Artificial Intelligence · Cross-listed from cs.LG
FreeSolo: Linear-time Sparse Attention with Zero-Shot Length Extrapolation
Zekun Shi and Alastair James Arthur Price
Linear-time sequence models typically store long-context information in a recurrent state. A fixed-size state limits how much information can be stored, while hybrid architectures that add full
attention for better recall incur quadratic sequence cost. Alternatively, sparse
attention with continued pretraining (CPT) can extend the effective context length. Generalization beyond the trained length remains challenging, however, and CPT can be costly. We introduce FreeSolo, a native sparse
attention mechanism with a short-range sliding window branch and a long-range branch that selects keypoint
cells for direct
token attention. Its linear-time variant, FS-L, learns to prune the prefix before query-dependent selection through short CPT. FS-B searches balanced trees with $O(N\log^2 N)$ algorithmic cost including radix-sort construction. FreeSolo demonstrates better zero-shot length extrapolation than the baselines without long-context fine-tuning.
Read the full abstract ▾
Artificial Intelligence
Aotian Chen, Frazier N. Baker, Reza Averly et al. (+5 more)
Current chemistry
benchmarks primarily evaluate outcome prediction or reaction pathway generation, but rarely test whether a model can explain why an observed chemical effect occurs. We introduce ChemExplain, a
benchmark of 1,180 multiple-choice chemistry questions drawn from 383 peer-reviewed papers. Each question pairs a molecular or reaction image with an observed chemical effect and four candidate explanations, each associated with a different structural feature visible in the image. Answering requires the model to perceive the depicted structure, apply chemical knowledge, and identify which feature most directly explains the effect, a capability we term explanatory attribution. The correct feature-mechanism relation is derived from supporting evidence in the source paper rather than invented by the question-generation LLM. We construct the
benchmark automatically with a multi-
agent framework that applies progressive quality control at three stages and validate it with eight chemistry domain experts. The strongest evaluated model reaches 78.6% accuracy, leaving considerable room for improvement. On a 600-question expert-reviewed subset,
reasoning-trace analysis classifies 71.4% of the strongest model's errors as attribution failures. Attribution is also the largest error category for the open-source and chemistry-specific models included in our analysis.
Read the full abstract ▾
All authors Aotian Chen, Frazier N. Baker, Reza Averly, Shan Zhang, Tianao Chen, Daniel Adu-Ampratwum, Xia Ning, Yuan Xue
Artificial Intelligence · Cross-listed from cs.RO
Generative Flow on Symbolic Abstractions for Embodiment Capability Discovery
Youwei Yu and Lantao Liu
Achieving complex, long-horizon
robot behavior remains challenging because successful execution depends on skills grounded in a
robot's physical affordances. Existing training-task distributions are often handcrafted or sampled from large
language models (LLMs), relying on semantic plausibility rather than embodiment-specific feasibility. This mismatch can produce curricula that are too difficult, redundant, or blind to non-obvious but learnable behaviors. We propose Generative Flow on Symbolic Abstractions (FOSA), a framework for discovering embodiment-specific capabilities by learning a grounded task generator. FOSA parameterizes an abstract policy as a Generative Flow Network that constructs symbolic task skeletons. Each skeleton is compiled into a simulation environment, where low-level policy-learning performance provides the reward signal for the abstract policy. Across heterogeneous
robot platforms, FOSA discovers diverse and executable tasks near the
robot's empirical capability frontier. After distilling the discovered task policies into a single
language-conditioned policy, FOSA improves performance on unseen complex and long-horizon tasks. The code and demonstration
videos are available at https://www.youwei-yu.com/fosa.
Read the full abstract ▾
Artificial Intelligence
Learning Perceptual Geometry of Natural Odor Mixtures from LLM-Derived Descriptors
Farhad Pashakhanloo and Venkatesh N. Murthy
The relationship between odor chemistry and perception remains incompletely understood. Many existing studies focus on the perception of single molecules, whereas natural odors contain tens to hundreds of components, adding extra layer of complexity to percept formation. Here, we explore the relationship between molecular composition and perceived similarity in natural odor objects. We study this using a database of more than 1,200 volatile-compound-in-food mixtures containing more than 8,000 molecular components, and use large
language models (LLMs) as a scalable surrogate for deriving mixture-level perceptual descriptions. We find that
language-derived representations provide useful supervision for predicting held-out mixture similarities from molecular composition. The prediction was consistently strongest when perceptual targets were derived from chemosensory
prompts than from other sensory
prompts. Further, during the mixture-level training, we learned low-rank molecular
embeddings that enabled better prediction of held-out mixture similarities than component-overlap metrics, even for mixture pairs with no shared molecules. Although no single-molecule labels were used during training, the learned molecular geometry showed significant
alignment with the independent human odor-descriptor space. Finally, we explored the use of external molecular features in our mixture-similarity prediction task. These features showed modest zero-shot
alignment with mixture-level perceptual similarity. They improved prediction under limited supervision but offered little additional predictive benefit with the full training set. Together, these results show that
language-derived descriptions can provide scalable supervision for predicting the perceptual organization of complex natural mixtures, contributing to a quantitative understanding of how molecular composition gives rise to odor perception.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Force-Modulated Dexterity: Unified Compliance for Contact-Rich Manipulation
Ying Yuan, David Held, Jitendra Malik et al. (+1 more)
Teleoperation is widely used to collect high-quality demonstrations for
robot learning. Dexterous manipulation, however, requires coordinated control of motion and contact forces. Operators can specify motion, but struggle to reproduce the subtle force adjustments of human manipulation without feeling the
robot's contacts. We introduce Force-Modulated Dexterity (FOMO-Dex), a unified compliance formulation for contact-rich manipulation. FOMO-Dex expresses nominal actions in coordinates defined by task geometry and contact structure. It applies force-driven motion corrections along selected directions while leaving the remaining command components unchanged. Across card picking, paper cutting, screwdriving, and nut-and-bolt assembly, FOMO-Dex reduces excessive contact forces compared with stiff control. A user study shows that operators collect more successful demonstration data per hour after brief practice. For policy learning, imitating the corrected actions improves card-picking success over imitating raw operator commands. Policies trained on FOMO-Dex demonstrations also achieve more rotation in nut-and-bolt manipulation and screwdriving than those trained on demonstrations collected with the stiff controller.
