Artificial Intelligence · Cross-listed from cs.RO
Representation Handoffs for OpenArm-Based Laboratory Mobile Manipulation
Yang Shen, Chonghao Cheng, Ziyi Zhao et al. (+6 more)
Open-source robotics and foundation models have lowered the barrier to
embodied AI, yet
language-guided laboratory automation still requires reliable
alignment from instructions and observations to safe actions. This field report presents an OpenArm-based mobile manipulation prototype for laboratory-style tasks, built by integrating dual OpenArm manipulators with a mobile base, vertical slide, RGB-D sensing,
lidar-based mapping, ROS2/MoveIt execution, and profile-defined skill interfaces. The system is organized around representation handoffs: natural
language requests are constrained into registered skill calls, sensor observations are grounded into maps and object poses, object priors provide role and skill constraints, and runtime bindings compile validated skills into executable motion goals. We use dry-run traces and startup checks to evaluate this integration path, showing how the prototype exposes missing calibration, incomplete object assets, and unfinished real-scene visual grounding as explicit deployment blockers. These intermediate representations serve as practical debugging interfaces for integrating
language, perception, planning, and
robot safety in
embodied systems.
Read the full abstract ▾
All authors Yang Shen, Chonghao Cheng, Ziyi Zhao, Jialuo Zhu, Zhenyi Yi, Qi Zhao, Jian Yang, Yuhui Shi, Chin-Teng Lin
Artificial Intelligence · Cross-listed from cs.LG
Interpretable reinforcement learning with decision-tree pruning
Mark Leon Ringer and Michel Tokic
Reinforcement learning policies are difficult to inspect, but interpreting them is a prerequisite for trustworthiness. Converting a trained policy into explicit decision-tree rules improves transparency and the resulting artifacts often remain too complex for human understanding. We present a
pruning process that simplifies such rule-based policies while preserving task performance and making edits to the policy auditable. The process defines a small set of structural and usage-aware operators and evaluates candidate edits by re-executing the policy to measure return and interpretability proxies. This exposes an transformation process from complex to compact policy structures. We investigate this approach on classic control and MuJoCo
benchmarks, where
pruning traces reveal consistent interpretability improvements while maintaining high performance.
Read the full abstract ▾
Artificial Intelligence
A MARL Centered Reference Architecture for Large Language Model Augmentation in Smart Manufacturing
Fouad Bahrpeyma and Dirk Reichelt
Modern manufacturing imposes six coupled demands on adaptive control: local decisions with global consequences, partial observability, nonstationarity, reflex speed response with long horizon effects, delayed and diffuse outcomes, and dynamics that resist explicit modeling. Cooperative multiagent reinforcement learning (MARL), posed as a Dec-POMDP under centralized training with decentralized execution, is a particularly natural formalism for these demands. This paper adopts a MARL centered scope and asks where large
language models (LLMs) should augment, interface with, train, or, in the strongest competitive case, replace that coordination core. A taxonomy organizes the literature through four LLM attachment points: policy, reward design, communication between
agents, and hierarchical planning. A conditional capability profile separates native mechanism, reported performance, formal guarantee, and engineering maturity, and a deployment readiness analysis identifies the evidence behind each role. These stages yield the principal contribution: a three layer MARL centered reference architecture, grounded in evidence, for semantic
reasoning, adaptive cooperative control, and independently assured execution. The LLM-Augmented Dec-POMDP is a descriptive comparative notation for that architecture, recording four attachment choices without introducing a new decision process class or
algorithm. Under the reviewed evidence, conventional MARL is better suited to frequent, structured, decentralized coordination after task specific training, whereas LLM components are promising for semantic interpretation, reward drafting, human interaction, and slower supervisory planning. Current LLM only manufacturing controllers do not yet establish equivalence for strict real time, decentralized, safety critical control; this conclusion is bounded by the available evidence and does not assert impossibility.
Read the full abstract ▾
Artificial Intelligence
DiDPO: Diff-in-Diff Policy Optimization for Coding Agent Training
Xucong Wang, Zhe Zhao, Liheng Yu et al. (+3 more)
Reinforcement learning with Verifiable Reward (RLVR) has emerged as a powerful paradigm for training coding
agents, where the execution feedback from compilation and tests provides objective verification. However, unlike
agent tasks, coding
agents face a unique and finer-grained credit assignment challenge: at each step, coding actions simultaneously pack varying changes into different regions of a code version, which makes the contribution of independent change indistinguishable. Existing RLVR methods mostly leverage the outcome reward or step-level reward, which fails to dive into a code diff and makes unique properties of coding actions invisible to training. In this paper, we propose Diff-in-Diff Policy Optimization (DiDPO), a critic-free RL method that constructs fine-grained credit units directly from the structure of code diffs. DiDPO organizes multi-turn coding interactions into multiple thought–action steps and discovers code diffs across sampled trajectories. It then selects anchors by aggregating highly similar sub-diffs split from each whole diff by our “groupability score”, which provides the splitting schema that optimally balances the semantic scope of anchors and the group mass they may form. Finally these anchors form advantage groups and project the diff-level advantage back to individual response
tokens. Experiments on long-horizon coding and
reasoning benchmarks show that DiDPO significantly outperforms strong agentic RL baselines. On Qwen2.5-7B-Coder, DiDPO exceeds comparable methods by over 10% and narrows the gap with far larger models, offering a principled framework for fine-grained credit assignment in coding
agent training. We also open-source verl-code, an agentic rl codebase that supports various RL methods and coding
benchmarks.
