Artificial Intelligence · Cross-listed from cs.CL
How Local Mixing Encodes Relative Position in Global NoPE Attention
Cutter Dawes, Nick Alonso, Tom Figliolia et al. (+1 more)
The
attention operation is naively position invariant. However, positional information is fundamental to natural
language, and therefore a variety of explicit position encodings have been developed in
transformer-based models, such as rotary position encoding (RoPE). Although explicit position encodings have long been assumed to be required, recent methods that interleave local mixing layers, such as sliding window
attention (SWA) and gated linear
attention, while not encoding position (NoPE) in global
attention layers has recently been shown to be successful at scale. How and why this approach works is not well-understood. In this paper, we develop an explanation of how hybrid models of this sort can implicitly encode position at global NoPE layers. Supported by both theoretical and empirical evidence, our central argument is that SWA and gated linear
attention induce a recency bias in the residual stream that propagates to, and is selected by, the global
attention logits. Moreover, in contrast to the implicit position encodings found in models with only global NoPE
attention, in which positional information arises solely from the causal mask, the recency bias in hybrid models can be maintained across long sequences. In addition to deepening our understanding of how hybrid models encode position, these findings may provide insights for how to encode position in a way that can extrapolate to longer sequence lengths indefinitely.
Read the full abstract ▾
All authors Cutter Dawes, Nick Alonso, Tom Figliolia, Beren Millidge
Artificial Intelligence
Do LLM Agents Execute the Plans They Declare? From Planning-Mode Declaration to Pattern-Specific Execution
Subba Reddy Oota, Francisco Herrera, Jordi Cabot Sagrera et al. (+2 more)
Large
language models (LLMs) enable
agents to solve long-horizon tasks by generating a plan and then executing it in an environment. However, successful planning requires two distinct capabilities: selecting an appropriate plan for the task and executing it faithfully. Existing planner–executor systems can fail at either stage, while final task success alone cannot distinguish selection from execution failures. We therefore study the Plan Declaration–Execution Gap and introduce Planning-as-Routing, where an LLM declares one of four planning modes: Predefined, Sequential, Hierarchical, or Search, and a deterministic router dispatches the task to the corresponding pattern-specific executor. Across four
benchmarks and three LLMs, we find three consistent patterns. First, generic Plan+ReAct often fails to preserve declared planning structure, especially for longer plans: across three
benchmarks, only (22)–(45%) of trajectories preserve it, whereas pattern-specific executors enforce the intended structure. Second, planning-mode effectiveness varies across environments and models: Search performs best on ALFWorld, Hierarchical on SWE-bench, and the strongest pattern can vary across models within the same
benchmark. Third, the largest gains come from execution: pattern-specific executors improve task success from (0.48) to (0.92) on ALFWorld and from (0.36) to (0.44) on SWE-bench Verified over Plan+ReAct. Current LLMs, however, do not reliably select the strongest mode for each task, although few-shot examples improve selection in some
benchmark–model combinations. Overall, reliable
agent planning requires both effective mode selection and faithful execution: routing substantially closes the execution gap, while task-specific mode selection remains open.
Read the full abstract ▾
All authors Subba Reddy Oota, Francisco Herrera, Jordi Cabot Sagrera, Marcos López de Prado, Shadab Khan
Artificial Intelligence · Cross-listed from cs.CL
Correct Answers, Invalid Traces: What Verifiable Grade-School Math Reveals About Chain-of-Thought Traces
Ratish Puduppully, Pranabendu Misra, Paarth Iyer et al. (+3 more)
Chain-of-thought traces are widely read as records of how models reach their answers, informing debugging,
agent auditing, and claims about
reasoning. Testing this interpretation is difficult because natural-
language thinking traces are rarely mechanically verifiable. We revisit it in iGSM, a synthetic grade-school mathematics
benchmark designed to study thinking traces and used to support claims of learned
reasoning and planning. Crucially, iGSM exposes the exact quantities and dependencies that a correct solution should use, allowing generated traces to be checked programmatically step by step and enabling us to test whether correct answers are reliably accompanied by valid traces. We first evaluate models trained exclusively on valid, minimal traces. Answer correctness and trace validity nearly coincide in distribution but decouple out of distribution: on the hardest instances, 31.6% of correct answers have invalid traces, over half of which pass all syntactic and arithmetic checks but fail semantic dependency checks. We then intervene on trace supervision. Non-minimal training traces induce non-minimal outputs, while re-asking the same problem with a different query reveals computations inherited from the original query, weakening minimality as evidence of selective planning. Shuffling
tokens in 10% of training trace sentences preserves near-clean accuracy even out of distribution despite no trace passing verification. Swapped training traces likewise retain high in-distribution accuracy. We discuss the implications of these findings for chain-of-thought monitoring and interpretation in the context of AI safety.
