Artificial Intelligence · Cross-listed from cs.LG
VStress: Correlation-Aware Auditing and Adaptive Budget Allocation for Repeated Verifiers
Miaobo Hu, Shuhao Hu, Xiaobo Guo et al. (+4 more)
Repeated verifier calls are useful only when they contribute conditional information. We introduce VStress, an auditable replay contract, and VStress-CA, a correlation-aware allocation policy that estimates the conditional marginal information of an unqueried verifier on a sealed calibration split, discounts uncertainty, normalizes by call cost, and stops or abstains when the next call is not informative. The controller freezes its decision and cost ledger before joining the clean oracle; a dependence-shift alarm disables channel preference and falls back to exact-stop. The controlled audit gives the mechanism boundary: at 35% symmetric corruption, majority-5 improves balanced accuracy from 0.6578 to 0.7739, whereas at 65% it loses 0.1226 points. In the matched fixed-budget comparison, breadth, redundancy, and adaptive allocation obtain balanced accuracies 0.6048, 0.6375, and 0.6538, with 3.4216 calls per item and an RLVR score of 0.6417 for VStress-CA. Dependence diagnostics also increase from same-model repeats to cross-family channels, with conditional marginal gains of 0.0126, 0.0462, and 0.0913. These measurements turn correlation from a post-hoc warning into an auditable allocation decision.
Read the full abstract ▾
All authors Miaobo Hu, Shuhao Hu, Xiaobo Guo, Xin Wang, Bokun Wang, Peng Zhang, Daren Zha
Artificial Intelligence · Cross-listed from cs.CR
Controlled Decoding Attacks on Black-Box LLMs
Jesson Wang, Shawn Li, Wei Yang et al. (+4 more)
Manipulating next-
token probabilities during generation can bypass the safety
alignment of large
language models. Existing approaches, however, rely on access to model weights or numerical
token probabilities and therefore do not apply to interfaces that return only sampled text. Reconstructing probabilities from sampled outputs offers a possible alternative, but finite sampling produces sparse and noisy estimates, while repeating this process at every generation step incurs substantial query costs. Our empirical observations suggest that large distributional changes along successful jailbreak trajectories are concentrated at a small subset of positions, motivating selective control. We introduce \method{}, a framework for jailbreaking through text-only continuation interfaces that permit repeated sampling and assistant-prefix continuation. Sample-Based Distribution Reconstruction combines sampled outputs with a prior over unobserved actions to obtain a usable control signal. Risk-Gated Residual Control uses the evolving response prefix to decide when to reconstruct and modify the distribution, concentrating sampling costs at selected positions. Speculative Multi-
Token Execution further amortizes target calls by verifying and accepting draft prefixes that require no intervention. Across four target endpoints and three
benchmarks, \method{} achieves the highest mean score most comparisons against baselines.
Read the full abstract ▾
All authors Jesson Wang, Shawn Li, Wei Yang, Franck Dernoncourt, Ryan A. Rossi, Charith Peris, Yue Zhao
Artificial Intelligence · Cross-listed from cs.DC
Purlin: Separating Orchestration from the Datapath of Collectives
Osayamen Jonathan Aimuyo, Swapnil Gandhi and Christos Kozyrakis
Distributed inference depends on GPU collective communication that must keep pace with evolving hardware and specialized workloads. However, existing works often couple the semantics, orchestration (where and when data moves), and datapath (how data moves) of collective communication. This coupling makes it costly to adopt new hardware mechanisms and customize communication for applications. We present Purlin, a scale-up communication framework that separates these concerns. At the top of Purlin, we specify collectives as a naming of an input and output layout and a copy or reduction operation. In the middle, we introduce a shared orchestration protocol, Stage, Notify, And Consume (SNAC), which derives coordination from these specifications. Below SNAC sits a hardware-specific datapath we call Atom, which implements two key data movement primitives for collectives: copy and reduce. This separation lets us customize collectives and adopt new hardware mechanisms while reusing orchestration via SNAC. We evaluate Purlin on A100, H200, and B200 GPUs. Across seven collectives, Purlin achieves latency speedups of up to 5.14x and bandwidth improvements of up to 4.50x over baselines. Integrated into SGLang, Purlin improves offline LLM serving throughput and interactivity by 1.13x on average and up to 1.37x over baselines. For online LLM inference, Purlin improves interactivity by 1.26x on average and up to 2.85x, with the largest gain occurring under overload. For
diffusion image generation, Purlin reduces end-to-end latency by up to 1.13x.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
ER-JEPA: Experience Replay Improves Joint-Embedding Predictive Learning in Language Models
Jingnan Pu, Zi-En Fan and Feng Lian
Large
language models (LLMs) excel at
token-level generation but may learn undesirable abstract semantics and lack comprehensive perception. LLM-JEPA mitigates this by aligning different views of the same underlying knowledge via a joint-
embedding predictive architecture (JEPA). However, strong
alignment does not necessarily lead to accurate, stable predictions. To address this, we propose ER-JEPA, which adds an episodic replay path to LLM-JEPA. ER-JEPA stores training pairs in a
memory. At each step, it stores and retrieves relevant data to provide additional supervision. This enables learning from both the current batch and stored training pairs, providing additional supervision for
token prediction and representation
alignment. Experiments across multiple
datasets (NL-RX, GSM8K, Spider, and NQ-Open) demonstrate that ER-JEPA consistently outperforms LLM-JEPA.