Read the full abstract ▾
All authors Xucong Wang, Zhe Zhao, Liheng Yu, Di Wu, Xiaofeng Cao, Pengkun Wang
Artificial Intelligence · Cross-listed from physics.acc-ph
Autonomous discovery of accelerator commissioning algorithms
Thorsten Hellert
Simulated commissioning has become essential for de-risking modern light-source design and commissioning, but the procedures being simulated are still designed entirely by human experts. Their labor-intensive redevelopment after
lattice changes makes such studies hard to repeat and limits their use during early design iteration. This Letter demonstrates a closed research loop in which a
language-model
agent writes commissioning code, tests it in simulation, and improves the
algorithm from the results. Applied to RF beam capture in the ALS-U accumulator-ring model, the loop substantially improves a working expert procedure and can construct a working one from a minimal starting point, with more capable models succeeding from less initial code. Extending the same framework to multiple objectives produces 16 non-dominated
algorithms spanning physically distinct trade-offs between rapid beam capture and correction of seeded machine errors. This reframes commissioning studies from evaluating human-designed procedures toward a mode in which
agents participate directly in discovering accelerator
algorithms.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.HC
PHOENIX: Fine-Tuned SLM-Powered Autonomous Satellite Lifetime Extension via Predictive Self-Healing and Multi-Agent AI Recovery
Sumaiya Islam and Harsha Kumara Moraliyage
Most CubeSats, small and low-cost satellites roughly the size of a shoebox, do not survive as long as they were designed to: a study of 178 missions found that only 48-65% remain operational after two years, against a designed lifetime of 2-5 years. The deeper issue is that a CubeSat in low Earth orbit (LEO) is physically unreachable from the ground for roughly 85 minutes out of every 96-minute orbit, so faults that start during that window go unnoticed until the next contact pass, by which point recovery may no longer be possible. We propose PHOENIX (Predictive Health On-orbit Edge Neural Intelligence eXtension) to give the satellite its own fault
reasoning capability. A fine-tuned Small
Language Model (SLM) compact enough to run on embedded hardware is deployed onboard the CubeSat, running on the flight-proven Aethero NxN-ECM computer, monitoring all sensor readings continuously, and resolving recurring faults using a
memory system that stores past repairs so the same inference does not need to run twice. Once per orbit it sends a short structured health report to the ground instead of a raw data dump; six specialized AI
agents on the ground read that report and generate validated satellite commands within the 5-10 minute contact window. A generative
diffusion model (DDPM) creates synthetic training data because real fault examples make up only 0.57-1.80% of the
dataset. We report preliminary results on the ESA Anomaly Detection
Benchmark (14 years, 76 channels, 118 labeled faults).
Read the full abstract ▾
Artificial Intelligence
How Much, Then Where: Credit-Conserving Action-to-Token Allocation for Multi-Turn Agent Reinforcement Learning
Lichao Ma, Yang Sun, Shuaitao Zhao et al. (+9 more)
Credit assignment in multi-turn
agent reinforcement learning operates at two levels: assigning trajectory-level credit to actions and distributing each action's credit across its
tokens. In this paper, we introduce FACTOR, which separates these decisions. FACTOR uses checkpoint-calibrated TD residuals to assign per-action credits that
telescope to the trajectory advantage, and feedback-conditioned teacher-student likelihood gaps to allocate each credit across the realized action
tokens. Per-action normalization preserves the action-average coefficient and prevents
token-level sign flips. We pair this construction with an action-mean reduction, removing the implicit dependence of an action's scalar surrogate weight on its
token length. At the behavior policy and before clipping, each action's inner action-mean surrogate equals its TD credit. FACTOR consistently improves over competitive baselines across ALFWorld, WebShop, and ScienceWorld, with every environment-seed comparison favoring FACTOR and the largest gains emerging on the longest-horizon environment. The same hyperparameters transfer without retuning to a larger backbone and to a different model family. Ablations identify TD action credit as the dominant driver of the improvement, with hindsight
token allocation contributing complementary gains.
Read the full abstract ▾
All authors Lichao Ma, Yang Sun, Shuaitao Zhao, Yangyi Fang, Cong Qin, Xiaoliang Fu, Yuhang Tian, Yuchen Wei, Junbo Zhu, Yang Wei, Lu Pan, Jiaye Lin
Artificial Intelligence · Cross-listed from cs.CV
Geometry-Aware Camera Localization for Bronchoscopy
Lumin Chen, Qingyao Tian, Jinpeng Li et al. (+5 more)
Camera localization in bronchoscopy remains a challenging problem due to stringent accuracy requirements, real-time constraints, and limited training data. Compared to natural scenes, the confined anatomical structures demand millimeter-level precision, while intraoperative guidance necessitates low-latency inference. However, existing methods often fail to effectively exploit preoperative
geometric priors, limiting their robustness and accuracy. To address these limitations, we propose a unified geometry-aware bronchoscope localization framework (GABL) that effectively fuses preoperative structural priors with paired intraoperative
video to estimate 6-DoF camera poses. Specifically, to address visual ambiguity in complex airways, we propose a graph-guided coarse-to-fine localization scheme that effectively leverages structural priors for precise pose estimation. Furthermore, to mitigate pose jitter and bridge the visual-structural gap, we integrate a
Transformer-based tracking model with a novel RGB-depth matching objective, jointly enforcing spatio-temporal and
geometric consistency. Extensive experiments demonstrate that our method yields remarkable reductions of 8.37% and 31.76% in translation and rotation errors over the prior state-of-the-art, alongside 4 times inference speedup (33.6 FPS) for robust real-time bronchoscope localization. Project website: https://paulili08.github.io/GABL/.