Read the full abstract ▾
All authors Ratish Puduppully, Pranabendu Misra, Paarth Iyer, Durgesh Kalwar, Vardhan Palod, Subbarao Kambhampati
Artificial Intelligence
NeuronEye: Query-Guided Visual Concept Activation for Vision-Language Reasoning
Ruiyu Yan, Bowen Chen, Shaowen Wan et al. (+1 more)
Current
vision-
language models (VLMs) encode visual information in dense hidden states where object identity, spatial layout, and local attributes are implicitly entangled rather than explicitly disentangled, limiting their ability to isolate and modulate the specific visual evidence required by a given
language query. Inspired by sparse population coding and top-down modulation in biological
vision, we introduce NeuronEye, a plug-in framework that constructs a sparse, concept-level
neuron vocabulary from intermediate VLM representations and selectively activates query-relevant visual concepts during inference. NeuronEye decomposes
vision-
token states into an overcomplete sparse basis organized by concept-level clusters, uses the
language query to activate relevant clusters and localize the patches where selected concepts are expressed, and injects the focused evidence back into
vision tokens. A complementary suppression mechanism attenuates dominant perceptual directions to preserve weaker but relevant cues. All operations run in a single forward pass over a frozen VLM backbone. On Qwen2.5-VL-7B, NeuronEye raises CV-Bench overall accuracy by +3.1 with gains of +9.5 on Distance, and improves BLINK Multi-view by +8.3, with similar trends on LLaVA-1.6-7B. These results suggest that sparse
neuron vocabularies can serve not only as post-hoc interpretability tools but also as active interfaces for concept-level visual
reasoning.
Read the full abstract ▾
All authors Ruiyu Yan, Bowen Chen, Shaowen Wan, Lin Zhao
Artificial Intelligence
Character Training for Risk-Averse Agents
Arav Dhoot, Punya Syon Pandey, Jamie Johnson et al. (+3 more)
Risk aversion in resources could prevent misaligned AI
agents from causing catastrophic harm. Misaligned but risk-averse
agents would tend to favor safer strategies like making deals with humans over riskier strategies like rebelling. We train
agents to be risk averse through character training, finding that persona traits provide a robust mechanism for instilling risk preferences. To do this, we construct a model constitution describing constant absolute risk aversion (CARA) over an
agent's resources and instill it through on-policy
distillation. Despite never seeing the
benchmark's decision format during training, character-trained models are competitive with baselines trained directly on it, and generalise better than them out of distribution on two of our four models. We also modulate different aspects of the constitution, finding that
token budget and model choice are the most influential aspect of character training to instill risk aversion. We conclude from these results that character training is a promising and scalable way to instil broad dispositions, which we can use to our advantage in mitigating risk from misaligned AI
agents.
Read the full abstract ▾
All authors Arav Dhoot, Punya Syon Pandey, Jamie Johnson, Daniel Tan, Elliott Thornley, David Demitri Africa
Artificial Intelligence · Cross-listed from cs.CE
Neural topology optimization of ship structures under propulsion machinery vibrations
Shengyu Yan, Muhammad Muztahidul Hakim Zareer and Jasmin Jelovica
Ship structural vibrations contribute to noise, fatigue, and equipment damage, while dynamic-compliance
topology optimization can produce pathological designs near resonance. This study extends neural-reparameterized
topology optimization using a convolutional Kolmogorov-Arnold network (KATO) to forced-vibration design with active input power (AIP) as the objective. Applications include a 100 Hz engine-supporting deck panel and an 18 Hz thruster foundation frame. Helmholtz PDE filtering and Heaviside projection control feature sizes and manufacturing tolerance. Across both deck families, all eight optimized layouts reduce AIP relative to size-optimized references and, after finite-depth extrusion, also achieve lower static compliance. For unrestricted, manufacturing-aware, and stress-aware frame variants, KATO matches GCMMA in AIP within 0.5 dB while yielding 22-36x lower static compliance after matched-volume binary re-analysis. In a near-resonant 300 Hz case, both methods reduce initial AIP by more than 32 dB; KATO maintains a connected design, achieves 59x lower binary static compliance, and reduces maximum AIP over 1-500 Hz by 2.7 dB. KATO runs 6.4-10.4x faster than GCMMA for the implemented stress-aware formulations. The results demonstrate neural AIP-driven
topology optimization as an efficient approach for designing connected, feature-size-controlled ship structures with improved forced-vibration performance.
Read the full abstract ▾
Artificial Intelligence
Probability is Not Enough: Exploring and Counting Divergent Tokens for Reasoning Uncertainty Quantification in LLMs
Feiyang Li, Shengjing Liu, Qi Zhan et al. (+7 more)
As the chain-of-thought
reasoning capabilities of large
language models improve, evaluating and calibrating their
reasoning confidence is becoming increasingly important for quantifying the uncertainty of their answers. Current methods for estimating the confidence of large
language models are generally based on probabilities of selected key
tokens, but the underlying mechanism remains unclear. Our pilot study finds that replacing selected
token probabilities with coarse substitutes can also improve calibration, motivating us to further explore effective signals of model confidence. We introduce Divergent
Token Confidence (DTC), a framework that estimates confidence by counting
tokens at which two models strongly disagree during decoding. DTC identifies these divergent
tokens using the Jensen-Shannon divergence between next-
token distributions evaluated along the same
reasoning trajectory. We find that their count is almost negatively associated with answer accuracy, thereby serving as a simple yet effective signal for uncertainty quantification. DTC supports both white-box and black-box evaluation using auxiliary models, without explicit training and affecting the generation process. Experiments across multiple model families and six mathematical
benchmarks demonstrate improved calibration over probability-based and verbalized baselines. Under white-box evaluation, the count-only
estimator achieves an average expected calibration error of 13.0%, compared with 32.7%-42.4% for standard full-sequence confidence methods. In black-box settings, it also improves calibration over the original verbalized scores. For example, mean expected calibration error falls from 32.1%-40.2% to 13.7%-16.3% on DeepSeek-V3.2. These findings provide new insights for improving
reasoning uncertainty quantification in large
language models. The code is released at https://github.com/szu-tera/DTC.git.