Read the full abstract ▾
Artificial Intelligence
Dual-Channel Robust Group-Relative Policy Optimization via Advantage and Sequence-Weight Estimation
Zhongyi Li, Wan Tian, Xiang Xu et al. (+4 more)
Group-relative policy optimization relies on reward-derived advantages and sequence-level likelihood weights, both of which can be sensitive to localized outliers. Extreme rewards can collapse the contrast among clean responses after group normalization, while
token-level log-ratio perturbations can alter sequence weights and clipping decisions. We introduce RoVR-GSPO, a dual-channel robust optimizer that addresses these failure modes separately. Its reward channel combines robust reference estimation with bounded residual credit, while its ratio channel uses differentiable SoftRoVR aggregation to construct robust sequence weights. We provide stability and efficiency analyses for both channels. Experiments on mathematical
reasoning, long-context summarization, and tool-call annotation show consistent improvements over GSPO, while controlled perturbation studies demonstrate stronger robustness to reward contamination and
token-ratio anomalies.
Read the full abstract ▾
All authors Zhongyi Li, Wan Tian, Xiang Xu, Yutian Xiao, Yikun Ban, Yijie Peng, Fuzhen Zhuang
Artificial Intelligence · Cross-listed from cs.LG
Safe-by-Design Learning via Energy-based Neural Networks
Simone Betteti, Morteza Lahijanian and Luca Laurenti
Learning neural-network models of dynamical systems with safety guarantees is a fundamental requirement for their deployment in safety-critical settings. Safety is commonly established by proving the invariance of a desired subset in state-space, ensuring that every trajectory initialized in this subset remains confined to it for all time under admissible inputs. Existing frameworks, however, either rely on computationally expensive post-hoc verification or employ safety-enforcing mechanisms without formal correctness guarantees. In this paper, we introduce a novel neural architecture grounded in energy-based modern Hopfield networks to guarantee safety-by-design while retaining sufficient expressiveness to model complex nonlinear dynamics. Specifically, we integrate modern Hopfield networks with a port-
Hamiltonian neural ODE, enabling by design the construction of barrier functions yielding explicit admissible-input sets and quantitative robustness radii. Across several
benchmarks, including an 12-dimensional nanodrone model, our framework achieves state-of-the-art performance while producing certified invariant sets that are more robust to external solicitations than comparable existing approaches.
Read the full abstract ▾
Artificial Intelligence
SCA: Spatial Credit Assignment for Reinforcement Learning of GUI Agents
Shengtian Yang, Ziyu Xiong, Kaibing Yang et al. (+6 more)
GUI
agents automate tasks on digital devices by grounding
language instructions in visual interfaces. Existing group-relative reinforcement learning improves GUI action prediction by comparing the rewards of multiple responses sampled from the same GUI state. However, binary evaluation treats spatially different failed clicks as identical and provides no relative signal when all sampled clicks fail. To address these limitations, we propose Spatial Credit Assignment (SCA), which uses the screen coordinates of sampled clicks to refine group-relative credit. Specifically, SCA predicts each held-out response's reward from the other responses in groups containing both successes and failures, then uses the prediction residual to adjust credit. When all sampled clicks fail, SCA instead orders them by distance to the annotated target. These spatial references are used only to construct the training update; the deployed policy remains unchanged. We evaluate whether this correction improves the policy update itself by comparing its error and directional
alignment with the exact return gradient in a controlled synthetic study. Across GUI grounding and offline action-prediction
benchmarks, SCA improves grounding across professional domains and achieves the strongest results among reinforcement-fine-tuned models on most action-prediction metrics, with consistent gains across the reported GUI suites.
Read the full abstract ▾
All authors Shengtian Yang, Ziyu Xiong, Kaibing Yang, Guangfeng Cai, Yewen Li, Peng Jiang, Gai Kun, Qingpeng Cai, Lei Feng
Artificial Intelligence · Cross-listed from cs.CV
WeLike2Party! In-Context Motion Transfer for Multi-Human Image Animation
Sangeyl Lee, Seunghyun Shin, Seungho Park et al. (+2 more)
Human image animation aims to transfer motion from a driving
video to subjects in a reference image. Despite remarkable progress in
video generation, achieving high-fidelity animation of multiple interacting subjects remains a challenge. Many existing approaches rely on explicit motion representations such as 2D skeletons or parametric body meshes and struggle to preserve identity-motion binding under inter-person occlusion. To address this limitation, we propose WeLike2Party, a multi-human animation framework built on direct in-context
video conditioning without explicit pose or mesh extraction at inference. We further introduce Reference Asymmetric RoPE Conditioning to preserve fine-grained appearance details, and Identity Binding Supervision to associate each reference identity with its intended motion trajectory. To support cross-identity training, we construct MotionTwin, a large-scale synthetic
dataset comprising 14.4K cross-identity
video pairs with shared subject and camera motions, totaling 84.3 hours of photorealistic
video. We additionally present MotionTwin-Bench, a cross-identity
benchmark specifically designed to evaluate subject-level visual fidelity and identity-motion binding. Extensive experiments on MotionTwin-Bench and real-world
videos demonstrate that WeLike2Party outperforms recent state-of-the-art methods in subject-level visual fidelity, identity-motion binding, and overall perceptual quality, particularly in multi-person interactions with substantial occlusion.
Read the full abstract ▾
All authors Sangeyl Lee, Seunghyun Shin, Seungho Park, Wooseok Jeon, Hae-Gon Jeon
Artificial Intelligence
CoEM: Empowering Long-Context Reasoning with Commit-on-Evidence Memory
Jingguang Li, Yebo Wu, Zuyi Guo et al. (+7 more)
Long-context
reasoning is essential for complex and long-horizon tasks, yet the performance of large
language models (LLMs) degrades as context length increases. Recent approaches address this by processing input chunk by chunk while maintaining a bounded textual
memory in model context. However, premature information compression can discard critical details essential for subsequent
reasoning. In this paper, we introduce Commit-on-Evidence
Memory (CoEM), which learns when to convert source evidence into compact
memory facts. Specifically, under a fixed context-
memory budget, CoEM preserves potentially useful source excerpts verbatim in a pending set, allowing subsequent context to clarify their relevance before irreversible compression. As new context arrives, a learned policy revisits each pending excerpt and decides whether to promote it to the committed
memory, retain it for further consideration, or discard it. A frozen verifier ensures proposed facts are accepted only if supported by retained excerpts and current context. To further guide effective
memory management, we train this policy using reinforcement learning by combining fine-grained, step-level evidence rewards with final answer rewards. Extensive experiments demonstrate that CoEM consistently improves long-context
reasoning. When evaluated on 6,400 documents long-context input, CoEM outperforms the strongest
memory baseline by 10.4-11.4 F1 points on Qwen3.5-9B. Code repository: https://github.com/benmagnifico/CoEM.