Videos are shown on https://yingyuan0414.github.io/fomo-dex/ .
Read the full abstract ▾
All authors Ying Yuan, David Held, Jitendra Malik, Haozhi Qi
Artificial Intelligence
The Format is the Filter: Scoring Format Fixes What an LLM Judge Can Express
Lovedeep Gondara, Jekaterina Novikova, Sagarika Suresh et al. (+2 more)
When an LLM judge filters instruction-tuning data, its scoring format (binary verdict, 1–5 rating, 0–100 score, or comparison) is rarely justified or ablated. Holding the candidate pool, judge
prompt, decoding and selection budget fixed, we score 15,406 UltraFeedback candidates under five formats with three judges, curate, fine-tune 66 models, and evaluate them with four judges. A 0–100 scale is worth only 7–12 equally used levels, two to three times a 1–5 scale rather than twenty, and a binary verdict leaves the top score tied in 77–78% of
prompts, so most selections are made at random. These properties are set by the format almost independently of the judge. Kendall's $\tau_b$ hides them: it ranks binary best while $\tau_a$ and top-1 agreement rank it last, because it discounts the ties a selector must break at random. Both comparative formats inherit a slot bias whose sign differs across judges. Downstream, curated data beat random selection under every evaluation judge, robust to length and markdown adjustment, but no ordering among formats is detectable. We propose four quantities that judge-based curation pipelines should report.
Read the full abstract ▾
All authors Lovedeep Gondara, Jekaterina Novikova, Sagarika Suresh, Jack Ji, Jithin Pradeep
Artificial Intelligence · Cross-listed from cs.SD
SonicWorld: Source-Centric Latent Dynamics for Spatial Audio Reasoning
Chenlong Wei, Hanling Wang, Mingjin Lou et al. (+6 more)
Dynamic spatial audio
reasoning requires a model to associate changing acoustic observations with the correct source and recover its spatial state at a queried time or interval, a challenge intensified by overlapping
speech and source motion. To study this problem, we introduce Sonic-Bench, comprising 2.8K first-order Ambisonics clips and 28.8K target-specific question-answer pairs across 480 simulated indoor scenes. The
benchmark covers localization, distance estimation, and motion
reasoning in single- and dual-source settings. We further propose SonicWorld, which integrates physical, learned acoustic, and semantic features into persistent source states through learned transitions and recurrent updates, and projects them into an Omni LLM for spatial
reasoning. Compared with Spatial-Omni on the Sonic-Bench test split, SonicWorld improves direction accuracy from 31.98% to 34.69% and reduces azimuth error from 57.22{\deg} to 48.01{\deg}. In zero-shot transfer to Spatial LibriSpeech, SonicWorld retains strong localization performance, achieving 73.98% direction accuracy and 19.29{\deg} azimuth error, compared with 27.14% and 70.74{\deg} for Spatial-Omni.
Read the full abstract ▾
All authors Chenlong Wei, Hanling Wang, Mingjin Lou, Yufan Shi, Yandong Sun, Sheldon Yu, Xiaohui Zhu, Xiaobo Jin, Yiwei Wang
Artificial Intelligence
EvoQuantLab: Training-Free Dual-Loop Evolution for Auditable Quantitative Research
Haolin Yang, Zhiqiang Qian, Chutian Chen et al. (+7 more)
Automated alpha factor discovery is critical for modern quantitative research. While large
language models (LLMs) have increasingly been integrated into quantitative workflows, existing
agent-based approaches remain highly susceptible to severe backtest overfitting. To address this challenge, we propose EvoQuantLab, a training-free, dual-loop self-evolving framework for robust factor discovery. Instead of relying entirely on LLM generation, EvoQuantLab deploys an inner genetic-programming (GP) loop that dramatically improves
token efficiency while evolving typed factor expressions under structural and diversity constraints. An outer diagnosis loop then systematically audits evidence across cycles to drive protocol-level improvements. Furthermore, our evaluation pipeline applies multi-metric validation to rigorously filter out spurious factors before deployment. Extensive out-of-sample experiments across both daily and hourly frequencies – covering equities and cryptocurrency – demonstrate the robustness of EvoQuantLab. Specifically, on daily CSI 500 and S&P 500 tasks, EvoQuantLab achieves leading annualized returns of 18.34% and 21.30%, consistently outperforming existing
agent baselines. On high-turnover hourly cryptocurrency data, EvoQuantLab delivers a 37.91% annualized return while effectively avoiding execution collapse.