Read the full abstract ▾
All authors Feiyang Li, Shengjing Liu, Qi Zhan, Sijie Cheng, Weiqing Wang, Hongwen Chen, Yuxuan Yang, Wen Wang, Yile Wang, Hui Huang
Artificial Intelligence · Cross-listed from cs.LG
Jaxolotl: A Unified High-Performance Benchmark Suite for LTL-Based Multi-Task RL
Mathias Jackermeier, Jacques Cloete and Alessandro Abate
Training
agents to follow arbitrary instructions is an important goal of multi-task reinforcement learning (RL). Linear temporal logic (LTL) provides a precise and structured formalism for specifying instructions to
agents, and has been successfully adopted for training generalist multi-task policies. However, differences in implementations, task distributions, and evaluation protocols make existing methods difficult to compare, while high computational costs limit the scale and statistical reliability of experiments. We introduce Jaxolotl, a unified high-performance
benchmark suite for multi-task LTL-RL to address these concerns. Jaxolotl provides a modular, end-to-end JAX implementation of six representative
algorithms and four environments, together with newly curated task suites and a standardised, statistically robust evaluation protocol. By precompiling symbolic task representations into static arrays, Jaxolotl enables fully JIT-compiled training and evaluation, achieving end-to-end speedups of up to $220\times$ and supporting controlled comparisons at substantially greater experimental scale. We use this framework to systematically evaluate existing approaches, revealing complementary strengths and limitations: general methods capable of non-myopic
reasoning struggle as the number of propositions grows, while methods with stronger scaling rely on environment-specific assumptions and suffer from myopia.
Read the full abstract ▾
Artificial Intelligence
UserProxyBench: Evaluating LLM User Simulators for Agent Benchmarks and Training
Ashish Jain and Armaan Sandhu
Interactive
agent benchmarks and multi-turn reinforcement learning increasingly place a second
language model in the role of the user. This simulated user controls what information the
agent receives and when, yet current
benchmarks score only the
agent and do not directly measure whether the user correctly executed its assigned role. We introduce UserProxyBench, an evaluation layer over the tau-bench family, and the User Fidelity Score (UFS), which measures adherence to the
benchmark's private user instructions using task-grounded rubric criteria scored independently of
agent success. Holding the
agent fixed at GPT-5.5 and varying only the user proxy across 375 enterprise tasks changes mean task reward by 15.2 points, while 24.4% of successful episodes contain a user-specification violation. The dominant failure is premature disclosure: users provide information before it is requested. This behavior has little effect on task reward, yet among successful episodes it causes the
agent to make 1.06 fewer tool calls on average, changing the interaction being evaluated while preserving the reward. Finally, across seven proxies we identify an empirical cost-fidelity frontier, enabling practitioners to select the least expensive simulator that satisfies a required fidelity level.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Gender bias across LLMs is common and highly heterogeneous
Edoardo Bolzoni and Valerio Capraro
Understanding gender biases in large
language models (LLMs) is increasingly important as these systems become embedded in decision-support tools with real consequences. Prior research has focused only on a small set of models, leaving open the extent to which gender biases are common and heterogeneous across LLMs. We address this gap across ten models released between April 2025 and June 2026, spanning nine vendors, using two paradigms: gender attribution to stereotyped phrases (Study 1) and moral judgment of abuse or torture against a woman or a man to prevent a catastrophic outcome (Study 2). In Study 1, two of ten models attributed masculine-stereotyped phrases to female writers more often than the reverse, while three models showed the opposite pattern. In Study 2, several models converged on a male-disadvantaging asymmetry that was directionally consistent with a documented human tendency to protect female targets from harm, though the specific conditions under which this asymmetry emerged varied by model; three other models, by contrast, showed no variation across conditions. These results indicate that gender-related biases are common in LLMs. Their direction and magnitude, however, are highly heterogeneous, to the point that some models behave in diametrically opposite ways to others. Bias
auditing should therefore be treated as an ongoing, multi-vendor process, rather than a one-time assessment.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.RO
doPlan: A Variable-Horizon Dataset for Multi-Stage Language-Conditioned Planning in Autonomous Driving
Parthib Roy, Yash Tandon, Marcus Blennemann et al. (+4 more)
Autonomous vehicles interacting with passengers through natural
language must reason beyond immediate commands. Passenger intent may span multiple stages of behavior, depend on future events, refer to surrounding
agents or landmarks, and remain relevant as driving conditions evolve. Existing
language-enabled driving
datasets largely focus on short, localized interactions, leaving these longer-horizon forms of passenger intent comparatively underexplored. We introduce doPlan, to our knowledge the first publicly available, human-annotated real-world
dataset designed to study passenger
language as persistent task context. Built on nuPlan, doPlan contains 5,154 human-written passenger instructions spanning 169.1 hours of cumulative instruction-aligned context over 50.9 hours of unique driving, with annotation windows ranging from 30.0 to 508.8 s. The annotations capture immediate, deferred, event-conditioned, persistent, and multi-stage passenger intent. The
dataset, annotation interface, and supporting resources are publicly available at https://github.com/Mi3-Lab/doPlan. We evaluate four
language-conditioned driving models and find that sensitivity to passenger
language does not reliably translate into behavior consistent with the requested direction. More broadly, among 2,161 examples with a matched future maneuver, the first associated maneuver occurs a median of 24.6 s after the evaluation point, and only 9.8% occur within the models' common 5 s prediction horizon. These findings highlight the need to connect persistent passenger intent with successive planning decisions. doPlan provides a setting for studying how unresolved goals can be retained, grounded in evolving scenes, and tracked across multiple stages, including how a planner determines when a future goal becomes relevant to the current plan.