Read the full abstract ▾
All authors Jingguang Li, Yebo Wu, Zuyi Guo, Kailang Ma, Xianjie Dai, Han Zheng, Benwang Chen, Li Li, Can Rong, Heye Huang
Artificial Intelligence
VLALight: A Vision-Language-Action Model for Traffic Signal Control
Pan Zhang, Siqi Lai, Kemu Dong et al. (+1 more)
Traffic signal control (TSC) is essential for improving urban mobility and reducing congestion. Although roadside cameras are widely deployed at signalized intersections and provide rich visual observations of evolving traffic, existing TSC methods typically rely on manually engineered traffic states or separate perception modules, creating a gap between physical observations and control decisions. We present VLALight, the first
vision-
language-action (VLA) model for end-to-end traffic signal control from multi-view roadside
videos. VLALight directly maps visual observations to coordinated signal actions through multi-target spatiotemporal traffic
reasoning and
topology-aware cooperative perception across intersections. To establish this capability, we develop a two-stage supervised cold-start training strategy for visual traffic understanding and signal decision-making, followed by cooperative agentic reinforcement learning that jointly optimizes local control and network-wide traffic efficiency. Furthermore, VLALight introduces adaptive fast and slow
reasoning modes, enabling the policy to allocate deeper
reasoning only when additional deliberation provides sufficient control benefits. Through balanced mode-aware rollouts and relative advantage optimization, VLALight learns to trade off decision quality and inference cost. Extensive experiments on seven real-world traffic-flow
datasets across three urban networks demonstrate that VLALight consistently outperforms transportation-based, RL-based, and LLM/VLM-based baselines. Ablation studies validate the effectiveness of cooperative perception, network-level optimization, and adaptive
reasoning. These results demonstrate the potential of VLA models for real-world physical traffic control. Our project is available at https://github.com/usail-hkust/VLALight.git.
Read the full abstract ▾
All authors Pan Zhang, Siqi Lai, Kemu Dong, Hao Liu
Artificial Intelligence
Learn from the Gap: Differential-Aware Advantage Pruning with Adaptive Rollout Sampling for GRPO
Jiahua Yang, Zhiwei Yang, Xianpeng Zhang et al. (+7 more)
Recently, Group Relative Policy Optimization (GRPO) and its variants have been developed for policy optimization and demonstrated notable performance gains. However, these methods usually incur substantial computational overhead due to per-question multi-rollout sampling and repeated per-
token probability evaluation across rollouts. Furthermore, low-information or highly homogeneous trajectories can degrade downstream learning signal efficiency, hindering model optimization and limiting final performance. To address these issues, we propose FastRL, a novel plug-and-play reinforcement learning framework that simultaneously improves training efficiency and the effectiveness of policy learning. Specifically, 1) We introduce an advantage-aware
pruning strategy to selectively preserve high-advantage trajectories while maximizing inter-trajectory gradient diversity. 2) Then, we design an adaptive rollout sampling mechanism to dynamically adjust the sampling scale across different training stages based on historical
pruning distributions, balancing exploration adequacy and computational efficiency. Experiments demonstrate that FastRL can be seamlessly integrated into GRPO, DAPO, and GSPO variants, achieving an average 2.07$\times$ training speedup on Geometry3K and GeoQA8K-R1V, along with an approximately 1.64% improvement in average accuracy on visual
reasoning benchmarks. Source codes will be available at https://github.com/Nicozwy/FastRL.
Read the full abstract ▾
All authors Jiahua Yang, Zhiwei Yang, Xianpeng Zhang, Dongyu Chen, Xing Chen, Tianhuang Su, Haonan Lu, Quanlong Guan, Kai Tang, Chuangchuang Wang
Artificial Intelligence
Neuro-Symbolic Computer Use: Learning Reusable Policies for Reliable and Efficient Execution
Hyewon Suh, Thanh Minh Nguyen, Chih-Lun Lee et al. (+5 more)
Many computer tasks recur: the same workflow runs many times, with new inputs and from different starting states. Current computer-use
agents re-plan every step of every run, which makes them costly and unreliable on such tasks. We introduce neuro-symbolic computer use, in which a recurring workflow is executed by a learned policy rather than re-derived by an
agent on each run. The policy fixes the decisions that are stable across runs (ordering, variables, loops, and branches) in executable code, and delegates observation-dependent decisions, such as grounding and state checks, to neural models. We learn these policies with neuro-symbolic policy iteration: starting from one
agent trajectory, it executes the policy, diagnoses failures with task-completion and step-level judges, and revises the code with a coding model informed by an
agent's continuation from the point of failure, without access to the
benchmark evaluator. Iterating on generated parameter and initial-state variants makes the policy reusable, and a pre-action verifier guards each state-mutating step at deployment. On OSWorld-Verified and ScienceBoard, the learned policies achieve the highest Pass^3 of all methods in all four settings, 3.6-15.8 points above the base
agent, while cutting per-run cost by 15-217$\times$ and latency by 3.4-5.1$\times$. On OSWorld-Verified, policies built only on variants transfer to the held-out original tasks, exceeding AutoRPA by 8.6-17.5 points in Pass^3.