Read the full abstract ▾
All authors Lumin Chen, Qingyao Tian, Jinpeng Li, Haoyu Jiang, Huai Liao, Xinyan Huang, Hongbin Liu, Dong Yi
Artificial Intelligence
MemWM: Memory-Augmented Text-Based World Model
Yujun Wang, Tao Zhang, Jinhe Bi et al. (+9 more)
World models are increasingly used to support planning in
agents by predicting how environment states evolve in response to
agent actions. Yet fluent next-state predictions can still omit task-critical facts, corrupt product attributes, or apply incorrect transition rules. To address such systematic prediction errors, we introduce MemWM, a
memory-augmented text-based world model. MemWM uses world
memory, a curated
memory bank of transition rules, state caches, and hard-to-predict facts, to condition next-state imagination. We evaluate factual state preservation with Structured State Fidelity (SSF), which scores predicted states through
benchmark-specific facts and fields. Compared with SFT,
memory-augmented training improves SSF by up to 206.3%. In the full planning setting, we keep the policy model frozen and provide policy-side world skill: retrieved task-level skills and step-wise corrective guidance for action selection. Across ALFWorld, WebShop, and ScienceWorld,
memory-augmented
agents improve downstream success over an SFT-trained world-model
agent, with up to a 65.4% relative gain. Sensitivity analyses further show that retrieved
memory improves task success and efficiency under different
memory and action-budget settings.
Read the full abstract ▾
All authors Yujun Wang, Tao Zhang, Jinhe Bi, Aniri, Wenxuan Ye, Boliang Liu, Sikuan Yan, Shuning Wang, Xuebing Zhou, Sören Pirk, Hinrich Schütze, Yunpu Ma
Artificial Intelligence · Cross-listed from cs.CV
International Transfer of Stochastic Cortical Self-Reconstruction
Fabian Bongratz, Zhizheng Zhuo, Chao Zhang et al. (+3 more)
Stochastic cortical self-reconstruction (SCSR) enables personalized mapping of gray matter atrophy, a hallmark of neurodegenerative disorders such as Alzheimer's disease (AD), onto high-resolution cortical surfaces. Unlike conventional normative modeling approaches, which typically operate at a coarse regional level and remain inherently constrained by the
covariates included during training, SCSR estimates an individualized healthy reference directly from the observed cortical thickness at the vertex level. This allows the detection of subtle, subject-specific deviations from healthy cortical shape. In this work, we investigate the generalization and transferability of SCSR, originally trained on UK Biobank (UKB) data, to an independent Chinese population
dataset. Specifically, we evaluate the ability of SCSR-derived Z-scores to discriminate between healthy scans, individuals with mild cognitive impairment (MCI), and patients with AD, while also assessing model robustness across the lifespan. We compare four training strategies: direct application of the UKB-trained model, fine-tuning on Chinese data, training from scratch, and joint training on UKB and Chinese cohorts. As reconstruction backbones, we consider both a multilayer perceptron (MLP) and a Spherical UNet (SUNet). Our results demonstrate that SCSR provides robust detection of cortical atrophy in the Chinese population across all evaluated models. The highest discriminative performance was achieved by the fine-tuned SUNet model (average pairwise AUC = 0.848), followed closely by the UKB-trained SUNet. Moreover, reconstruction errors remained low across the lifespan, even when the training population exhibited a substantially narrower age distribution, indicating strong cross-population transferability.
Read the full abstract ▾
All authors Fabian Bongratz, Zhizheng Zhuo, Chao Zhang, Yaou Liu, Dennis M. Hedderich, Christian Wachinger
Artificial Intelligence · Cross-listed from cs.HC
Human-Centered Explainable AI for TinyML Edge Devices: A Pareto-Based Selection Framework with LLM-Guided Design
Zeinab Dehghani, Dhavalkumar Thakker, Koorosh Aslansefat et al. (+4 more)
Edge Artificial Intelligence (Edge AI) enables the deployment of AI models directly on local edge devices, while such deployments are subject to strict resource constraints, particularly in clinical applications requiring local and timely inference. In such contexts, explainable artificial intelligence (XAI) can serve as a human-AI interface intended to support healthcare professionals' and patients' understanding of model predictions and informed decision-making. To fulfill this role, XAI method selection for TinyML deployments can be formulated as a human-centered multi-objective design problem that jointly considers qualitative stakeholder preferences, explanation quality, and proxy-based deployment cost. We propose a framework that integrates a large
language model (LLM)-guided design interface that maps qualitative stakeholder preferences to candidate XAI methods, followed by deterministic feasibility filtering and Pareto-based optimization. The framework exposes trade-offs among explanation fidelity, stability, and proxy-based deployment cost while characterizing their implications for explanation quality and estimated deployment feasibility. A proof-of-concept evaluation on a skin lesion classification task illustrates how the framework systematically compares candidate XAI methods and identifies Pareto-efficient trade-offs. The present evaluation covers the computational selection stages, while physical MCU deployment and empirical human-expert validation remain outside the scope of this study.
Read the full abstract ▾
All authors Zeinab Dehghani, Dhavalkumar Thakker, Koorosh Aslansefat, Kuniko Paxton, Bhupesh Kumar Mishra, Baseer Ahmad, Rameez Raja Kureshi
Artificial Intelligence · Cross-listed from cs.CV
RoRA: Role-Oriented Regional Allocation for Visual Token Pruning in MLLMs
Qiyanhui Lu, Han Wu, Rongjian Xu et al. (+6 more)
Multimodal large
language models (MLLMs) encode images as long visual
token sequences, making prefilling and KV-cache storage expensive. Existing training-free
pruning methods select
tokens by importance, diversity, or spatial coverage, but treat retained
tokens as interchangeable and do not explicitly track which object-related regions are already covered. We present RoRA, a training-free framework that casts visual
token pruning as role-oriented regional evidence allocation. Given a fixed budget, RoRA partitions
tokens into a protected semantic core, complementary context, and fine-grained detail. It first calibrates text-conditioned
attention with a positional prior and a
prompt-calibrated object prior, then builds
Attention-Anchored Regions (AARs) from high-confidence anchors as lightweight proxies for covered object support. Context is explored mainly outside AARs, while a small AAR-guided budget restores local detail; pairwise similarity is used only for context-stage redundancy filtering. Under matched budgets, RoRA consistently outperforms strong training-free baselines across LLaVA and Qwen-VL families, retaining most of the unpruned accuracy even at aggressive
pruning ratios, e.g., 96.5% of full performance at 88.9%
pruning on LLaVA-1.5, and improving over D2Pruner by about 5% on Qwen3-VL at 75-90%
pruning. At a 66.7%
pruning ratio, RoRA requires only 0.7 ms for
token selection and reduces end-to-end inference time by 24.6%, corresponding to a 1.33x speedup over unpruned inference on an NVIDIA H800.