Read the full abstract ▾
All authors Parthib Roy, Yash Tandon, Marcus Blennemann, Giovanni Tapia Lopez, Angel Martinez-Sanchez, Mohan M. Trivedi, Ross Greer
Artificial Intelligence · Cross-listed from cs.LG
Dr. OPD: Learning What to Follow for Optimal On-Policy Distillation of Large Language Models
Zhenyu Wang, Tianze Wang, Linjun Zhang et al. (+1 more)
On-policy
distillation (OPD) trains a student on its own generated responses using dense,
token-level supervision from a stronger teacher. Vanilla OPD treats all teacher signals equally, assuming that the teacher's supervision is equally important for every
token. However, teacher signals at different
tokens may have very different effects on the student's performance: some correct important
reasoning errors, while others have little effect on the final answer. Motivated by this observation, we introduce Dr. OPD (OPD Done Right), which defines the optimal weighted OPD to maximize the student's performance. We formulate Dr. OPD as a bilevel optimization problem in which the student learns from weighted teacher supervision, while the weights are selected to maximize the expected reward of the resulting student. To solve Dr. OPD, we develop an efficient iterative solver that updates the
token weights and student policy alternatively. At each round, it updates weights in closed form and then takes one gradient step on the resulting weighted OPD objective. Under regularity conditions, we show that this weighted update achieves a higher expected reward than a vanilla OPD update. Empirically, across strong-to-weak and same-size
distillation on math and code, Dr. OPD consistently outperforms all evaluated baselines. In particular, in the strong-to-weak
distillation setting, Dr. OPD improves average math performance by $9.7$ points over vanilla OPD, and enables the smaller student to surpass its larger teacher.
Read the full abstract ▾
All authors Zhenyu Wang, Tianze Wang, Linjun Zhang, Yifan Hu
Artificial Intelligence
Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation
Jaewon Chu, Ji Soo Lee, Jihwan Park et al. (+8 more)
An
agent skill is a reusable, actionable natural-
language artifact that guides an
agent to perform a task effectively under a given harness. Recent studies have explored the optimization of
agent skills, contributing to a growing collection of publicly available skills spanning diverse tasks, domains, and harnesses. Despite millions of publicly shared skills, existing skill optimization methods largely overlook this accumulated knowledge, instead relying solely on expensive
agent rollouts to iteratively refine skills for a target task. To address this, we propose
Retrieval-Augmented Skill Optimization (RASO), a framework that leverages an external skill corpus as prior knowledge throughout skill optimization. RASO retrieves relevant knowledge from existing skills and adapts it to the target task and harness via Cross-Harness Adaptation, accounting for mismatches in both domain and harness. RASO comprises two complementary stages:
Retrieval-Augmented Skill Initialization (RASI) constructs a knowledge-grounded initial skill without requiring
agent rollouts, while
Retrieval-Augmented Skill Update (RASU) iteratively refines the skill by retrieving external knowledge guided by execution feedback. Across four
agent benchmarks and two models, extensive experiments show that RASO consistently outperforms baselines without
retrieval-augmented skill initialization and updating.
Read the full abstract ▾
All authors Jaewon Chu, Ji Soo Lee, Jihwan Park, Dohwan Ko, Jeehye Na, Seunghun Lee, Taehoon Lee, Minseo Yoon, Minseok Joo, Yunyang Xiong, Hyunwoo J. Kim
Artificial Intelligence
PE-EK-PINN: Physics Embedding with Evolving Kernel for Scalable Physics-Informed Neural Networks
Huiwen Zhang, Feng Ye and Chu Ma
Physics-Informed Neural Networks (PINNs) embed governing equations into deep learning, but enforce them only through loss residuals, leaving highly oscillatory wave behavior to be discovered by optimization. As a result, methods that achieve relative $L_2$ errors below $10^{-3}$ on standard manufactured Helmholtz
benchmarks can fail on practical radiation problems involving singular excitations, absorbing boundaries, and wave fields spanning tens of wavelengths. Architectural physics
embedding addresses this limitation by factorizing the field into analytically derived oscillatory kernels and learnable envelopes. However, the kernel dictionary must be manually constructed and scales with the number of elementary units, growing exponentially with the depth of hierarchically structured systems such as
antenna arrays and metasurfaces. We propose PE-EK-PINN (Physics Embedded with Evolving Kernels), which treats physics kernels as reusable learned representations rather than fixed analytical inputs. A converged subsystem field is frozen and promoted to an evolved kernel, whose transformed copies are reused to represent higher-level configurations without deriving new governing equations. The resulting hierarchy makes the peak number of active kernels independent of system size and reduces cumulative training cost from $O(N)$ to $O(\log N)$. Experiments on dipole arrays, composite line-source geometries, and cross arrays demonstrate the dramatic training cost reduction, while achieving a reduced or comparable relative $L_2$ error. One notable example is PE-EK-PINN solves a $256$-dipole array more than 30 times faster than direct PE-PINN.