Read the full abstract ▾
All authors Hyewon Suh, Thanh Minh Nguyen, Chih-Lun Lee, Darrow Hartman, Lizhao Liu, Xin Eric Wang, Ang Li, Jiachen Yang
Artificial Intelligence · Cross-listed from cs.LG
State Transport Routing for Short-horizon Adaptation in Multi-horizon Photovoltaic Forecasting
Xu Yuqing, Zhou Liguo, Sun Ze et al. (+2 more)
Recent power measurements provide valuable information for photovoltaic(PV) power
forecasting, but directly extrapolating short-term trends can introduce substantial errors over longer forecast horizons. To address this challenge, we propose state transport routing (STR), a lightweight adapter that refines the predictions of a frozen
forecasting model. STR combines the original forecast with two complementary trajectories derived from the latest measured power level and its recent trend. A horizon-conditioned router adjusts their contributions over the first 120 min, while leaving subsequent predictions unchanged. Experiments on four public PV
datasets show that STR consistently outperforms a parameter-matched residual adapter. On PVDAQ, the same approach improves five neural
forecasting backbones, reducing all-horizon normalized mean absolute error by 0.0201-0.2364 percentage points, with paired 95% confidence intervals excluding zero. No reliable improvement is observed for LightGBM. These findings demonstrate the potential of structured state adaptation to improve short-term
forecasting across different neural architectures without retraining the underlying models or altering their longer-horizon predictions.
Read the full abstract ▾
All authors Xu Yuqing, Zhou Liguo, Sun Ze, Yu Lei, Jiang Mingming
Artificial Intelligence
PrecogUI: Proactive GUI Agents via Pre-cognitive Simulation and Experience Retrieval
Bin Kang, Jiarui Ouyang, Li Jiang et al. (+2 more)
Existing reactive Graphical User Interface (GUI)
agents often fail in long-horizon, dynamic scenarios, where unexpected disturbances trigger
attention-diverting and cascading failures. To address this, we propose PrecogUI, a pre-cognitive architecture that shifts the paradigm from reactive execution to proactive decision-making. Specifically, we design a Proactive Experience Pool (PEP), which caches recurring anomaly and success patterns as "state-action-result" tuples in a dual-
memory repository. Furthermore, we introduce a Proactive Simulation Executor (PSE) that learns to forecast the next symbolic UI layout given a candidate action, enabling early anomaly avoidance and ranking candidate actions by predicted reliability. Finally, a Pre-cognitive Execution Controller (PEC) fuses these priors and predictions, prioritizes handling of foreseen anomalies, and ensures execution robustness through a closed-loop error correction mechanism. For robust evaluation, we develop AutoTraj, an automatic data-generation engine, to construct InterfereBench, a
benchmark for long-horizon tasks with strong disturbances. Experiments demonstrate that PrecogUI surpasses state-of-the-art methods on InterfereBench while maintaining competitive performance on public
benchmarks. The code will be publicly available.
Read the full abstract ▾
All authors Bin Kang, Jiarui Ouyang, Li Jiang, Bin Chen, Zhuotao Tian
Artificial Intelligence · Cross-listed from cs.RO
AeroManip-VLA: Scalable Vision-Language-Action Learning for Aerial Manipulation with RL-Generated Demonstrations
Rui Huang, Yanlin Mu, Lidong Li et al. (+3 more)
Aerial manipulators extend robotic manipulation into 3D workspaces that are difficult for ground-based
robots to access, creating new opportunities for general-purpose manipulation. However, extending
Vision-
Language-Action (VLA) models to aerial
robots introduces distinct challenges due to the tight coupling between manipulation and flight, continuously changing observations, and safety-critical physical interactions. These challenges demand diverse training data and systematic policy evaluation, yet collecting demonstrations and evaluating policies directly on physical aerial platforms are costly, difficult to scale, and hard to repeat under controlled conditions. We present AeroManip-VLA, a scalable
benchmark for aerial VLA data generation and policy evaluation. AeroManip-VLA provides a GPU-accelerated simulation framework with low-level payload-aware flight and manipulation control in massively parallel environments. Building on this framework, we combine reusable reinforcement learning policies with expert task rules to automatically generate demonstrations without human teleoperation across diverse objects, environments, and randomized initial conditions. The generated data include basic skills such as grasping and placing, as well as long-horizon tasks that require both
navigation and manipulation. We further introduce automated event labeling and trajectory categorization to filter demonstrations. These mechanisms enable fine-grained analysis of task progress, behavioral outcomes, and safety-related failures. Finally, we evaluate a range of imitation learning and VLA baselines across different task settings, revealing their performance characteristics and failure modes. Together, AeroManip-VLA enables scalable aerial manipulation data generation, structured trajectory analysis, and systematic VLA evaluation in simulation prior to real-world deployment.