Read the full abstract ▾
All authors Qiyanhui Lu, Han Wu, Rongjian Xu, Tingzhang Luo, Cheng Fan, Xinghao Chen, Minjing Dong, Jufeng Yang, Jianyuan Guo
Artificial Intelligence · Cross-listed from cs.LG
Beyond Isolation: Unlocking Reinforcement Learning Component Synergy for Sample-Efficient Continuous Control
Qi Zhao, Guozheng Ma, Yilun Kong et al. (+9 more)
Reinforcement learning systems are significantly more complex than other machine learning paradigms due to inherent properties, causing RL system design to jointly account for many tightly coupled factors. Despite advances in individual algorithmic components, their functional interdependencies remain underexplored: do they exhibit mutual synergy or counterproductive interference? To bridge this gap, we conduct a systematic investigation and find that the efficacy of different components exhibits significant task-dependency, and naively stacking state-of-the-art techniques does not necessarily yield performance gains; instead, it often triggers emergent challenges, such as compounded non-stationarity. Building upon these findings, we distill a suite of actionable insights into the principled coordination of these components. Guided by these insights, we propose ROSER, an RL framework that coordinates three critical dimensions: Model-based Representation, Optimization Stability, and Experience Replay. Across diverse continuous-control
benchmarks, ROSER consistently outperforms vanilla baselines and achieves 17.60% gains over naive stack. Our findings underscore the necessity of a holistic perspective in RL system design and paves the way for developing sample-efficient
agents.
Read the full abstract ▾
All authors Qi Zhao, Guozheng Ma, Yilun Kong, Lu Li, Haoyu Wang, Zilin Wang, Tiantian Zhang, Yuxing Wang, Jian Sha, Yongzhe Chang, Xueqian Wang, Dacheng Tao
Artificial Intelligence · Cross-listed from cs.RO
LifelongCrossNav: Persistent 3D Semantic Memory for Cross-Floor Multi-Object Navigation
Zehui Li, Zihao Sun, Jiawei Xu et al. (+6 more)
Object-goal
navigation has made substantial progress in semantic perception and exploration, yet persistent
memory for multi-object
navigation and cross-floor
navigation are still commonly addressed separately. We present LifelongCrossNav, a framework for sequential multi-object ObjectNav in unknown multi-floor indoor environments. Within each episode, the
agent receives an ordered sequence of object-goal queries while continuously maintaining a shared sparse 3D semantic voxel
memory. This
memory incrementally accumulates
geometric structure, traversability states, and
vision-
language features, allowing subsequent object-goal queries to retrieve previously acquired scene information without rebuilding the map. To support persistent search across floors, LifelongCrossNav combines support-aware 3D traversability mapping, stair-specific perception, and direction-aware stair traversal. A unified
navigation policy coordinates same-floor frontier exploration, live and historical point-of-interest
retrieval, stair
navigation, and target-object search and approach. We further introduce HM3D-MFMON, a
benchmark for sequential Multi-Floor Multi-Object
Navigation built on HM3D scenes, including a dedicated subset in which completing the full sequence of object-goal subtasks requires at least one floor transition. Experimental results show that LifelongCrossNav consistently outperforms a representative planar persistent semantic-map baseline on HM3D-MFMON, demonstrating that persistent 3D semantic
memory and cross-floor traversability modeling effectively support sequential multi-object
navigation in multi-floor environments.
Read the full abstract ▾
All authors Zehui Li, Zihao Sun, Jiawei Xu, Zheqi He, Xiaoqiang Zhang, Jing-Shu Zheng, Lu Liu, Dahui Gao, Xiuwan Chen
Artificial Intelligence · Cross-listed from cs.DC
Scalable High-Fidelity Macromolecular Docking for GPU-Accelerated Supercomputers
Xiangyu Meng, Peng Chen, Mingzhen Li et al. (+7 more)
Flexible macromolecular docking offers high-fidelity predictions of biomolecular interactions, but remains prohibitively expensive at scale. Among existing approaches, LightDock leverages Glowworm Swarm Optimization (GSO) for accuracy, yet suffers from limited parallelism, irregular computation, and severe load imbalance, preventing efficient execution on GPU supercomputers. We present SparkleDock, a scalable GSO-based docking framework enabling near-real-time flexible docking. We redesign GSO to expose massive fine-grained parallelism at the glowworm-
agent level, and restructure the dominant energy scoring computation into a Tensor Core-compatible formulation, enabling efficient execution of irregular pairwise interactions through structured
matrix operations. We further introduce a performance-model-driven scheduling for load balancing and out-of-core scaling across GPUs. SparkleDock achieves 9.7 $\times$ and 18.9 $\times$ speedups over LightDock on single A100 and H100 GPU, and delivers over two orders of magnitude acceleration at scale. On 512 GPUs, it reduces docking time from hours to seconds, enabling large-scale, high-fidelity virtual screening previously impractical with flexible docking.