Read the full abstract ▾
Artificial Intelligence · Cross-listed from cs.CL
Auditing Long-Term Memory Evaluation: Repeated Judging, Reader Variation, and Negative Controls
Christopher J. Chanhnourack
This report audits evaluation of a long-term-
memory retrieval chain on the 500 LongMemEval-S development questions. Its strongest historical reader lane scores 479 and 475 under an adapted GPT-4o rubric; re-judging the same pass-1 answers changes three labels and yields 478. Fixed-answer knowledge-update re-scoring gives 70/72 under the upstream template and 69/72 under the modified template. Reader lanes span 93 to 479 on fixed packets; paired tests between the two strongest historical lanes establish neither superiority nor equivalence. A different-family reader, configured without client tools or operator files, scores 474, 1.0 percentage point below the headline pass (paired 95% interval [-3.0,+1.0]). Live reader request bodies were not retained. With the same requested reader label, route and judge snapshot, the full package scores 474 versus 454 for baseline sessions, a difference of +4.0 percentage points [95% interval +2.2,+6.0]. Eighteen of the 23 gains, and no losses, occur where baseline packets lacked listed evidence; this post-hoc split does not identify a component effect. In recovered LoCoMo data,
token-F1 gains do not survive answer-line extraction. A negative control rejects a verifier that repairs three wrong drafts but breaks eleven correct ones. All questions were used to develop the components; no untouched holdout was evaluated. These findings do not establish a new leaderboard leader or transferable
memory advantage. The A/D comparison has one pass per arm, including six reused identical-
prompt outcomes, with no pinned reader snapshot; B/C and repeats remain unrun. Original headline requests cannot be reconstructed and stages 1–4 remain closed. Released artifacts support packet inspection and saved-verdict recounting and re-scoring; they do not reconstruct the method.
Read the full abstract ▾
Artificial Intelligence
Brain-SAD: A Brain-Inspired Safe Autonomous Driving Control Framework with Dynamic Fear-Oriented Constraint on Dual-Policy
Huan Rong, Chao Yin, Anouar Imel et al. (+2 more)
Constrained Reinforcement Learning has recently gained increasing
attention in the field of Safe Autonomous Driving, where the general mechanism is to maximize the expected reward while keeping the overall action risk bounded. In this way, the safety issues arising in AD can be mitigated through constrained actions. However, existing Constrained RL methods still lack dynamics on the imposed constraints. For instance, the action cost adopted by the existing Primal-Dual/soft-constrained methods is often defined as static state-to-cost mapping, and the safe-action projection in hard-constrained methods relies on the static projection with the fixed feasible region boundary estimated from offline demonstrations. The above drawback tightly couples the imposed constraints to the training scenarios, leaving the AD policy hard to handle different interaction scenarios, due to the improper state-level action-cost and the static projection boundary. Consequently, in this paper, we propose
Brain-SAD, a
brain-inspired safe autonomous driving control framework with dynamic fear-oriented constraints. By perceiving the current vehicle-interaction scene,
Brain-SAD generates dynamic fear signal as fear reaction to online decide long-term policy for regular interaction or short-term policy for urgent-collision defense. In such two policy, the above fear-reaction will be constructed as the dynamic fear constraints, respectively reflecting the overall fear cost directly coupled with action-impact, and the dynamic fear boundary of the feasible region derived from different risky neighbors, both of which will in turn serve for the online policy optimization. Experimental results show that
Brain-SAD outperforms existing methods, achieving higher success rate in shorter task-completion and collision-recovery time, and exhibits stronger reliability across continuous intersections of fluctuating complexity.
Read the full abstract ▾
All authors Huan Rong, Chao Yin, Anouar Imel, Yijie Xia, Tinghuai Ma
Artificial Intelligence · Cross-listed from cs.CV
From Unity Simulation to Diffusion-Based Augmentation: Quantifying Dataset Balance for Robust Object Detection
Mohamed Benkedadra, Aissa Saoudi, Maxime Gloesener et al. (+2 more)
Modern computer
vision models achieve high accuracy when trained on large-scale annotated
datasets. In critical domains such as construction safety monitoring, data collection is costly, hazardous, and ethically constrained. This paper presents a systematic study comparing two complementary data generation paradigms, (1) Unity Simulation-based rendering and (2) Controllable
Diffusion-based generation (CIA), for object detection under real data-scarce conditions. A unified experimental framework enables controlled
dataset mixing across real, simulated, and generative sources, while maintaining identical model and training settings. Quantitative evaluation using Precision, Recall, mAP, and custom $\Delta$-metrics, reveals that neither simulation nor generative augmentation alone achieves optimal transferability. Unity-only training yields an mAP@0.5 drop of $-50\%$ relative to real data, while CIA-only training shows a milder $-16.5\%$ degradation. Hybrid compositions significantly improve performance, with the 90% real + 10% Unity configuration achieving the best overall mAP@0.5 of $62.68\%$ ($+7.64\%$ over baseline), and the 90% real + 10% CIA configuration maximizing precision at $74.45\%$. Results demonstrate that limited synthetic inclusion enhances generalization, while excessive substitution induces domain drift.