Read the full abstract ▾
All authors Rui Huang, Yanlin Mu, Lidong Li, Yucong Wang, Zichen Yan, Lin Zhao
Artificial Intelligence · Cross-listed from cs.CL
BaLEEN: Biasing with Latent Encoded Entities for Context-Aware ASR
Chihiro Taguchi, Yotaro Kubo and Rujikorn Charakorn
Transcribing domain-specific entities and rare proper nouns remains a major challenge in automatic
speech recognition (ASR). In this paper, we propose BaLEEN (Biasing with Latent Encoded Entities), a lightweight, hypernetwork-based framework for dynamic contextual adaptation without fine-tuning the underlying ASR model. BaLEEN encodes variable-length contextual keywords using a pretrained
language model, compresses them into a fixed sequence of latent vectors via a Perceiver bottleneck, and injects context-dependent bias vectors directly into the intermediate encoder representations of the ASR model. Because both the
language model and the backbone ASR model remain entirely frozen during training, BaLEEN operates as a plug-and-play adapter that incurs zero computational overhead at inference time when context biases are precomputed. We evaluate our method on a CTC-based ASR model using a Wikipedia-derived corpus with annotated named entities and synthetic
speech. Experimental results demonstrate that BaLEEN reduces keyword miss rate by 8.7% on the test set relative to the unbiased baseline while simultaneously improving overall word error rate by 21% and character error rate by 28%.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
MultiTalk: Scaling Full-Duplex Speech Models to Long, Multi-Party, Bilingual Conversation
Ke Wang, Houxing Ren, Zimu Lu et al. (+4 more)
End-to-end full-duplex
speech models have brought open-source machine conversation closer to human-like interaction, yet existing systems remain limited in two intertwined dimensions: long-context robustness and multi-party interaction. Real-world scenarios such as meetings, group lessons, and social-
robot reception require a single model to track, contextualize, and respond to multiple speakers over extended durations. Progress is constrained by both data and evaluation: open multi-party
speech corpora remain small and are not designed for codec-frame-level full-duplex modeling, while existing long-audio
benchmarks focus on passive listening and
speech-to-
speech benchmarks are mostly short and dyadic. We extend the Moshi paradigm jointly along the long-horizon and multi-party axes in English and Chinese. First, we release 57.6k hours of synthetic training data ($\href{https://huggingface.co/datasets/MultiTalk/MultiTalkPT}{MultiTalkPT}$ and $\href{https://huggingface.co/datasets/MultiTalk/MultiTalkFT}{MultiTalkFT}$) for long-form, multi-party, English-Chinese full-duplex dialogue, with controllable length, participant count, turn-taking, overlap, backchannels, interruptions, addressee shifts, and long-range coreference. Second, we introduce $\href{https://huggingface.co/datasets/MultiTalk/MultiTalkBench}{MultiTalkBench}$, built from real human recordings, for evaluating long-form, multi-party, bilingual full-duplex dialogue. Conversations average 32.6 minutes and include probes for long-range entity tracking, topic coherence, and addressee selection. Third, we train a bilingual Moshi-style model that sustains coherent multi-party English-Chinese conversations over extended durations and substantially outperforms open-source baselines including Moshi, MiniCPM-o-4.5, and Qwen3-Omni-30B-A3B-Instruct on MultiTalkBench.
Read the full abstract ▾
All authors Ke Wang, Houxing Ren, Zimu Lu, Yunqiao Yang, Zhuofan Zong, Mingjie Zhan, Hongsheng Li
Artificial Intelligence · Cross-listed from quant-ph
Digital Twin Modeling of Quantum Dynamical Systems: Dissipative Quantum Reservoir Computing
Abhijit Sen, Bikram Keshari Parida, Shital Chauhan et al. (+2 more)
Modeling the response of driven many-body
quantum systems from input–output data is difficult: the dynamics are nonlinear, history dependent, and expensive to simulate as system size grows. A paradigmatic case is High-Harmonic Generation~(HHG), where a strong field drives a medium to emit radiation that is highly sensitive to the drive and encodes long-range temporal correlations. We introduce a dissipative
quantum reservoir computing~(DQRC) framework that builds a digital twin of such a system, learning its input–output map directly from data while the reservoir—itself a small open
quantum system—stays fixed and only a classical readout is trained. We show that a minimal single-
qubit reservoir reproduces the HHG response of a substantially larger Ising
spin chain, and on a representative
benchmark matches and on several metrics surpasses previously reported temporal convolutional and Kolmogorov–Arnold-network models, while using a simpler, physically realizable system. A single fixed reservoir further generalizes across a broad range of drives, indicating that it learns a shared physical response structure rather than memorizing trajectories. These results establish dissipative
quantum reservoirs as compact, physically grounded digital twins for nonlinear,
memory-dependent
quantum dynamics. Code is available at \href{https://github.com/AI-and-
Quantum-Computing/DQuRC}{https://github.com/AI-and-
Quantum-Computing/DQuRC}.
Read the full abstract ▾
All authors Abhijit Sen, Bikram Keshari Parida, Shital Chauhan, Mahima Arya, Denys I. Bondar
Artificial Intelligence
STAR-GRPO: Canonical Anchoring and Reliability-First Advantages against Representation-Dependent Reward Hacking
Wan Tian, Zhongyi Li, Xiang Xu et al. (+3 more)
Reward hacking occurs when policy optimization exploits a brittle reward interface or an overly permissive proxy objective, improving the training score without improving the underlying response quality. This phenomenon is amplified in group-relative policy optimization: an unsupported reward can shift the group baseline and alter the updates of other rollouts, while post-hoc or purely relative weighting cannot represent group-wide uncertainty. We propose Self-Tuned Anchored Reliability Group-Relative Policy Optimization (
STAR-GRPO), a reliability-first advantage
estimator based on paired assessments of the same rollout.
STAR separates the quality signal from its learning influence: score disagreement determines rollout reliability, relative reliability enters a self-tuned robust location–scale fit before group normalization, and absolute group reliability attenuates the resulting bounded advantage. The analysis establishes coordinate and second-moment bounds, characterizes exact centering through the weighted location equation, and gives reliability-dependent attenuation guarantees for outlying rewards. We evaluate
STAR-GRPO in two complementary reward-hacking regimes. In
token-interface exploitation,
STAR prevents runaway optimization of the deployed-interface score while improving the canonical quality signal. In rubric-proxy overoptimization for medical
reasoning,
STAR improves independent semantic evaluation, narrows the proxy–judge discrepancy, and reduces overclaim while optimizing the same task proxy. Together, these results show that reliability-first normalization offers a principled way to limit unsupported reward influence on both group baselines and policy updates, while retaining the task reward as the optimization target.