Read the full abstract ▾
All authors Xiangyu Meng, Peng Chen, Mingzhen Li, Jianmin Wang, Sen Wang, Guangming Tan, Weile Jia, Mohamed Wahib, Tao Luo, Xun Wang
Artificial Intelligence
Transformers Struggle to Use Their Emergent World Models: Revisiting the Tower of Hanoi, and the Illusion of Thinking
Devin Pereira and Willem Zuidema
The Tower of Hanoi is a simple planning puzzle that in prior work has proven challenging for large
reasoning models (LRMs). Current models solve the standard formulation of the puzzle, but still struggle with the flat-to-flat variant (where initial and goal states are not restricted to have all rings on a single peg). This paper presents an in-depth study of how both small, in-house
Transformers and large, third-party LRMs solve this task. To understand the failures mechanistically, we first train small
Transformers from scratch on precomputed solution traces. Using a variety of interpretability techniques, we show that these
Transformers develop an emergent world model: a linearly decodable, geometrically faithful representation of the puzzle's state space (the Sierpinski triangle), that is causally involved in solving the puzzles. Second, we return to the large LLMs and apply our techniques to two frontier
reasoning models, Qwen3.6-27B and DeepSeek-R1-Distill-Qwen-32B, that attempt to solve the task through extended chain-of-thought. Surprisingly, we find that both models encode the Sierpinski world model near-perfectly at the end of the
prompt, and yet fail at the majority of tasks when there are more than 3 rings. We locate the source of this failure in the decaying representation of the world model. We probe for the representation at different stages during planning, and establish causality by showing that performance can be improved by injecting the
prompt-time representation at inference. The failure of the models is thus one of maintenance of the required representations, not their absence, and performance is at least partially recoverable. These results thus reframe the reported collapse in performance from prior work: current Large
Reasoning Models build a world model, and then lose it.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from physics.soc-ph
Coordinated incentives in AI-generated misinformation governance
Qin Li, Gui Zhang, Minyu Feng et al. (+2 more)
With the rapid
diffusion of AI-generated content, AI-driven misinformation is becoming increasingly pervasive and difficult to govern, undermining information credibility and social trust. This study models the strategic interdependence among a government regulator, an AI enterprise, and users through a three-party evolutionary game that incorporates heterogeneous rewards and punishments. From the resulting replicator equations, we characterize the evolutionary stability of competing governance and production strategies. The analysis indicates that neither unilateral regulation nor
market incentives alone can effectively curb misinformation. Instead, an evolutionarily stable regime of real-information production arises only when regulatory rewards and punishment intensity, enterprise reputation loss, and user adoption incentives collectively surpass critical thresholds. The findings highlight the need for coordinated and adaptive policy mixes that align regulatory instruments with enterprise behavior and user uptake while managing governance costs.
Read the full abstract ▾
All authors Qin Li, Gui Zhang, Minyu Feng, Matjaz Perc, Attila Szolnoki
Artificial Intelligence
Zhiyuan Liu, Tinghong Ye, Chenghao Liu et al. (+2 more)
Long-horizon
agents accumulate growing contexts during interaction, impairing performance and stability. Compact
memory mitigates this problem by compressing and rewriting the history retained between model invocations. Learning what to retain typically relies on proximal policy optimization (PPO) with final task rewards, but sparse rewards provide little guidance for individual
memory updates. This limitation motivates on-policy
distillation (OPD), which supplies dense teacher supervision on student rollouts. For such supervision to be valid, the teacher must evaluate each sampled action under the same state in which it was generated. However, the context rewriting performed during
memory compression can break this
alignment. When sampled responses are retained and re-encoded for later invocations, flattening the interaction into a persistent history may cause the teacher to score the action under a state that the student never visited during rollout. The action therefore remains on-policy by provenance, but not necessarily by state. We therefore propose
Memory-Aligned On-Policy
Distillation (MemOPD). MemOPD records the inputs and sampled outputs of each model invocation, restores its original
token positions and causal visibility, and packs the reconstructed invocations for efficient teacher scoring. The teacher provides full-vocabulary supervision at the sampled action positions, while PPO preserves the final task objective. Experiments verify state
alignment across several context updates and show that it improves F1 by 7.0% over persistent-history teacher scoring in a matched control. Overall, MemOPD-3B improves F1 over PPO by up to 416.2%, while packing yields up to a 1.63x speedup in actor computation during training. The code for this work is publicly available at: https://github.com/TPssp/MemOPD.
Read the full abstract ▾
All authors Zhiyuan Liu, Tinghong Ye, Chenghao Liu, Yizhuo Li, Songfang Huang
Artificial Intelligence
DocMemo: Dynamic Evidence Discovery via Probabilistic Memory-Guided Retrieval for Multi-Modal Document Understanding
Hanshu Yao, Janfeng Zhong, Niu Lian et al. (+1 more)
Long-document understanding requires locating sparse and heterogeneous evidence across hundreds of pages, yet existing systems remain limited by static
retrieval and fragile cross-round
memory. Mainstream single-round methods commit to a fixed top-$k$ page set at the outset and struggle to recover from early
retrieval errors; recent iterative approaches allow multi-round evidence acquisition, but they do not investigate the propagation mechanism of cross-round states, making it difficult to track the dynamic changes in page relevance. To address these limitations, we propose DocMemo, a
memory-guided framework that formulates long-document
reasoning as dynamic evidence exploration. DocMemo maintains a tri-level
retrieval state consisting of Document Schema
Memory, Page Belief
Memory, and Question Episodic
Memory, which respectively capture structural priors, dynamic relevance estimation, and query-specific
reasoning trajectories. During
reasoning, DocMemo continuously refines cross-round page selection through
Bayesian page belief updating with Thompson sampling, spatial proximity propagation, and structure-aware adaptive-granularity evidence access, while supplementing page-level evidence with fine-grained visual regions. Experiments on 3
benchmarks show that DocMemo achieves state-of-the-art performance and validate the efficacy of structured
memory and dynamic page belief updating. Code is available at https://github.com/Harrygof/DocMemo.