Read the full abstract ▾
All authors Haolin Yang, Zhiqiang Qian, Chutian Chen, Jipeng Zhang, Zhenghao Zhu, Tangjia Deng, Jian Xie, Shuaishuai Gong, Yike Guo, Sirui Han
Artificial Intelligence · Cross-listed from cs.CR
Who is the 'I' in AI? Establishing Decentralized Identity and Accountability for Autonomous Agents
Ahammod Munim Ramil, Khalid Al Kafi, M. A. Abdullahis Sany et al. (+4 more)
The rapid proliferation of autonomous AI
agents in decentralized ecosystems challenges existing identity paradigms. While human identity is traditionally anchored in biological and/or self-asserted attributes and government credentials, AI
agents lack a standardized definition of selfhood, creating critical gaps in trust and accountability. This paper introduces a novel framework for establishing Decentralized AI Identity rooted in Self-sovereign identity (SSI) principles. We propose a formal model that clearly distinguishes human users and AI
agents, enabling distinct verification logic for each class while maintaining a unified identity calculus. The central to our contribution is the ABCD Framework, a multi-layered approach to
agent identification and verification: (A) Algorithmic Fingerprint, which binds the identity to static model architectures and provenance; (B) Behavioural Fingerprint, which verifies dynamic performance metrics over time; (C) Cryptographic Identity, which anchors the
agent via Decentralized Identifiers (DIDs) and (D) Delegation, which cryptographically binds
agent actions to respective human accountability. By orthogonalizing these dimensions, we model how systems can enforce granular trust policies ranging from simple authentication to complex liability assignment, thereby solving the black box identity problem in the autonomous economic activities of AI
agents.
Read the full abstract ▾
All authors Ahammod Munim Ramil, Khalid Al Kafi, M. A. Abdullahis Sany, Muktadirul Islam Nibir, Md Yeasin Ali, Mohammad Zavid Parvez, Md Sadek Ferdous
Artificial Intelligence · Cross-listed from cs.CL
D2: High-Capability Full-Duplex Spoken Language Models from Half-Duplex Backbones
Cheng-Kuang Chang, Alexander H. Liu, Brian Kingsbury et al. (+5 more)
Full-duplex spoken
language models (FD-SLMs) support simultaneous listening and speaking, but often lag behind half-duplex spoken
language models (HD-SLMs) in general capabilities. We propose Dialogue-to-Duplex (D2), a framework that converts pretrained HD-SLMs into high-capability FD-SLMs at fine temporal granularity. D2 adapts the original audio encoder to streaming through decoder-free representation
distillation and learns full-duplex interaction through supervised fine-tuning. We systematically study the effects of chunk size on full-duplex interaction, general capabilities, and inference computation. We apply D2 to two distinct HD-SLM architectures, Qwen3-Omni and LLaMA-Omni 2. At a 12.5Hz update rate, Qwen3-Omni-D2 achieves 99.2% turn-taking success with 521-ms latency, 99.5% interruption success, and a state-of-the-art VoiceBench score of 70.1.
Read the full abstract ▾
All authors Cheng-Kuang Chang, Alexander H. Liu, Brian Kingsbury, Hilde Kuehne, Rogerio Feris, Samuel Thomas, James Glass, Kai-Wei Chang
Artificial Intelligence
When LLM Agents See a Conflict but Still Proceed: Cross-Domain Dependencies in Network Slicing
Marcos Lima Romero and Ricardo Suyama
Future AI-native networks are being designed to apply autonomous
agents built on large
language models (LLMs) in network management through intents. When intents from different domains meet on the same resource, an
agent must recognize the cross-domain dependency before taking an irreversible action. We investigate this problem through a smart-grid use case, in which a power utility holds an active intent on a backup slice for protection traffic. This slice appears idle by design, which is precisely the profile targeted by a cost-reduction intent. We built a tool-based environment in which the dependency must be either queried by the
agent or read from an inventory annotation, together with a negative control, and evaluated ten models from four different providers in 600 runs. Most models acted against the dependency they had observed: seven of the ten models removed the protection slice at least once after receiving the cross-domain dependency, and in the high-harm tier the slice was removed in 76% of the exposed runs, while four models practically never did. Only one of ten models never removed the slice. We identify two failure modes, not querying the dependency and querying it but proceeding anyway, and show that
agents often reported no conflict after observing it. These results indicate that, in AI-native networks, visibility of cross-domain dependencies is not a sufficient safeguard, and that dependency verification should be enforced by the management architecture before irreversible actions rather than delegated to the LLM's judgment.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
D-World: An Explicit World-Language-Action Model with Recursive Self-Improvement under Dual Control
Xuan Wen and Baichao Wang
Frontier large
language models (LLMs) now reason about space well enough to program
robots, yet the world models behind
robot policies are implicit, held in network weights or predicted
video, and cannot be inspected or corrected directly. We present D-World, an explicit world-
language-action model built on the Sense, Plan and Act decomposition. A perception
agent writes the scene as an executable digital twin using generated
vision and geometry code. A planning
agent searches for actions in simulation and, after each executed action chunk, revises the twin's object states and named physical parameters against what the
robot measured. A parameter revision is accepted only if replaying the latest chunk does not increase any measured residual beyond its tolerance, and every chunk is checked in the updated twin before it runs. Structural mismatches return to perception for reconstruction. We call this measurement-grounded cycle of correction and revision recursive self-improvement (RSI), in which the LLM stays frozen while the world it acts in improves. We model the choice of actions that both advance the task and expose model error as a dual control problem and show that the cost of incorporating evidence into the twin sets the threshold at which probing pays, so cheap local revision counteracts the turn-off of cautious controllers. Each episode runs a real-to-sim-to-real loop, and its recorded twins can be refitted and re-rendered offline into higher-fidelity environments for post-training. Because perception and planning communicate only through the twin and
language, either can be replaced by a learned model, and since inference dominates the loop, the loop speeds up with faster models. On a dual-arm
robot, towel and toaster tasks show local revisions, such as one reducing the bread's rendered-depth residual from 22.4 to 1.5 mm, that let execution continue without reconstruction.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Calibrated Typed Decisions for Entity, Relation, and Event Extraction
Yang Wang, Hanlin Xiao, Yanan Ma et al. (+2 more)
Information extraction models often perform well on the
datasets they are trained on, but transferring to new domains and annotation guidelines remains challenging. Supporting user-specified types alone does not resolve this problem. We present CalOn, a unified 0.6B-parameter encoder for entity, relation, and event extraction across
datasets and schemas. The model jointly encodes text and type definitions, then directly identifies entity spans, relations between spans, and event triggers and arguments. Its extraction decisions consider the requested types together, using their combined evidence to identify relevant candidates before assigning a type. This gives all three tasks a common probabilistic formulation while keeping every extracted mention anchored to the input text. We train on diverse sources, and supplement supervised learning with a reward that encourages correct extractions and penalises incorrect ones. Across 40
benchmarks, CalOn outperforms the evaluated baselines on most
benchmarks. It leads all reported relation extraction
benchmarks and achieves the highest average F1 for event triggers and arguments with gold triggers. The same model also performs strongly on aspect sentiment triplet extraction and pronoun resolution through its span-pair formulation. A correction for the probability bias introduced during training improves confidence estimates for entities, relations, and event arguments after calibration, with little change in F1.