Read the full abstract ▾
All authors Wan Tian, Zhongyi Li, Xiang Xu, Minhao Zou, Yijie Peng, Fuzhen Zhuang
Artificial Intelligence
HorizonFlow: Variable-Length Planning for Offline Goal-Conditioned RL
JunHyeok Oh, Zian Jang and Byung-Jun Lee
Recent advances in generative planning have made trajectory inpainting a promising approach to offline goal-conditioned reinforcement learning. However, these methods typically specify the planning horizon before generating plan content, even though the appropriate horizon depends on the route itself. A horizon that is too short can force infeasible transitions, whereas one that is too long can introduce redundant motion. We introduce HorizonFlow, a hierarchical planner that treats plan length as an output of generation rather than a prescribed input. Its subgoal route planner guides its action-prefix controller through a sequence of latent subgoals. Both components combine insertion-based generation with flow matching to jointly generate continuous plan content and length, using the partially generated plan to guide
token insertion. HorizonFlow reuses the resulting length information to select candidates and steer generation toward shorter plans without a separate learned value model. Across Maze2D, Multi2D, and OGBench
navigation and visual manipulation
benchmarks, HorizonFlow achieves the highest average performance among the compared methods.
Read the full abstract ▾
Artificial Intelligence
Harness Evolution as Learning: Approximation, Generalization, and Optimization Limits of Self-Improving Personal Agents
Zeyu Gan, Zixuan Gong and Yong Liu
As the capabilities of large
language models (LLMs) continue to advance, increasing
attention is turning to how to translate their abilities into useful behavior. Personal
agents bring this question into everyday settings, where models are expected to serve individual users and continually adapt to their preferences. With the underlying model held fixed, such adaptation relies on harness engineering: designing and evolving the surrounding layer that manages context,
memory, tools, and execution. Despite rapid progress, the factors governing effective harness
evolution remain insufficiently understood. To narrow this gap, we investigate three central questions concerning harness architecture, harness scale, and self-
evolution algorithms through complementary empirical and theoretical analyses. Empirically, we introduce a preference-oriented
benchmark and systematically characterize the capabilities and limitations of personal
agents associated with these three dimensions. Theoretically, we formulate harness
evolution as a learning problem and explain these phenomena through approximation, generalization, and optimization errors. Analyses of reachable policies, capacity under finite interaction evidence, and biased update dynamics provide theoretical accounts of the observed phenomena. Together, these results offer a unified perspective on the limits of personalization through harness
evolution and inform future harness design.
Read the full abstract ▾
Artificial Intelligence
Beyond Sub-Gaussian Detector Scores: Robust Weighted Profile-Loss Change Point Detection for Human-LLM Text Segmentation
Wan Tian, Zhongyi Li, Yawen Li et al. (+3 more)
Mixed human-LLM documents require locating authorship transitions from detector scores whose reliability varies across text units. Existing weighted mean contrasts are vulnerable to extreme scores, while directly replacing means with robust centers obscures how a misplaced boundary changes the population objective. We propose Robust Weighted Profile-Loss Change Point Detection (RWCP), which combines capped reliability weights, Huber profile gains, and narrowest-over-threshold search in reliability coordinates. Our key analysis expresses the population gap between a true and a displaced split as a merge cost, avoiding a closed-form solution for the nonlinear center of a mixed segment. Under explicit
curvature, spacing, and dependence conditions, core RWCP recovers the number of changes and localizes their boundaries; its quadratic-loss limit recovers squared weighted CUSUM. We also study RWCP-R, a separately evaluated decoder that shares source centers across nonadjacent passages. Across five retrospective cached-score
benchmark families, core RWCP reduces family-macro WindowDiff by 17.6% relative to weighted change-point detection, and RWCP-R lowers it further. Boundary recovery improves most clearly for isolated changes, while both fixed configurations miss changes in collaborative and densely alternating text.
Read the full abstract ▾
All authors Wan Tian, Zhongyi Li, Yawen Li, Rui Zhang, Yijie Peng, Fuzhen Zhuang
Artificial Intelligence
WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents
Bo Mao, Hang He, Linting Wang et al. (+17 more)
Recent efforts to scale tool-use post-training have largely centered on the synthesis of executable environments, which constitute only one component of a broader agentic interaction system comprising the environment, task,
agent harness, and evaluator. Scaling environments in isolation, however, does not guarantee commensurate gains in model performance, because reliable learning signals depend on coherent interactions among all components of the agentic interaction system. To address this problem, we introduce WEFT (Whole-system
Evolution For Tool-use Post-training), which couples scalable agentic interaction system construction, execution-driven self-
evolution, and stable post-training. WEFT scales agentic interaction system construction across environment breadth, task complexity, and interaction diversity. Execution-driven self-
evolution iteratively uses execution traces and state evidence to attribute failures and revise the responsible components, with fresh rollouts evaluating the changes and providing evidence for subsequent
evolution rounds. For stable post-training at scale, WEFT addresses both optimization and execution reliability: prefix-preserving sampling retains verified progress and atomic-turn credit assignment localizes learning signals, while MegaMCP maintains isolated, recoverable state across concurrent rollouts over shared tool services. Extensive experiments across various models and
benchmarks demonstrate the effectiveness of WEFT for tool-use post-training. WEFT-8B and WEFT-14B outperform all evaluated matched-size environment-scaling baselines on BFCL V4, $\tau^2$-Bench, and Claw-Eval. In particular, WEFT-14B improves over
Agent-World-14B by 6.41, 2.23, and 12.27 percentage points. WEFT-35B-A3B further extends these gains to more challenging long-horizon workflow
benchmarks, including Toolathlon-Verified and AutomationBench.