Read the full abstract ▾
All authors Hanshu Yao, Janfeng Zhong, Niu Lian, Jinpeng Wang
Artificial Intelligence
PTQ4SNN: Membrane-Aware Post-Training Quantization for Spiking Neural Networks
Hui Xie, Tong Shi, Haotong Qin et al. (+3 more)
Spiking neural networks (SNNs) enable sparse and event-driven computation, but their low-bit deployment remains incomplete because recurrent membrane states are commonly retained in floating point even after weight quantization. Quantizing these states is challenging because their distributions differ across channels and from the preceding weights, while small perturbations near the firing threshold may alter spike decisions and accumulate over time. We propose PTQ4SNN, a membrane-aware post-training quantization framework that jointly quantizes weights and recurrent membrane states using only a small calibration set. First, a channel-wise Unified Scale Bridge constrains the membrane scale as s_mem,c = s_w,c * 2^k_c, adapting to membrane distributions while enabling shift-compatible scale conversion. Second, Mixed-Precision Bit Allocation assigns 2/4/8-bit precision to membrane channels according to firing activity and quantization sensitivity under an average-bit budget. The framework operates on reusable projection-LIF pairs and supports both convolutional SNNs and spike-driven
Transformers without backbone retraining. Experiments on static and event-based classification and semantic
segmentation show that PTQ4SNN effectively preserves model accuracy under W4 quantization and approximately 4-bit membrane precision.
Read the full abstract ▾
All authors Hui Xie, Tong Shi, Haotong Qin, Aishan Liu, Xiaode Liu, Jinyang Guo
Artificial Intelligence · Cross-listed from cs.RO
AutoIntervene: Calibrated Intervention for Action-Chunking Imitation Learning Policies
Jinhe Tang and Weiming Zhi
Action-chunking visuomotor policies learn from demonstrations and improve temporal consistency by predicting short action sequences rather than single-step commands. Yet perception errors and execution drift can move the
robot outside the demonstration distribution, while the policy continues to produce smooth action chunks that are inconsistent with the observed state. We present AutoIntervene, an online framework that selectively transfers control between an action-chunking policy and an operator during deployment. AutoIntervene evaluates proposed chunks against a visual-action support
memory built from successful task executions, combining visual similarity with consistency between proposed and reference actions. Phase-local support governs policy-to-operator transfer within the current task phase, whereas global support governs the return to policy control after operator recovery. We calibrate separate switching thresholds for the two directions from empirical
quantiles of evaluation-level scores on held-out expert demonstrations, avoiding direct manual tuning of score cutoffs. Intervention segments retained from successful rollouts target learner-induced states and provide corrective supervision for subsequent policy updates. Experiments on real-world bimanual manipulation tasks show higher post-adaptation task success and lower operator-control time than manual intervention.
Videos and additional results are available at https://aus.bot/research/autointervene/.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
Soft Redaction of Image Provenance via Zero-Knowledge Proofs
Muhammad Awan and John Collomosse
Content provenance standards, such as C2PA, are increasingly used to attach signed records of origin, editing history, and rights to digital images. However, provenance transparency can conflict with
privacy – assertions that strengthen trust in an image may also reveal sensitive information about the creator or capture context. We propose soft redaction for image provenance: a mechanism that replaces sensitive provenance assertions with zero-knowledge proofs (ZKPs) of selected properties over hidden data. Our work focuses on distance proofs. We first show how location assertions can support proofs of proximity to a public reference point, using Chebyshev
polynomial approximations within the ZKP proof
circuit. We then extend the approach to L2 distance proofs over biometric
embeddings, enabling
privacy-preserving claims related to likeness to help enforce personality rights with images. Finally, we apply the same distance-proof construction to perceptual hashes (visual fingerprints), supporting an anti-spoofing use case in watermark-based recovery of stripped provenance metadata. Our results demonstrate that ZKPs over image provenance can provide practical soft-redaction capabilities, compatible with C2PA, that may be constructed in seconds and verified in milliseconds.