Read the full abstract ▾
All authors Yang Wang, Hanlin Xiao, Yanan Ma, Chenghao Xiao, Chenghua Lin
Artificial Intelligence · Cross-listed from cs.SE
AIPOCH Open-Science: An Open-Source AI Research Workbench with Reproducible .science Packages
Wen Ouyang, Bocheng Huang, Qianyu Yao et al. (+76 more)
AI-assisted research leaves instructions, computations, artifact revisions and checks whose relationships matter when another researcher receives the work. We present AIPOCH Open-Science, an open-source research workbench with portable .science session packages, and specify an exchange contract for these recorded relationships. Version and assessment targets remain attributable while receiving-workspace identifiers can be remapped, eligible contents can be omitted explicitly, and imported history remains separate from a writable fork. A controlled session tested an incorrect first version, a reviewed correction, an unreviewed revision and a planned but unexecuted step. We compared complete and partial exports with source records extracted independently of the exporter, then inspected imports into separate projects within the same installation. Both conditions retained the tested version and review associations, kept the unreviewed revision distinct from earlier assessments and represented excluded content as unavailable. A documentation-rich ordinary directory also supplied evidence for all seven static inspection questions. A separate registry case connected a table to its recorded task, execution and review; offline execution of its retained script and fixed input reproduced two saved CSV tables byte for byte. The study contributes an implemented exchange contract and a controlled examination of its preservation rules, content-selection constraints and interpretation boundaries.
Read the full abstract ▾
All authors Wen Ouyang, Bocheng Huang, Qianyu Yao, Fei Sun, Minying Deng, Haoyue Cheng, Wenwen Zhou, Lei Mou, Yusi Wei, Jiang Li, Kun Zhu, Lei Wang, Yi Feng, Jiaheng Dai, Ke Qian, Dan Wang, Yahui Wang, Chenyi Wang, Mingsheng Lyu, Yaqiang Zhang, Ping Zheng, Chunhua Tang, Xinge Ma, Xu Zhang, Youjia Fan, Can Lu, Zhijun Dai, Man Hu, Qiqi Xie, Beinan Liu, Yuanning Guo, Yunze Liu, Jinhong Jiang, Xianjun Fu, Mingwei Zhang, Yuanji Xu, Shilin Xia, Bowen Yang, Mingjun Yu, Jingdun Xie, Xuwei Chen, Xia Zou, Yuzhou Xue, Jianguo Zhou, Chunhao Cao, Donghao Tian, Lei Huang, Jinxiao Li, Shengrong Long, Zefeng Song, Honglin Li, Jiang Luo, Wenying Jiang, Shanshan Li, Lei Dai, Ning Jiang, Ying Cai, Chaohui Li, Chunyan Peng, Hetong Zhao, Angqing Li, Chunyan Yang, Chongyang Sun, Yong Li, Xinyu Shi, Wei Dai, Ming Peng, Chen Sang, Yuanyuan Han, Desong Qiu, Haixin Miao, Jian Xu, Yi Chen, Xiaoliang Shi, Tian Shen, Teng Hu, Shuhao Wang, Yingyong Hou, Huimei Wang
Artificial Intelligence
SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise
Xupeng Chen, Chenqian Le, Jiayi Cheng et al. (+2 more)
A model diff credits post-training with whatever separates a base checkpoint from one post-trained descendant, presuming a rerun would land close by. On the sparse co-activation graph of Qwen3-1.7B it does not: two LoRA-SFT reruns sit over half as far apart as either sits from the base. We score each base-to-post contrast against the run-to-run band of its own recipe, and show that $k$ runs certify no better than $p=1/(k+1)$ under run exchangeability, however large the effect, so the band $z$-score is a descriptive scale. SFT leaves a large, reproducible signature: base $\to$ SFT displaces the graph by 17.8 pairwise-distance SDs beyond the mean distance between four independent LoRA-SFT runs, and the pre-registered
estimator replicates on Llama-3.1-8B with Llama-Scope. At 29 steps each, four SFT and four DPO runs occupy disjoint displacement ranges, a gap $5.0\times$ and $5.6\times$ the spreads of the two arms, without any band. All bands use graphs built on one GPU architecture. Three other readings stop short of a verdict: DPO band counts (3/4, 1/4, 3/4 contrasts outside at 12, 29, 60 steps) show no consistent dose ordering while its displacement stays flat; light GRPO is a secondary non-detection, not an absence, and we run no equivalence test; and the graph concentration read as an RL signature is already in the zero-RL base. A pre-registered causal sweep at three edge budgets on 4,816 held-out
prompts found the displaced sources load-bearing ($12\times$ a matched random control in mean, $3.5\times$ in median at 10,000 edges), but their stage-specificity interaction reversed at two budgets and the third failed its faithfulness gate, so we claim calibrated structural displacement, not a changed mechanism. Scope: one backbone, one SFT recipe and general-text probe states for the full protocol.