Read the full abstract ▾
All authors Mohamed Benkedadra, Aissa Saoudi, Maxime Gloesener, Sidi Ahmed Mahmoudi, Matei Mancas
Artificial Intelligence
HARISSA: Inference-Time Self-Checks for Efficient and Safe Local Language Model Deployment
Kenan Alkiek, Moontae Lee, David Jurgens et al. (+1 more)
Running a
language model locally offers advantages in
privacy, latency, and cost, but local hardware fits only small models, which are less capable than frontier models. The usual remedy for a hard query, escalating it to a cloud model, gives up the
privacy and cost advantages of running locally. A deployment that stays local faces two decisions for hard queries instead. First, it can spend more computation on a query, e.g.,
reasoning before answering, which raises accuracy at a cost in latency, so it must decide which queries are worth the extra computation (efficiency). Second, some queries are beyond the local model, and delivering a wrong answer is worse than deferring the query to a human in the loop, so it must decide which answers are safe to deliver (safety). We show that both decisions can be made from the model's own hidden states. The prefill state, computed before any
token is generated, predicts whether the model will answer correctly, and the answer state, at the end of the generated answer, predicts whether that answer is correct. HARISSA fine-tunes the model so that both states predict correctness, then makes both decisions with one policy that cascades through the ways of answering from cheapest to most expensive, skipping a way the prefill state predicts will fail and deferring the query when the answer it stops with is predicted wrong. On a device running a single model, HARISSA is within one accuracy point of chain-of-thought at 2.7 times lower latency. On a server holding four sizes of one model, HARISSA is more accurate than the FrugalGPT and Self-REF cascades at the same latency, and at the same deferral rate the answer state leaves fewer wrong answers than the standard confidence signals in five of six task and setting pairs.
Read the full abstract ▾
All authors Kenan Alkiek, Moontae Lee, David Jurgens, V.G.Vinod Vydiswaran
Artificial Intelligence
Diagnosing and Improving Probabilistic Reasoning in Large Language Models
Huaman Sun, Dingcheng Wang, Jason Hartline et al. (+1 more)
Large
language models (LLMs) are increasingly proposed as decision assistants who must reason probabilistically from available evidence under explicit decision costs. We propose a decision-theoretic framework that decomposes LLMs' decision loss into two components: forming accurate beliefs from provided evidence and translating those beliefs into actions that optimize a provided utility function. Using a synthetic
benchmark with known ground truth, we apply the decomposition to characterize probabilistic
reasoning in frontier and open-sourced models. We further evaluate whether RL interventions targeting beliefs, decisions, or both improve these components across three domains, whether improvements transfer across components and elicitation formats, and whether decision performance can improve without improvement in belief formation. We find that targeting one component of probabilistic
reasoning redistributes decision loss, improving the target without necessarily transferring to others, and that jointly targeting belief formation and decision-making improves both but hinges on matched formats between training and evaluation.
Read the full abstract ▾
All authors Huaman Sun, Dingcheng Wang, Jason Hartline, Jessica Hullman
Artificial Intelligence · Cross-listed from cs.LG
No Scale Left Behind: Multi-Scale Autoencoder with Bi-directional Attention for Time Series Anomaly Detection
Jiaheng Guo, Haochen Zhang, Yu-Chao Huang et al. (+3 more)
Time series anomaly detection (TSAD) plays a crucial role in healthcare, finance, industrial monitoring, and other sectors. Within and between these settings, anomalies span vastly different temporal scales, from sub-second point spikes to multi-hour drift patterns. However, most existing TSAD methods commit to a single temporal granularity, and multi-scale designs either analyze different scales in isolation or are constrained to a predefined coarse-to-fine hierarchy, both failing to sufficiently capture multi-scale interactions. To resolve this limitation, we propose Multi-Scale Autoencoder with Cross-Scale
Attention for TSAD (MSCAD), a simple yet powerful semi-supervised TSAD framework founded on parallel autoencoder branches corresponding to different patch sizes. A stack of symmetric bidirectional cross-scale
attention blocks enables every pair of scales to exchange information before reconstruction without allowing any single scale to be privileged. On the comprehensive TSB-AD
benchmark (40
datasets, 530 series), MSCAD achieves large performance gains against 50 baselines across multiple metrics, with VUS-PR of 0.57(+9.6%) on the univariate split and 0.47(+9.3%) on the multivariate split compared to the state-of-the-art.
