; a ranking objective against verified outcomes then trains rubric generation so that the criteria track genuine subtask success. In addition, a complementary leaf-coverage signal provides direct credit for task decomposition. Our central finding is that training the policy to generate aligned rubrics is what drives the gains: because the same weights both evaluate and execute, learning to judge subtasks sharpens the agent's ability to solve them. Notably, external supervision is also reduced: the judge is consulted only to train the rubric generator, while solving is trained against the agent's own rubric scores, which outperform direct use of the judge. Beyond training, the learned rubric doubles as an inference-time selector for tree search. On TextCraft-Synth and TextWorld-Sync, SERA improves over strong recursive-agent baselines by 5.38 and 13.14 points on average, and rubric-guided tree search at inference adds a further 2.43 points on TextWorld-Sync.
Read the full abstract

All authors TianYi Lyu, Xiaozhe Li, Yang Li, Yongkang Chen, Kefei Tian, Junbo Niu, Zican Hu, Hongbo Liu, Mingliang Xiong, Qingwen Liu

Systems and Control

A Unified Framework for Robust Data-Driven Model Predictive Control with Terminal Ingredients

Zhaohua Yang, Nan Bai, Pengyu Wang et al. (+1 more)

This paper proposes a unified framework for robust data-driven model predictive control (MPC) with terminal ingredients for unknown linear time-invariant systems. Based on Willems' fundamental lemma, a single offline input-output trajectory is used as an implicit model, while online implementation only requires past input-output measurements. Bounded measurement noise is considered in both offline and online output data. The framework consists of an offline stage, where robust terminal ingredients are designed directly from noisy data, and an online stage, where these ingredients are incorporated into a one-step MPC scheme. Recursive feasibility of the proposed framework and practical exponential stability of the closed-loop system are established. Numerical results illustrate the performance tuning capability of the terminal set, with particularly pronounced benefits for short prediction horizons, and show that the proposed framework achieves performance comparable to data-driven MPC without terminal ingredients while requiring a reduced prediction horizon and less online computation.
Read the full abstract

All authors Zhaohua Yang, Nan Bai, Pengyu Wang, Ling Shi

Computation and Language

Rewrite What Matters: Adaptive Multilingual Query Rewriting for Reasoning via Agentic Reinforcement Learning

Rui Qi, Yufeng Chen, Yunlong Liang et al. (+6 more)

In multilingual scenarios, queries with equivalent semantics but in different languages could guide the model into different reasoning trajectories, leading to performance disparities. To mitigate this gap, previous studies typically apply a one-size-fits-all query rewriting strategy, such as translation, which overlooks the fact that different scenarios require diverse types of semantic transformations. In this paper, we propose mRewriter-R1, an agentic multilingual query rewriting framework with reinforcement learning. Unlike single-turn rewriting, mRewriter-R1 formulates multilingual query rewriting as a multi-turn sequential decision-making process, where the model dynamically performs multi-aspect optimization through adaptive operator selection. Experimental results demonstrate that mRewriter-R1 outperforms all strong multilingual rewriting baselines on different large reasoning backbones. Further analyses show that the learned policy can adaptively decide on rewriting operators according to query characteristics, exhibiting strong generalization ability across diverse reasoning tasks, and plug-and-play compatibility with heterogeneous reasoning language models.
Read the full abstract

All authors Rui Qi, Yufeng Chen, Yunlong Liang, Chuan Meng, Sijin Lu, Ge Shi, Jinan Xu, Fandong Meng, Kaiyu Huang

Computation and Language

A Systematic Analysis of the Predictive Power of LM Surprisal in Reading Chinese

Hongao Zhu, Muxiaoqiao Xu, Yikang Liu et al. (+4 more)

This study analyzes the predictive power of LM-derived, token-level surprisal on Mandarin Chinese reading times. We first propose the Shortest Matching Sequence (SMS), an alignment scheme that maps between the word segmentation assumed by eye-tracking corpora and the LMs' subword tokenization, as the two tokenizations often disagree in the context of Mandarin Chinese. Then, using a suite of Chinese-Pythia models (14M-1.4B) trained on scratch with 30B tokens, we examine how well surprisal predicts first fixation duration, gaze duration, and total reading time in three paragraph-level eye-tracking corpora of Mandarin Chinese (GECO-CN, HKP, and MECO). Contrary to previous null findings, our results show that surprisal is predictive of Chinese reading times. However, whether predictive power scales with model size and the amount of training is corpus-specific: bigger models predict better in GECO-CN, whereas inverse scaling emerges in HKP and, at the largest sizes, in MECO. Subsequently, we tested one possible explanation for the inverse scaling in HKP and found that checkpoints whose surprisal remains closer to $n$-gram statistics are better predictors of reading. All in all, the predictive power of surprisal on Chinese reading time measurements is corpus-specific, which cautions against drawing scaling conclusions from a single corpus.
Read the full abstract

All authors Hongao Zhu, Muxiaoqiao Xu, Yikang Liu, Siyuan Song, Yuxia Wang, Byung-Doh Oh, Hai Hu