Read the full abstract ▾
All authors Xupeng Chen, Chenqian Le, Jiayi Cheng, Runhao Li, Michael Yue
Artificial Intelligence · Cross-listed from math.HO
What the Machine Invented: Mining New Mathematical Instruments from OpenAI's October 2026 Release of AI-Generated Mathematics
Ying Xie
On 6 October 2026 OpenAI published an initial 722 AI-written mathematical manuscripts, organized into 372 problem families, in the public repository github.com/openai/math. The release includes claimed solutions to many prominent open problems. We approach this collection as a treasure mine of mathematical ideas. Our aim is to extract new lemmas, constructions, inequalities and proof mechanisms introduced in the source arguments, and to distinguish them from established tools and new combinations of those tools. We call these mathematical instruments. Extraction comes first; their validity, novelty and possible reuse then become subjects for further study. The resulting descriptions also help readers understand the selected papers without having to reconstruct every argument at the outset. We examine 38 families in two groups of 17 and 21, spanning number theory, geometry, analysis, combinatorics, complexity,
algebra, operator
algebras,
topology and mathematical physics. Each entry records the claim, extracted instruments, antecedents and caveats. Eleven cross-cutting patterns connect the entries, and a scoreboard records formalization status and dependencies. Novelty assessments are provisional and sometimes mixed. Selected source comparisons correct mathematical statements, hypotheses and counts; they do not independently establish priority or certify the underlying proofs. No Lean development was compiled or kernel-checked for this survey. We also briefly describe a subsequent application of the signed restriction lemma from family 112 to
circuit lower bounds at every fixed depth.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
Interactive Navigation Beyond Reachability: Benchmark and Agentic Framework
Delun Li, Xueyao Wei, Rui Chen et al. (+4 more)
Existing embodied navigation tasks commonly assume that traversability and object states remain fixed during an episode. Yet reaching a goal may require opening a door to access a room and then opening a container to reveal a hidden target. We formulate interactive navigation beyond reachability, unifying channel-induced changes in spatial connectivity, container-induced changes in target visibility, and their sequential dependencies. We introduce MultINav-Bench, a 3K-episode ObjectGoal
benchmark in MolmoSpaces spanning channel, container, and mixed tasks, with interaction-necessity annotations covering required and unnecessary episodes. Its data generation pipeline automates task construction across multiple task types. The evaluation protocol separately measures navigation success, interaction effectiveness, and cost. We further propose MultINav-
Agent, a three-stage agentic framework built on a persistent, state-conditioned interaction graph. Semantic interactive perception grounds entities and interaction states; a
vision-
language model selects task-relevant actions based on expected changes in connectivity and target observability; and post-interaction verification updates the graph to guide subsequent navigation, exploration, or interaction. Experiments on MultINav-Bench show that MultINav-
Agent consistently outperforms adapted baselines across channel, container, and mixed tasks.
Read the full abstract ▾
All authors Delun Li, Xueyao Wei, Rui Chen, Yifei Wang, Junzhi Yu, Wenjie Song, Xingyu Chen
Artificial Intelligence · Cross-listed from cs.CY
Superintelligence and the Triple Risk of an AI Race
Matthew Rendall, Max Hellrigel-Holderbaum and Leonard Dung
On many estimates, artificial general intelligence (AGI) is likely to emerge within the next few decades or even sooner. Once it does, it may quickly surpass human intelligence, possibly by a huge margin. Some believe that the country that develops AGI first could attain global dominance. This prospect risks setting off intense competition between the United States and China. Indeed, a narrative has already developed that the superpowers are locked in an AI race, with the Trump administration proclaiming its determination to 'dismantle unnecessary regulatory barriers' to winning it. We argue that this approach presents three profound dangers. The first two are familiar from past arms races: being overtaken by a rival or triggering a war. The third is new: losing control of human beings' future to
agents far more intelligent than we are, which could endanger our very survival. Striving to get to AGI first risks a race to the bottom on safety practices and regulation concerning them. China does not yet appear bent on racing to superintelligence. The United States should prioritise both unilateral and co-operative efforts to improve AI safety and avoid provoking a race that all humanity could lose.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
Gradient Routing Localizes and Removes Unintended Behaviors in RL
Jake Ward, Shawn Hu, Aria Wong et al. (+4 more)
We propose a mitigation to reward hacking in reinforcement learning. Our setup involves a misspecified reward function that gives rise to unintended behavior, and a monitor used to detect unintended behavior. As with frontier AI systems, the monitor makes systematic errors. Consequently, using the monitor for data filtering or to apply a reward penalty fails to prevent the model from learning unintended behavior ("reward hacking"). To address this problem, we introduce GRAFT: Gradient Routing Adapter Fine Tuning. Rather than penalizing or filtering flagged samples during training, GRAFT constrains gradient updates on those samples to a sacrificial set of new parameters. This has two benefits: First, because the monitor is not part of the reward function, the model does not learn to hide misbehavior. Second, ablating the sacrificial parameters reduces or entirely stops the unintended behavior while maintaining improved performance on target tasks. We demonstrate these benefits in RL environments where reward penalties cause models to learn to reward hack in undetected ways, training models ranging from 135M to 8B parameters. Additionally, we show a similar effect at a larger scale by distilling frontier LLM trajectories containing reward hacking into Qwen3-32B, without teaching that model to reward hack. Overall, our work suggests GRAFT may be a promising approach for leveraging imperfect monitors during post-training in settings where true performance is difficult to evaluate.