Read the full abstract ▾
All authors Jiaheng Guo, Haochen Zhang, Yu-Chao Huang, Jinhao Duan, Nicholas Konz, Tianlong Chen
Artificial Intelligence · Cross-listed from cs.CL
BITEM at the NTCIR-19 R2C2 Task: Predicting Confidence from Agentic RAG Pipeline Signals
Julien Knafou, Luc Mottin, Alexandre Flament et al. (+3 more)
The BITEM team entered both subtasks of the NTCIR-19 R2C2 task with a single agentic pipeline, in which a model searches, reads and records evidence over a movie corpus while an orchestrator holds the record and rules on what may be submitted. A claim is admitted only once an entailment cascade has checked it against the passage it cites, and an answer is released only once enough checked evidence stands behind it. Each question is run three or four times, every pass retrieving from a corpus stripped of what the earlier passes have already seen. The confidence filed with each answer is computed by the orchestrator from what the run leaves behind and is never asked of the model, which is offered no way to rate itself. The two
retrieval runs placed 4th and 5th of 22, pooling the passes was worth 0.0709 nDCG@20, and the gain was largest on the multi-hop and post-processing-heavy questions, where the organisers rank the pooled run top of the field. Sixteen of the 25 answer runs were built on passages these two runs supplied, 12 of them filed by other teams. HMR rewards a system whose confidence is high where it answers right and low where it answers wrong. The pipeline reached an accuracy of 0.9219, 6th of 25, while the confidence filed with those answers gave an HMR of 0.4915, 13th. A few rules crafted over those same recorded signals, with no further model call and no further
retrieval, raise that to an accuracy of 0.9375, 5th, and an HMR of 0.6985, 9th. Ranking on HMR alone can reward a system for answering wrongly with low confidence, so we propose accHMR, the accuracy multiplied by HMR, which reports the reward in proportion to the accuracy, and on which the revised rules would have scored 0.6549, 5th. For future work, fitting a model on the numbers the pipeline already produces, rather than writing such rules by hand, would be a real step forward.
Read the full abstract ▾
All authors Julien Knafou, Luc Mottin, Alexandre Flament, Paul van Rijen, Esteban Gaillac, Patrick Ruch
Artificial Intelligence
Which Attention Heads are like the Human Head? Not the Ones that Compute
Christopher Pinier, Gustaw Opiełka, Hannes Rosenbusch et al. (+3 more)
Brain-AI
alignment is often interpreted as a sign that model and
brain perform similar computations. Whether the aligned units are causally involved in model computation is rarely checked. On an abstract pattern-completion task (AAABAAA $\rightarrow$ B), we compare LLM
attention-head representations with human
EEG and test how ablating those heads affects task performance.
Alignment and causation dissociate:
brain-aligned heads contribute to performance, but their removal is substantially less disruptive than removal of heads selected via attribution patching. We compare two head sets that prior interpretability work defines without reference to the
brain: concept vectors (CVs), which represent abstract patterns across formats, and function vectors (FVs), selected for their contribution to correct-answer prediction.
Brain alignment shows little association with FV scores, while its association with CV scores varies across models. Among
brain-aligned heads, we find recurring
attention profiles: one emphasizes distinctive elements (novelty heads), the other repeating elements (repetition heads). The novelty family tracks salience and attends to the same elements that humans look at, yet its removal is less damaging than random ablation on average. Repetition heads contribute modestly to performance and are associated with abstract-pattern representation (CVs). Across 17 models spanning 3B-72B parameters, FV-ranked removal is substantially more disruptive than
brain-ranked removal.
Brain alignment thus captures how the model reads the stimulus, and only faintly captures how it represents the pattern and solves the task.
Read the full abstract ▾
All authors Christopher Pinier, Gustaw Opiełka, Hannes Rosenbusch, Taylor Webb, Michael D. Nunez, Claire E. Stevenson
Artificial Intelligence
KV-Kaizen: Learning Context-Adaptive Cache Compression Choices
Joao Monteiro, Louis Béthune, Anastasiia Filippova et al. (+3 more)
As the context size of text processed with an LLM grows, the size of KV caches can outstrip the
memory allocated for the original model weights. This impacts LLM throughput negatively, since decoding is
memory-bound and decode cost grows with cache size. Recent work alleviates this bottleneck by discarding the least relevant
tokens. Eviction introduces a tension, since a one-off decision to discard content may prove detrimental later. Instead, we focus on alternative choices that can lead to cache compression without evicting
tokens. We achieve this by learning a selector that is able to produce, based on context, a per-layer cache configuration towards an overall compression budget. The selector operates along three axes: sharing one cache across layers (depth), caching at fewer bits (precision), or truncating the low-rank latent cache representations (rank). We call the resulting method KV-Kaizen, for the many small per-layer choices it compounds. We observe that these interventions taken independently and uniformly over all layers limit achievable compression because they degrade accuracy. Crucially, composing them locally and adaptively to the context can instead preserve accuracy while achieving large
memory savings. At inference, the selector runs once, before pre-fill. In evaluations on instruction following and
reasoning tasks, our selectors reach the Pareto frontier of accuracy against cache size, against learning-free and post-hoc baselines. On long-context tasks, KV-Kaizen improves on eviction and can be composed with it, reaching a 32x smaller decode-time cache on a 14B model while preserving accuracy. A 4x cache size reduction incurs no accuracy degradation from 7B parameters up, and a compressed model is more accurate than a smaller uncompressed one with the same cache size. Together, these findings support pre-training large models and compressing them only afterwards.