Read the full abstract ▾
Artificial Intelligence
BONSAI: Evolvability-Guided Tree Search over Skills
Yash Priya Shastri, Anand Eswaran, Adnan Qidwai et al. (+2 more)
A skill is a naturallanguage document that steers a frozen
agent whose weights cannot be updated so any capability the
agent lacks must be supplied in prose Optimising a skill is therefore optimising text against a score and the standard recipe which keeps any edit that raises a heldout score is blind in a specific way a single score cannot tell a document perched on a narrow overfit spike from one resting on a broad plateau even though only the second can still be improved We introduce BONSAI a novel skilloptimisation framework that steers instead by evolvability the capacity of a region of documentspace to keep producing viable variation under further mutation a property biology treats as separate from present fitness BONSAI grows skills as a MonteCarlo search tree in which every child document is a mutation of its parent and descends it under an upperconfidence selection rule whose exploitation term blends a skills own fitness with the fitness of its mutational neighbourhood Because every child is a mutation the mean score recorded beneath a node estimates that neighbourhoods evolvability at no extra cost so the rule concentrates budget on regions that keep improving while its exploration term keeps a currently weak branch in contention BONSAI ships the single bestscoring document it finds at no cost beyond the acceptifbetter loop it replaces With a frozen 30B
agent and averaged over three
benchmarks BONSAI lifts heldout accuracy over the skillfree
agent by 2313 points and improves on two budgetmatched baselines GEPA and SkillOpt by 387 and 397 points respectively
Read the full abstract ▾
All authors Yash Priya Shastri, Anand Eswaran, Adnan Qidwai, Pankaj Thorat, Sachin Joshi
Artificial Intelligence
Unsupervised Adaptation of PDE Foundation Models
Ziye Song, Zhao Wei, Xin Yu et al. (+2 more)
Pretrained partial differential equation (PDE) foundation models can generalize across different equations, but adapting them to unseen PDE systems typically requires dense solution data, which is often expensive or unavailable. To address this limitation, we propose an unsupervised PDE-based finetuning framework that eliminates the need for ground-truth solutions. We first pretrain a neighborhood
attention Transformer on diverse time-dependent PDEs spanning varying spatial scales, yielding transferable representations across heterogeneous equations. In the adaptation stage, we construct a physics-based objective using the PDE residual and boundary conditions, and finetune the model on unseen equations via low-rank adaptation (LoRA). To address the uneven learning across physical quantities in standard LoRA, we introduce NSLoRA, a Newton-Schulz orthogonalized variant that rebalances adaptation. Our method achieves performance comparable to supervised LoRA finetuning without requiring any ground-truth solutions, while consistently outperforming competitive neural operator baselines and recent PDE foundation models across heterogeneous PDE
benchmarks spanning multiple spatial dimensions.
Read the full abstract ▾
All authors Ziye Song, Zhao Wei, Xin Yu, Ivor Tsang, Yueming Lyu
Artificial Intelligence
Not All Problems Are Best Modeled as MILP: A DSL-Centric Framework for Flexible and Accurate Optimization Modeling
Shaofeng Zhang, Hongyuan Su, Qingwen Peng et al. (+4 more)
Solving combinatorial optimization problems (COPs) requires not only efficient
algorithms but also carefully crafted formulations. While recent works have leveraged LLMs to automate optimization modeling, current frameworks predominantly rely on a rigid mixed-integer linear programming (MILP) paradigm. In this paper, we argue that not all problems are best modeled as MILP, as forcing complex domains into linear constraints can induce prohibitive modeling complexity and severely restrict solver flexibility. To address this, we propose OptiDSL, a framework that shifts the focus from rigid MILP formulations to domain-specific
language (DSL) representations. By utilizing LLMs to map natural
language onto standardized, domain-accepted structures, OptiDSL decouples problem formulation from execution. This paradigm enables seamless integration with a diverse library of specialized solvers, ranging from traditional heuristics to modern learning-based methods. Experimental results on the comprehensive
benchmark of 44 COP types show that OptiDSL significantly surpasses MILP-based pipelines, yielding a 51.66% gain in formulation accuracy and a 91.71% decrease in modeling time. Notably, it also outperforms MILP-based pipelines on the existing
benchmark, achieving a 23.09% higher formulation accuracy. Our code is available at https://anonymous.4open.science/r/OptiDSL.
Read the full abstract ▾
All authors Shaofeng Zhang, Hongyuan Su, Qingwen Peng, Zefang Zong, Shengcai Liu, Ke Tang, Yong Li
Artificial Intelligence · Cross-listed from cs.SE
Beyond Text Matching: Towards Reference-Free Evaluation for Human-Oriented Binary Reverse Engineering
Xiuwei Shang, Li Hu, Xiao Jiang et al. (+7 more)
Human-Oriented Binary Reverse Engineering (HOBRE) aims to transform decompiled pseudocode into a more human-friendly representation, thereby reducing the cognitive burden of reverse analysis and improving efficiency. However, reliably evaluating HOBRE outputs remains a fundamental challenge: human evaluation is costly, time-consuming, and difficult to scale, while existing automated metrics either require executable test cases and runtime environments that are often unavailable for real-world binaries, or rely on high-quality source code references that are typically inaccessible and fail to capture semantically equivalent but lexically diverse outputs. Although LLM-as-a-Judge paradigm is naturally well-suited to HOBRE evaluation, its effectiveness remains underexplored. This paper presents the first systematic investigation of the LLM-as-a-Judge paradigm for HOBRE across three representative tasks: function name recovery, binary code summarization, and decompilation optimization. We introduce BinJudgeBench, the first expert-annotated, reference-free evaluation
benchmark based on multi-dimensional human judgment, where LLM-as-a-Judge achieves an average correlation of 63.20% with human judgment, outperforming traditional automated metrics at 35.04%. By analyzing judge configurations across backbone LLMs, prompting strategies, and decoding temperatures, we find that no “one-size-fits-all” configuration exists, as the optimal setup varies across tasks and individual samples. To address this, we propose BinJudge, which employs a lightweight routing mechanism to adaptively select the optimal judge configuration for each task and sample. BinJudge improves correlation with human experts by 4.5%-24.7% and reduces API cost to 0.06$\times$-0.84$\times$ of that of static best configurations, providing a scalable, cost-effective, and high-fidelity automated evaluation scheme for HOBRE.