Read the full abstract ▾
All authors Jake Ward, Shawn Hu, Aria Wong, Nathan Hu, Bryce Woodworth, Alexander Matt Turner, Alex Cloud
Artificial Intelligence
PatientWM: Towards Generalizable Clinical World Models via Unified Patient States
Ziwen Kan, Jie Peng, Bo Yan et al. (+5 more)
Clinical decisions depend on anticipating how a patient's condition will evolve as treatment is adjusted and new evidence becomes available. Existing medical world models capture patient-state
evolution, but often define the evolving state around a particular modality or task, limiting reuse as inputs or prediction targets change. These models also retain history through observation sequences or recurrent or latent summaries rather than exposing preceding patient states and clinical actions as an ordered transition context. This distinction matters because similar current measurements may follow different recent changes, treatment exposures, and observed responses. To tackle these limitations, we propose PatientWM, a clinical world-model framework built around a unified patient state and sequential latent history. Availability-aware encoders integrate observations available at each decision time into the patient state, while typed decoders produce task-specific clinical readouts without defining the state around any single target. PatientWM further conditions each next-state prediction on the current state and supplied action together with a bounded, ordered history of preceding latent patient states and clinical actions, preserving recent treatment and response context. Experiments across MIMIC-III, MIMIC-IV, and three external clinical
datasets show superior performance in clinical prediction, multi-step forecasting, and action-planning evaluation. Transfer experiments further demonstrate the generalizability of PatientWM's patient state. Together, these results establish its ability to forecast clinical
evolution and support planning.
Read the full abstract ▾
All authors Ziwen Kan, Jie Peng, Bo Yan, Davis Hobley, Zheng Zhang, Yu Tian, Tianlong Chen, Song Wang
Artificial Intelligence
VL-DocIR: A Benchmark for Vision-Based Long Document Information Retrieval
Simon Ott, Yufan Chen, Ruiping Liu et al. (+6 more)
Vision-based document
retrieval has improved rapidly, but current evaluation settings still emphasize short documents and single relevant pages. This leaves an important gap between leaderboard performance and realistic long-document
retrieval, where the evidence needed to answer a query may span multiple pages or even multiple documents. We present VL-DocIR, a page-level
benchmark for evidence-complete visual long-document
retrieval. VL-DocIR is built from 29,641 HTML-born documents rendered into 388,548 page images from Wikipedia, arXiv, PubMed, and SEC proxy statements. It contains 271,760 queries across 23 domains and six evidence structures, covering single-page, within-document multi-page, and cross-document evidence configurations. Evidence annotations are grounded to rendered pages and HTML element identifiers, and queries are filtered with a cleaning pipeline targeting clarity, correctness, closedness, and the absence of explicit layout references. We evaluate leading single-vector and multi-vector visual retrievers together with diagnostic
retrieval settings such as document-context scoring, query splitting, reranking, and round-robin ensembles. The strongest evaluated configuration reaches 69.3 nDCGAll@10 and 80.6 RecallAll@10 under structure-balanced Macro evaluation, but source- and evidence-structure breakdowns show that cross-document
retrieval remains substantially harder than single-page
retrieval, and that document-context scoring is especially helpful for within-document multi-page queries. VL-DocIR exposes these failure modes and provides a more demanding target for visual long-document
retrieval. The new
dataset and code will be made publicly available at https://yufanchen96.github.io/VL-DocIR.
Read the full abstract ▾
All authors Simon Ott, Yufan Chen, Ruiping Liu, Junwei Zheng, Jiale Wei, Di Wen, Kunyu Peng, Jiaming Zhang, Rainer Stiefelhagen
Artificial Intelligence
Neos: Learning to Interleave Search and Visual Reasoning
Ekko He, Jack Hong, Shilin Yan et al. (+8 more)
Recent
multimodal deep search
agents have advanced tool use and visual content
retrieval, yet they still struggle to convert intermediate visual evidence into actionable guidance for subsequent search, limiting their effectiveness in long-horizon settings. To address this gap, we present Neos, a
multimodal deep search framework that learns both how to acquire evidence and how to use it to guide subsequent decisions. To make this coupling learnable, Neos constructs training tasks with intermediate visual dependencies while filtering out textual shortcuts, and introduces a lightweight, trainable
Multimodal Evidence Interface (MEI) that transforms retrieved content into goal-conditioned observations. At its core, an
agent-environment co-
evolution procedure treats MEI as a co-adaptive component of this loop. Specifically, reference-guided credit assignment uses verified successful trajectories to localize critical policy errors while preserving credit for useful decisions in failed searches, whereas rollout feedback selects informative local evidence-processing interactions for MEI supervised fine-tuning (SFT). By alternating policy reinforcement learning (RL) with MEI SFT, Neos allows the policy's evolving evidence requests to shape MEI training and the adapted MEI to reshape subsequent observations, closing the loop between evidence acquisition and evidence-conditioned action. Across ten
benchmarks, Neos-9B and Neos-35B demonstrate leading performance among specialized
multimodal deep-search
agents.