Cryptography and Security

WLPA: A Network Management Framework for Allocating Scarce Quantum-Safe Link Postures under Weakest-Link Exposure

Bhanwar Gupta and Sanjeev Rana

Network operators migrating distributed systems to post-quantum and quantum-safe cryptography face a resource-management problem: quantum key distribution (QKD) gives the strongest guarantee available but is hardware-scarce and costly, so only a fraction of a deployment's links can receive it. Default practice – ranking links by traffic or centrality and upgrading the top scorers – optimizes each link in isolation, while a distributed job's real security is set by whichever active link ends up weakest. We present WLPA (Weakest-Link Posture Assignment), an implementation-ready decision framework and algorithm for allocating scarce quantum-safe postures under hardware, latency, and compliance constraints. WLPA computes the optimal weakest-link posture in closed form and returns an assignment in O(|E| log |E|) time – 125 ms for a 20,000-link network on a laptop – with a breach-aware refinement matching an exact integer program under common conditions. Our central contribution is a dichotomy telling operators exactly when existing per-link heuristics already match this optimum and when they systematically fail: under constant upgrade cost and uniform traffic-driven risk the two coincide exactly; once costs vary or an adversary concentrates on weak targets, heuristics leave the weakest link unprotected, unboundedly. We validate WLPA across 19 experiments: four microservice topologies, a real enterprise network (SNAP email-Eu-core), a post-quantum latency benchmark, a Qiskit BB84 simulation and a real-hardware BB84 run on IBM's ibm_marrakesh processor, checks against real production traffic traces, a CVE-calibrated correlated-compromise study, Bayesian uncertainty quantification, and seven baseline methods. A concrete-security reduction grounds the framework as theoretical foundation, not primary contribution.
Read the full abstract

Robotics

Tackling Sim-to-Real Mismatch Through Sampling-Based Disturbance Observers: From Analytical Models to Learned World Models

Tianqi Zhu, Jun Yang, Jianliang Mao et al. (+2 more)

Robotic controllers increasingly rely on analytical models, simulators, cost-query interfaces, and learned world models. However, physical deployment can deviate from nominal assumptions, and additional disturbances may arise even when the model itself is accurate. In control systems, disturbance observers (DOB) are widely used to estimate such unmeasured effects from nominal models and measured feedback. Classical DOB formulations are generally built around explicit plant models. This paper develops the sampling-based disturbance observer (SDOB), extending the DOB principle to a broader range of models, including simulators and learned world models, through state-rollout or cost-query interfaces. SDOB separates two observable channels: state-effect disturbances, for which the feedback state differs from its prediction, and cost disturbances, for which the same query state receives different costs as the perceived environment changes. Diverse simulation and real-robot experiments across traditional and learned models demonstrate the effectiveness of SDOB in compensating for sim-to-real mismatch and improving control performance.
Read the full abstract

All authors Tianqi Zhu, Jun Yang, Jianliang Mao, Cong Li, Shihua Li

Machine Learning

SFlexRCA: Lightweight, Scalable, and Flexible Root Cause Analysis for IIoT Edge Systems

Amr M. Zaki, Farhoud Jafari, Honggeun Ji et al. (+2 more)

Industrial Internet of Things (IIoT) systems generate high-dimensional sensor telemetry from interconnected components, where faults can propagate across the system. To address these challenges, we propose SFlexRCA (Scalable and Flexible Root Cause Analysis), a topology-free RCA framework designed for resource-constrained IIoT environments. SFlexRCA transforms multivariate telemetry into compact orthogonal representations and applies shared lightweight linear modeling, avoiding explicit graph construction, message passing, and per-variable or lag-specific parameter growth. We evaluate SFlexRCA on three publicly available IIoT datasets, BATADAL, SWaT, and WADI, spanning different numbers of monitored variables, temporal characteristics, and training-data regimes. SFlexRCA is compared with 10 statistical, causal, and non-causal baselines in terms of RCA accuracy, training efficiency, inference latency, and memory consumption. In addition, inference efficiency and memory consumption are evaluated on Raspberry Pi 3 and Raspberry Pi 5, while energy consumption is additionally measured on Raspberry Pi 5. We further investigate temporalcontext sensitivity, architectural and loss components, and alternative representations. Notably, SFlexRCA maintains strong localization performance on BATADAL despite its limited normal-operation training data, while its compact shared architecture avoids the parameter growth associated with causal and graph-based approaches. Its lightweight shared architecture further enables efficient deployment on resource-constrained IIoT edge devices. The SFlexRCA code is available at https://github.com/theamrzaki/RootCause- Analysis-Correlation-Attentive-Modeling.
Read the full abstract

All authors Amr M. Zaki, Farhoud Jafari, Honggeun Ji, Komal Sarda, Marin Litoiu

Artificial Intelligence

ForkPilot: Self-Evolving Policy for Retrospective Search in Long-Horizon Agents

Xinyue Zeng, Shivam Shandilya, Guilherme Potje et al. (+6 more)