Read the full abstract ▾
All authors Xiuwei Shang, Li Hu, Xiao Jiang, Jieke Shi, Junda He, Zhou Yang, Shaoyin Cheng, Guoqiang Chen, Weiming Zhang, David Lo
Artificial Intelligence · Cross-listed from cs.LG
Accounting Graph Transformer for Short-History Multi-KPI Forecasting in Small Businesses
Shrutendra Harsola and Vignesh Subrahmaniam
Small businesses often have only 12-24 months of accounting history, yet planning and risk workflows require coordinated forecasts across financial statements. We study joint 12-month
forecasting of 13 income-statement, balance-sheet, cash-flow, and working-capital key performance indicators (KPIs) from 71 monthly ledger series. We introduce the Accounting Graph
Transformer (AGT), which represents each ledger series as a masked
token, exchanges information through typed
attention on a fixed accounting-relation graph, pools target-specific context, and fuses it with a gated three-month recency path. Across 11,993 forecast origins from 1,060 unseen companies, AGT achieves sample-weighted KPI-macro mean absolute error (MAE) $0.6990 \pm 0.0013$ over three independent seeds, compared with $0.7378 \pm 0.0014$ for the strongest baseline, LightGBM. At the pre-specified seed 42, a paired company-clustered bootstrap gives a LightGBM-minus-AGT difference of 0.0395 with 95% confidence interval (CI) $[0.0350,0.0439]$. AGT is best on all 13 KPIs against LightGBM, TimeMixer, and SOFTS in the matched seed-42 comparison, while final-architecture ablations show that relational
attention, accounting
topology, and the recency path each improve validation and test accuracy. On 7,094 additional unseen companies with origins sampled from January-May 2025, AGT obtains 0.7548 MAE versus 0.7694 for SOFTS. A single 5.3M-parameter model produces 156 aligned forecasts without company-specific fitting, providing one
forecasting layer for integrated planning, liquidity, and working-capital analysis.
Read the full abstract ▾
Artificial Intelligence
ZIPBrain: Can EEG Foundation Models Be Faster, Locally Deployable, but Accurate?
Lingwei Li, Yirong Kan, Peng Chen et al. (+3 more)
This work investigates whether Electroencephalograph (
EEG) foundation models (EFMs) can be made faster and locally deployable without sacrificing accuracy.
EEG foundation models are a major trend, offering strong general-purpose representations. However, their computational burden grows quadratically with input length, hindering deployment on resource-constrained scenario, particularly for real-time clinical monitoring.
EEG's low SNR further suggests many of these
tokens are redundant and compressible with little accuracy cost. We propose ZIPBrain, a novel redundancy-aware
EEG token pooling module that leverages this low-SNR characteristic to reduce
token count. Given a
token sequence, ZIPBrain partitions
tokens into redundant and unique groups, then merges each redundant
token with its most similar counterpart in the unique group. Furthermore, ZIPBrain serves as a training-free, plug-and-play module that seamlessly integrates into standard
Transformer encoders with negligible computational overhead. Extensive experiments across multiple
EEG foundation models show ZIPBrain's strong versatility, achieving 1.3%-10.5% average improvement over baselines, while reducing wall-clock inference time by 32.7% (up to 41.8% with CUDA Graph) compared to the original
EEG foundation models.
Read the full abstract ▾
All authors Lingwei Li, Yirong Kan, Peng Chen, Xu Cao, Zheng Chen, Yasuhiko Nakashima
Artificial Intelligence · Cross-listed from cs.CL
An Agentic Hybrid Top-Down and Bottom-Up Approach to Knowledge Graph Generation
Emma Jouffroy, Warren Jouanneau and Marc Palyart
Organizing thousands of unstandardized,
multilingual expertise declarations is a persistent challenge for Human Resources (HR) platforms, directly impacting downstream tasks like accurate talent matching. To address this, we propose a hybrid knowledge graph generation pipeline that grounds a Large
Language Model (LLM) in the Wikidata
multilingual Knowledge Graph (KG) while employing an agentic reflexion pattern to synthesize emerging concepts and their associated metadata. Unlike rigid top-down methods or fragmented bottom-up approaches, our system anchors recognized concepts to stable Knowledge Graph entities while dynamically creating new nodes and relational metadata for unrecognized skills. Executed across five stages, entity reconciliation,
multilingual canonicalization, active curation, deduplication, and the iterative recovery of unmapped concepts, the system autonomously adapts to rapidly evolving, noisy skill mentions across five European
languages. Ultimately, this pipeline provides a highly scalable, explicable, and self-healing framework for generating a comprehensive skills knowledge graph, from which a structured taxonomy is derived, using unstructured, noisy text.
Read the full abstract ▾
Artificial Intelligence
ReQuant: Fixed-Grid Discrete Refinement for Post-Training Quantization
Yongge Ma, Guoan Wang, Feiyu Wang et al. (+5 more)
Post-training quantization (PTQ) is widely used to reduce the
memory and computational cost of large
language models. Existing PTQ methods typically obtain an initial quantized model through heuristic rules or greedy optimization, and once quantization is completed the resulting integer assignments are usually treated as final. This observation motivates a complementary optimization stage within PTQ that keeps quantized weights improvable after an executable quantized model has been produced, while preserving the quantized format. We introduce ReQuant, a backpropagation-free fixed-grid refinement procedure for this stage. Agnostic to the PTQ initializer, ReQuant takes an existing quantized model as a feasible starting point and iteratively revisits its discrete weight assignments on the fixed quantization grid. Accepted updates strictly reduce the mean squared reconstruction error and remain on the original grid. In this way, ReQuant turns the initially fixed PTQ output into an iteratively optimizable discrete solution and serves as a plug-and-play post-processing stage for existing PTQ pipelines. Experiments across diverse model families, bit-widths, and downstream tasks show that ReQuant consistently improves quantized models from heterogeneous PTQ initializers, with especially large gains on simple initializers and lower bit-widths. Notably, ReQuant can refine a simple round-to-nearest initialization across multiple sweeps until it approaches or surpasses GPTAQ under the same quantization format. These results establish ReQuant as a practical complementary stage for further improving existing PTQ pipelines.
Read the full abstract ▾
All authors Yongge Ma, Guoan Wang, Feiyu Wang, Yaoming Li, Qian Zhang, Zihan Yan, Yinjun Han, Tong Yang