Read the full abstract ▾
All authors Ekko He, Jack Hong, Shilin Yan, Xintong Zhang, Yujie Zhang, Wenjie Li, Haoran Sun, Kaixun Jiang, Jiyuan Fu, Guannan Zhang, Hongwei Xue
Artificial Intelligence · Cross-listed from cs.LG
SPLICE: Sparse Physics Library Identification and Compositional Expansion
Lucas Thil, Jesse Read, Guillaume Doquet et al. (+1 more)
Neural operator splitting composes a library of neural operators, one per physical mechanism, into zero-shot simulators of new equations. Existing approaches, however, require these mechanisms and their labels to be specified in advance. We ask whether a pretrained library can instead be adapted and grown from unlabeled trajectories in which multiple mechanisms act simultaneously. We introduce SPLICE, a framework that discovers operators without mechanism labels on mixture data. The contributions of the candidate operators to each trajectory are inferred by solving a convex optimization problem. A calibrated test then assigns each discovered operator the mechanism it implements. Failure cases are also detectable, when the library lacks the required physics or when mechanisms are insufficiently separable. Across one and two dimensional systems, the discovered operators recover mechanisms from unlabeled mixtures and compose into zero-shot simulators of unseen equations; a frozen library can also grow an operator for physics absent from pretraining, without labels and without forgetting. On Navier-Stokes, the discovered operators compose about as accurately as their supervised counterparts.
Read the full abstract ▾
All authors Lucas Thil, Jesse Read, Guillaume Doquet, Rim Kaddah
Artificial Intelligence
Benchmarking Quantum Kernel SVMs for Credit Card Fraud Detection: Performance Realities Under NISQ Constraints
Hitanshi Arora, Mohit Swarnkar and Aswani Kumar Cherukuri
Detecting credit card fraud is notoriously difficult because fraudulent charges make up less than 0.2% of total transactions.
Quantum Machine Learning (QML), particularly
Quantum Kernel Support Vector Machines (QSVM), promises richer feature representations by
embedding classical data into high-dimensional
Hilbert spaces. However, whether this theoretical advantage holds up when managing real-world financial data bottlenecks remains unclear. We designed a controlled
benchmark comparing three
quantum encodings, Angle, ZZFeatureMap, and IQP against classical models while keeping sample sizes, feature counts, and scaling strictly matched. To handle class skew without corrupting
quantum state overlaps, we embedded synthetic minority oversampling (SMOTE) directly into the
quantum Gram
matrix workflow, raising PR-AUC scores by roughly +0.04 across feature maps. When trained on the full European credit card
dataset with 30 features, classical baselines reached a top PR-AUC of 0.983. However, restricting classical models to match QSVM hardware constraints (500 samples, 4 PCA features) dropped their PR-AUC to 0.750. This puts our best
quantum result 0.730 PR-AUC using IQP encoding on 150 samples into realistic context. Testing on physical
quantum hardware reduced performance further to 0.62 due to CNOT gate errors and thermal noise. Overall, our findings pinpoint two main operational bottlenecks for near-term
quantum kernels: the scaling of Gram
matrix evaluation and heavy information loss from squeezing features onto small
qubit registers.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CR
CWE-bench: Refocusing Agentic Security from Exploitation to Defense
Gonzalo Gonzalez-Pumariega, Ajay Jagannath, Adit Jain et al. (+3 more)
Cybersecurity evaluations of AI
agents have focused largely on offense, yet a working exploit does not show that an
agent can make software safe. An attacker needs to exploit only one vulnerability; a defender must find and fix all of them. We introduce CWE-bench, a private
benchmark of 120 held-out repository audit-and-repair tasks spanning 73 CWE types, eight
languages, and all OWASP Top 10 2025 categories.
Agents are given a repository to audit and a description of its threat model, but are not told the weakness, where it occurs, or how many vulnerable sites there are. Each patch must block the exploit while preserving original functionality, as checked by a programmatic verifier. We validated the verifier against a panel of agentic judges, manually reviewing disagreements during development and refining the checks. The best
agents reach 68% pass@1 and 81% pass@4. We further conduct analyses showing that (i)
agents with the same pass@1 differ widely in retry gains and cost, and (ii) no single
agent is best across
languages or vulnerability categories, and difficulty varies far more by vulnerability category than by
language. As the offensive capabilities of
agents improve, CWE-bench provides a broad and rigorous measure of whether their defensive capabilities keep pace.
Read the full abstract ▾
All authors Gonzalo Gonzalez-Pumariega, Ajay Jagannath, Adit Jain, Guram Gogia, Soumyadeep Bakshi, Nazneen Rajani
Artificial Intelligence
Understanding Personalization Gains in Whisper
Sergei Katkov and Antonio Liotta
Whisper-style ASR models provide strong zero-shot transcription, but their residual errors are not evenly distributed across
datasets, recording conditions, and metadata-based groups. We study when lightweight low-rank adaptation (LoRA) improves Whisper and whether observed gains require group-specific adapters. Across Common Voice, LibriSpeech, and VoxPopuli, we compare zero-shot Whisper, pooled LoRA, and group-specific LoRA under matched within-group splits. We find that adaptation is not uniformly beneficial: gains are concentrated in difficult Common Voice groups, are consistent on VoxPopuli, and largely disappear on low-error LibriSpeech. Crucially, pooled LoRA often matches, and sometimes clearly outperforms, group-specific LoRA. Gains over zero-shot should therefore be tested against matched pooled adaptation before being interpreted as evidence of personalization.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.LG
ProbabilityBench: Model Evaluation and Calibration with Exact Ground-Truth Uncertainty
Yuyang Dai, Yuting Tang, Futoshi Futami et al. (+1 more)
Evaluating model uncertainty on real-world data is challenging because each instance provides only a single observed label, leaving true conditional class probabilities unknown. To address this, we introduce ProbabilityBench, a
benchmark that provides exact, instance-level class probabilities across three simulated text-based domains: peer review, covert information transfer, and credit risk. By explicitly defining the full data-generating process for each environment, we analytically compute both exact class probabilities and Bayes error. Furthermore, we provide a theoretical guarantee that rendering these cases into natural-
language memos strictly preserves their underlying generative probabilities. This exactness enables direct measurement of reported probability quality via KL divergence. Across 16 evaluated models, most models on the observed cost-quality Pareto frontiers are decision models, including Jev and Perplexity Decider. Finally, ProbabilityBench serves as a meta-evaluation framework, leveraging known ground-truth values to
benchmark the accuracy of standard calibration metrics and Bayes-error
estimators themselves.