Interactive language-model agents increasingly solve complex tasks through long-horizon, multi-call reasoning, where errors in beliefs or actions can compound across tool interactions. Retrospective search can recover from such failures but is prone to misallocation. Delayed outcomes obscure the contribution of intermediate search decisions, leading to Attribution Complexity, while evolving execution evidence leads to Adaptation Complexity, where previously learned estimates become stale. To address these challenges, we first introduce Search Value Dynamics (SVD), which characterizes the evolving trade-off between the gain and cost of retrospective search. Building on SVD, we propose ForkPilot, a self-evolving two-stage policy-learning framework. In the first stage, ForkPilot learns a search-value policy offline from completed trajectories through automatically constructed outcome comparisons. In the second stage, it makes search decisions based on current observations and then self-evolves by incorporating newly completed trajectories into subsequent policy updates. We evaluate ForkPilot across 6 diverse benchmarks and 7 widely used LLM backbone families, including four open-source families, GPT-5.6 Sol, and Opus 4.8 in a production agentic system, against 9 competitive baselines, including a real-world harness deployment used by hundreds of thousands of paid users. ForkPilot achieves comparable state-of-the-art performance while reducing token usage by up to 59.2%, demonstrating its efficacy.
Read the full abstract

All authors Xinyue Zeng, Shivam Shandilya, Guilherme Potje, Leonardo Nunes, Rakshanda Agarwal, Ranveer Chandra, Emre Kiciman, Dawei Zhou, Tusher Chakraborty

Computation and Language

No Hindsight for LLM Fact-Checkers: Measuring Leakage Channels in Misinformation Detection

Kuan-Hua Wu Lu and Yohanes Andre Setiawan

As automated fact-checking scales on social media, large language model (LLM) verdict scores can look stronger than warranted. One reason is that evaluations mix in information that was not knowable at claim time. Two channels are easy to conflate: outcomes memorized in pre-training and retrieved evidence published after the claim. Yet standard benchmarks rarely separate the two. In this study we measure both channels on AVeriTeC and QuanTemp++ by reconstructing point-in-time evidence conditions and probing for outcome information encoded in model representations. We find substantial evidence of parametric leakage, that can be hidden by the aggregate accuracy, while a simple representation bottleneck reduces this future leakage more efficiently than a mutual-information-based training penalty. We also find that allowing post-claim evidence inflates zero-shot accuracy by 6.3 points in AVeriTeC while the effect is negligible in QuanTemp++, where retrieval provides little post-claim evidence. These results show that misinformation benchmarks can overstate fact-checking performance when they do not account for what information was actually available at claim time.
Read the full abstract

Sound

TS-SP: Learning Speaker-Preserving Representations in Audio Large Language Models

Junjie Li, Zheng Liang, Zhe Li et al. (+2 more)

Audio large language models (ALLMs) can understand speech content, yet their ability to use speaker identity for verification remains limited. We propose TS-SP (Two-Stage Speaker Preservation), a parameter-efficient framework for learning speaker-preserving representations and making them accessible to an ALLM's language-model component. We instantiate and evaluate TS-SP on Qwen2.5-Omni-7B. First, we adapt the audio encoder with speaker identity supervision. We then freeze the adapted encoder and train the language model to compare speakers. Both stages use low-rank adaptation (LoRA), keeping the pretrained base weights fixed. On Vox1-O, TS-SP reduces the equal error rate (EER) from 7.01% for the Paired Loss Adaptation Baseline to 4.37%. EER remains within 4.31–4.79% under unseen prompts. Cross-domain evaluation on CN-Celeb yields a similar EER to the baseline, but lower accuracy at the native decision threshold. These findings support two-stage adaptation for improving speaker verification on the evaluated backbone.
Read the full abstract

All authors Junjie Li, Zheng Liang, Zhe Li, Tianchi Liu, Kong Aik Lee

Computer Vision

Reflection-Robust 6DoF Object Tracking with Light Fields

Nikolai Goncharov and Donald G. Dansereau

Tracking the 6DoF pose of a moving rigid object is fundamental to robotics and autonomous driving, but existing trackers assume that object appearance is stable across a sequence, an assumption that breaks down on reflective surfaces whose appearance changes as they mirror the environment. We introduce a light field based reflection-robust 6DoF tracker that turns this apparent nuisance into a pose cue. Per frame, our method recovers depth robustly against reflections, back-projects it into a point cloud, and estimates surface normals. It then decomposes the object's view-dependent appearance into a diffuse albedo and the environment map it reflects, resulting in a relightable surface light field. Starting from a coarse initialization, we relight it by the recovered environment map and optimize the pose on the photometric loss. Because a moving object mirrors new parts of the scene, the environment map fills in as the sequence proceeds, sharpening this signal over time. To evaluate this approach, we introduce a light field tracking dataset re-rendered from a robotic manipulation benchmark at four controlled reflectivity levels, each paired with simulated depth that reproduces how consumer RGB-D sensors fail on shiny surfaces. Additionally, we evaluate on two captured light field sequences. Our method trails the strongest baselines on diffuse objects and is the only one that holds its accuracy on fully reflective objects, where every baseline degrades.
Read the full abstract