Read the full abstract ▾
All authors Bo Mao, Hang He, Linting Wang, Lizhi Lin, Maosen Zhou, Guanming Liu, Jinxiu Liu, Tianyu Huai, Chaoyun Zhang, Bingxuan Li, Kepeng Lei, Guanting Dong, Zhou Shao, Rui Zheng, Hang Yan, Jie Zhou, Chengcheng Wan, Tao Gui, Liang He, Xipeng Qiu
Artificial Intelligence · Cross-listed from cs.CR
SKILLLITE: Evidence-Guided Malicious Skill Auditing with Compact LLMs
Haoran Ou, Gelei Deng, Xuanye Zhang et al. (+3 more)
As LLM-based
agents perform increasingly complex tasks,
Agent Skills have emerged as a flexible mechanism for extending their capabilities. An
Agent Skill packages task-specific instructions with executable components and auxiliary resources to provide specialized functionalities. However, the growing adoption of third-party Skills introduces a new supply-chain attack surface. Malicious Skills can embed harmful behaviors that abuse
agent privileges and compromise the
agent execution environment or accessible resources. Although recent LLM-based malicious Skill
auditing approaches have achieved promising performance, they often rely on capable commercial LLMs. How to achieve effective
auditing with compact, locally deployable LLMs in security-sensitive and resource-constrained settings remains largely unexplored. Our investigation reveals that compact LLMs struggle to identify malicious behaviors hidden in complex Skill packages. This difficulty arises from both the implicit nature of such behaviors and the limited
reasoning capacity of compact LLMs. To address these challenges, we propose SKILLLITE, an evidence-guided agentic framework for malicious Skill detection. SKILLLITE effectively extracts security-relevant behaviors and infers the intended functionality from complex Skill packages. It then employs a compact LLM to assess the maliciousness of the Skill based on the observed behaviors and their functional context. Experiments show that SKILLLITE improves malicious Skill detection across different compact LLM backbones and outperforms existing representative
auditing baselines. Its effectiveness generalizes to behaviorally confirmed in-the-wild malicious Skills. Meanwhile, SKILLLITE maintains a low inference latency, supporting its practical deployment.
Read the full abstract ▾
All authors Haoran Ou, Gelei Deng, Xuanye Zhang, Wenbo Guo, Tianwei Zhang, Kwok-Yan Lam
Artificial Intelligence
State Trace Rationale As Auxiliary Task in Reinforcement Learning
Muhammad U. Nasir, Alex Vogt, Steven D. James et al. (+1 more)
We propose STRAT, an auxiliary task that trains deep reinforcement learning (RL)
agents to predict a short textual trace of their own state. Inspired by human spatial
navigation, the description combines landmark, route, and survey knowledge, tracking the
agent's position, inventory, goals, and immediate progress. Environment rules generate this text online without human labelling. Our method adds a single auxiliary head to a standard policy. Across 60 sparse-reward XLand-MiniGrid tasks, STRAT solves complex environments where standard RL fails outright, while compacting state representations and preventing rank collapse. Beyond performance gains, the predicted trace provides a readable account of
agent beliefs at every step for no extra cost.
Read the full abstract ▾
All authors Muhammad U. Nasir, Alex Vogt, Steven D. James, Julian Togelius
Artificial Intelligence · Cross-listed from cs.CR
Safer Content or Firmer Refusals? A Hybrid Perturbation Defense for Alignment under Harmful Fine-tuning
Muhammad Zeeshan Akram, Mufid Kamel Marican, Anvesh Reddy Yenugu et al. (+2 more)
Fine-tuning-as-a-service lets users adapt a safety-aligned
language model to their own data, but it also creates a harmful fine-tuning attack surface: a small amount of harmful data mixed into an otherwise benign fine-tuning set can degrade the model's
alignment. Two recent
alignment-stage defenses address this problem at different levels of the model. Vaccine improves the robustness of hidden
embeddings to the representation shifts induced by harmful fine-tuning, whereas Booster simulates harmful weight updates and attenuates their effect during
alignment. We investigate whether these mechanisms are complementary and propose VaccineBooster, a single
alignment procedure that combines
embedding perturbation and weight-level gradient attenuation within each training step. On Llama-2-7B aligned with BeaverTails and then attacked through poisoned fine-tuning, VaccineBooster achieves the lowest OpenAI moderation score among the compared defenses, 0.315, while a Booster-Only variant retains the highest post-attack refusal rate, 50%. Together with ablations over the
embedding-perturbation and gradient-attenuation strengths, these results indicate a trade-off:
embedding perturbation primarily reduces flagged harmful content, whereas gradient attenuation primarily preserves explicit refusal behavior. Because our evaluation uses ten
prompts and a single unseeded run per configuration, we report this trade-off as an observed pattern rather than a statistically resolved effect. These results provide practical guidance for prioritizing content safety or refusal retention when aligned models are exposed to untrusted fine-tuning.
Read the full abstract ▾
All authors Muhammad Zeeshan Akram, Mufid Kamel Marican, Anvesh Reddy Yenugu, Ali Zain Kaimkhani, Minghong Fang
Artificial Intelligence
IronLLM: Forging Compact Edge-Native Language Models for Real-Time Embodied Intelligence
Changdi Yang, Fengquan Jiao, Haochih Lin et al. (+14 more)
We present IronLLM-0.6B, a 654M-parameter
language model designed for efficient on-device inference. IronLLM-0.6B combines a hybrid
attention architecture with X-MTP, a lightweight shared-KV multi-
token prediction design that eliminates per-depth KV-cache replay and employs a lightweight verification head for rollback-free drafting, achieving a 1.48x decoding speedup. The model is pretrained on approximately 6.2 trillion
tokens using a quality-oriented data pipeline and is further post-trained with Multi-Domain On-Policy
Distillation to integrate capabilities from domain-specialized teachers. To better meet the low-latency requirements of on-device scenarios, IronLLM-0.6B adopts an Instruct-Only design. Evaluations show that IronLLM-0.6B achieves competitive performance relative to larger models such as Qwen3.5-0.8B and MiniCPM5-1B, while producing more concise responses on many tasks. We further present IronLLM-0.6B-Light, which replaces RMSNorm with Dynamic Tanh and simplifies several computationally expensive components to improve inference and quantization efficiency. Together, the IronLLM models provide an effective performance-efficiency trade-off for resource-constrained deployment.