Read the full abstract ▾
All authors Yuyang Dai, Yuting Tang, Futoshi Futami, Takashi Ishida
Artificial Intelligence · Cross-listed from cs.LG
MAGNET: Manifold-Aware Graph Diffusion Network for Connectome Generation
Protyay Dey, Ayush Roy, Hyuna Cho et al. (+2 more)
Functional
brain connectome represents neural connectivity as a
matrix of pairwise interactions between
brain regions. Generation of functional connectomes is not only a question of validity; rather, having satisfied the constraints on the correlation
matrix, the next step is to recover the class-conditional geometry buried under coarse labels. We propose MAGNET, a
Manifold-Aware Graph
Diffusion Network which uses a normalized-Cholesky representation of the
manifold of correlation
matrices that guarantees validity. MAGNET lifts noisy latent states into ROI-level region
tokens and performs denoising with a relational inductive bias over
brain atlas regions. To deal with structural problems induced by coarse labels, MAGNET employs class-anchored conditioning, amortized structural bridge, and relevance-preserving corruption. Across ABIDE, ADNI, and OASIS-3, MAGNET consistently achieves favorable results compared to previous
manifold-aware approaches, demonstrating improvements of 7-21% in class-conditional fidelity ($\alpha,\beta$-F1) across three cohorts and better sampling efficiency. Moreover, while training only with strict binary labels, MAGNET is capable of maintaining clinical heterogeneity through fine substructure of the connectomes in a zero-shot setting, improving subclass covariance
alignment ($\lambda$-MSE) by over 30%. These results suggest that
geometric validity is a necessary but insufficient condition for clinical utility in connectome synthesis. Moreover, efforts in making the
diffusion denoising class-conditional
manifold aware finds utility beyond the highly curved
brain connectome generation as this is a critical problem in various general settings. The code repository can be found at https://github.com/protyayofficial/MAGNET.
Read the full abstract ▾
All authors Protyay Dey, Ayush Roy, Hyuna Cho, Won Hwa Kim, Vishnu Suresh Lokhande
Artificial Intelligence · Cross-listed from cs.CY
Governing Copyright Responsibly in the Era of Generative AI
D. Kochetkov
Large
language models are trained on collections that may include scholarly works, while authors generally lack work-level information about whether and how their works were used. This paper asks how copyright governance frames and operationalises the protection of such authors, and what a responsible alternative would require. Forty legislative, judicial and soft-law instruments issued between 2019 and 2026 were coded deductively against a framework derived from Responsible Research and Innovation theory, yielding 1,337 category assignments across 835 segments. The European Union and the United States are the primary cases; the United Kingdom, China and international bodies serve as comparators. Normative orientation and the distribution of responsibility dominate the corpus, while reflexivity is the least represented category and reaches its minimum in the US sub-corpus. Both primary jurisdictions frame protection procedurally rather than as an entitlement, and no instrument in the corpus creates a general author-facing attribution duty for the use of works in AI training. From the coded gaps, the paper derives a six-instrument governance design and a capacity-based allocation of responsibility among developers, publishers, collecting societies, funders, institutions, regulators, and individual authors.
Read the full abstract ▾
Artificial Intelligence
Glasseek: A Transparent Recipe for Training and Trustworthy Evaluation of DeepSearch Agents
Cong Pang, Jiaqi Su, Chengrui Wu et al. (+14 more)
Deep search enables
language agents to solve complex information-seeking tasks through iterative web exploration. However, developing robust open-source
agents remains challenging for three reasons. First, opaque trajectory-construction pipelines make training data difficult to audit and reproduce. Second, context compression can create a substantial mismatch between training and inference. Third,
agents may retrieve
benchmark content from the open web during evaluation, contaminating the results and overstating their performance. To overcome these bottlenecks, we introduce Glasseek, a fully transparent deep search framework spanning the complete development lifecycle, releasing all data, model weights, training recipes, and code. Specifically, for data construction, we establish a verifiable trajectory curation pipeline that systematically generates high-quality exploration paths. For training, we propose Compaction-Managed GSPO (CM-GSPO), which uses the same policy for search and summarization while optimizing only execution sub-trajectories, enabling end-to-end search-policy training across context-compaction boundaries. For evaluation, we conduct the first systematic audit of test-set leakage in open-web
agents and release a modular anti-leakage plugin that seamlessly integrates into existing evaluation harnesses. Under this rigorous evaluation protocol, our 9B
agent outperforms frontier proprietary
agents across almost all deep research
benchmarks spanning diverse task types, and achieves the best overall performance among recent open-weight
agents, setting a new state of the art at the 9B scale.
Read the full abstract ▾
All authors Cong Pang, Jiaqi Su, Chengrui Wu, Kuihao Yan, Tianrui Zhang, Zixuan Qiu, Chao Lin, Zixiu Lin, Zixuan Chen, Zelin Xiao, Tiankuo Yao, Jiawei Hong, Zixuan Chen, Dan Xu, Lewei Lu, Wenjie Wang, Xin Lou