Read the full abstract ▾
All authors Changdi Yang, Fengquan Jiao, Haochih Lin, Haoran Yang, Jing Xiao, Liangyu Huo, Suxin Lu, Tiance Chen, Wei Liu, Yinggan Xu, Yunxiang Lu, Zai Zheng, Zhirui Xie, Zhongyang Che, Ziyan Tang, Zuoxiang Zhao, Jian Yao
Artificial Intelligence
When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaboration
Yaxin Gong, Gangyi Zhang, Chongming Gao et al. (+7 more)
Multi-
agent LLM systems rely on message passing among specialized
agents to accomplish complex tasks. However, an upstream
agent may provide useful information or an incorrect answer that causes a downstream
agent to override a correct answer supported by its own evidence. Prior work has not clearly separated the benefits of communication from the damage caused by incorrect messages. We study this problem with controlled experiments across five
benchmarks and five receivers, keeping the downstream task and evidence fixed while comparing answers under three conditions: no message, the upstream
agent's original message, or a message with the opposite conclusion. Our experiments reveal three key findings. First, messages often help when the downstream
agent would otherwise answer incorrectly. Second, messages can also hurt: when the downstream
agent would answer correctly without a message, an incorrect upstream message changes the answer in up to 32% of cases. Third, in 94% of audited harmful cases, the downstream
agent copies the upstream's specific wrong answer–a pattern we term answer substitution. Removing unreliable messages recovers part of the lost accuracy, suggesting that communication should be selective based on upstream reliability and the evidence already available to the downstream
agent.
Read the full abstract ▾
All authors Yaxin Gong, Gangyi Zhang, Chongming Gao, Leyang Shen, Chenxiao Fan, Jiakai Wang, Dong Wang, Yang Liu, Wenjie Wang, Xiangnan He
Artificial Intelligence · Cross-listed from cs.CR
Does the Unsafe Gradient Survive a Conversation? On the Fragility of Gradient-Based Jailbreak Detection in Multi-Turn Dialogue
Omar Sheta, Rinku Deuja, Hadi Masoudi et al. (+1 more)
Safety-aligned
language models are commonly deployed as multi-turn assistants, which lets adversaries spread unsafe intent across several user turns instead of a single
prompt. Gradient-based jailbreak detectors such as GradSafe were developed for single
prompts: they score an input by the
alignment between its induced gradient and a fixed unsafe reference direction, and their effectiveness in multi-turn dialogue remains unclear. We conduct a controlled evaluation of gradient-based jailbreak detection in multi-turn settings. We extend GradSafe with a Context Window Scanner that applies the detector to fixed-size windows of user turns and uses the maximum window score as the conversation-level score. We evaluate different window sizes, attack families, benign conversation distributions, and target models. The results differ sharply between synthetic and realistic benign settings. Against synthetic benign conversations, the detector achieves an ROC-AUC of 0.98 on human-authored multi-turn jailbreaks. On WildChat benign conversations, ROC-AUC drops to 0.76, and a threshold calibrated on synthetic data flags more than 90% of benign conversations as unsafe. Under realistic benign distributions, single-turn windows give the highest separability, whereas longer windows and accumulated contexts reduce performance. The detector is also sensitive to the attack-generation method and target model: successful Crescendo attacks receive scores comparable to or lower than benign conversations, and Qwen2.5-7B-Instruct yields near-random separability with a different optimal window size. These findings show that gradient-based signals can support multi-turn jailbreak detection, but reliable deployment requires calibration on realistic benign conversations, short-window scoring, length-aware thresholds, and evaluation across attack types and model architectures.
Read the full abstract ▾
All authors Omar Sheta, Rinku Deuja, Hadi Masoudi, Minghong Fang
Artificial Intelligence
Automated Screw Planning for Reduced Pelvic Fractures Based on Statistical Shape Models and Deep Learning
Yang Gao, Sutuke Yibulayimu, Yanzhen Liu et al. (+2 more)
Percutaneous iliosacral screw fixation is an important minimally invasive treatment for unstable pelvic fractures. Because the sacroiliac region has complex anatomy and narrow screw corridors, the accuracy and safety of screw placement directly affect
surgical outcomes. Accurate and reliable preoperative screw planning is therefore essential to improve
surgical success and reduce intraoperative risks. Conventional preoperative planning typically requires surgeons to determine screw trajectories through manual measurements, a labor-intensive process that depends on subjective clinical experience. To address these challenges, we propose a fully automated pipeline for preoperative iliosacral screw planning in patients with pelvic fractures. Using patient-specific three-dimensional anatomy, the pipeline automatically identifies safe screw corridors and generates individualized insertion trajectories to support clinical preoperative planning. We evaluated the proposed pipeline on 200 clinical cases of pelvic fractures. Compared with conventional manual measurements, the safety margin of the safe insertion corridors increased by 2% across the four screw types, the mean planning time decreased by more than 90%, and the clinical acceptance rate reached 95%.
Read the full abstract ▾
All authors Yang Gao, Sutuke Yibulayimu, Yanzhen Liu, Zian Zhao, Yudi Sang