Read the full abstract ▾
All authors Joao Monteiro, Louis Béthune, Anastasiia Filippova, Sonia Laguna, David Grangier, Marco Cuturi
Artificial Intelligence · Cross-listed from cs.LG
$S^3$: Spectral Null-Space Swap Makes Reasoning Models Efficient
Hongbo Ma, Sansheng Cao, Jiajun Fan et al. (+2 more)
LLMs trained with Chain-of-thought excel in
reasoning capability, but often come with excessive
token cost. We find that the core of
reasoning capacity lies in the Thinking model's weight component within the null space of a projection defined by the corresponding Non-thinking model's dominant singular directions, and removing the subspace component can largely improve
reasoning efficiency without hurting the accuracy gained during thinking-mode post-training. Unlike existing efforts that mostly operate within the dominant subspace, we are the first to unveil the critical role of the null space and harness it for model optimization. Motivated by this finding, we propose Spectral Null-Space Swap ($S^3$), a training-free composition of paired Non-thinking and Thinking checkpoints. Our method keeps the Non-thinking model inside its own dominant subspace and takes the Thinking checkpoint outside it, improving
reasoning efficiency while maintaining accuracy. We extensively evaluate $S^3$ on 2B-30B dense and mixture-of-experts (MoE) architectures spanning 28 evaluation environments across mathematical,
multimodal, and audio
reasoning domains. $S^3$ establishes new empirical Pareto Frontiers among training-free model composition strategies: across all settings, it reduces inference
token overhead by an average of 27.4% compared to full Thinking models while simultaneously improving overall task accuracy by 1.0 percentage point (e.g., yielding +8.3% accuracy on HMMT25 alongside a 33.0%
token speedup). We further use
attention entropy for explanation and find that the retained component produces more concentrated
attention, and we use a simplified analytical model about optimization to demonstrate why null-space can effectively reduce
attention entropy, thereby improving the efficiency of
reasoning.
Read the full abstract ▾
All authors Hongbo Ma, Sansheng Cao, Jiajun Fan, Bangji Yang, Ge Liu
Artificial Intelligence · Cross-listed from cs.LG
On Trajectory-Aware Training for Masked Diffusion Language Models
Manuel Madeira, Amitis Shidani, Alice Bizeul et al. (+6 more)
Masked
diffusion models (MDMs) generate text by unmasking several
tokens per step, but they are trained and sampled under different conditions. The model is trained on randomly masked sequences, whereas inference follows a trajectory shaped by the model's own predictions. Additionally, each step has no access to what the previous one computed. Recent methods narrow these limitations from separate angles, leaving open how these choices interact. We introduce PUMBA, a unified framework for trajectory-aware training that trains the denoiser on consecutive steps of policy-induced trajectories, passes information between steps, and optimizes them jointly by backpropagation through time. A controlled study of this design space shows that i) exact train–inference
alignment fails due to local overfitting, whereas a looser
alignment still brings training masks closer to those seen at inference; ii) passing continuous information outperforms discrete gradient
estimators through the commitment at each step; and iii) performance improves as backpropagation through time spans more steps, which we support theoretically. Combined, these components match the best checkpoint of a same-size autoregressive model. Building on these findings, we scale PUMBA to supervised fine-tuning of LLaDA-8B, where it improves the trade-off between performance and number of function evaluations (NFEs) in both full-canvas and block
diffusion generation. At matched performance, it needs up to 22% fewer NFEs than standard fine-tuning with twice the budget in full-canvas generation, and up to 26% fewer than standard fine-tuning for the same number of steps in block
diffusion.
Read the full abstract ▾
All authors Manuel Madeira, Amitis Shidani, Alice Bizeul, Victor Turrisi, Louis Béthune, Bhavika Devnani, Dan Busbridge, Pierre Ablin, João Monteiro
Artificial Intelligence · Cross-listed from cs.CR
Dagger: Decoupling-based Model Stealing Attack against Graph Neural Networks
Ying Song, Xiaowei Jia and Balaji Palanisamy
As Graph Neural Networks (GNNs) are widely deployed as Machine Learning-as-a-Service (MLaaS) APIs, model stealing attacks have emerged as a critical security threat. By querying a victim model's black-box API, an adversary can construct a functionally equivalent surrogate model, compromising proprietary intellectual property and downstream security. Existing GNN stealing attacks, however, rely on overly permissive assumptions, such as soft-label outputs, large query budgets, full-graph query access, and prior knowledge of victim backbones that rarely hold in real-world deployments. In this work, we formalize a strictly constrained black-box, hard-label and backbone-agnostic threat model for GNN stealing attacks under a tight query budget. Given these realistic restrictions, we identify four fundamental challenges: sparse local structures and isolated nodes that degrade victim label quality, insufficient supervision signals, systematic imbalance with incomplete class coverage, and backbone mismatch. To address these interlocking barriers, we propose Dagger, a novel two-phase decoupling-based attack framework. Specifically, in Phase 1, Dagger pre-trains a surrogate using decoupled information propagation to preserve structural context over sparse local subgraphs while handling isolated nodes, combined with
manifold-level node mixup to synthesize continuous supervision signals and smooth decision boundaries. In Phase 2, Dagger freezes the encoder and fine-tunes the classifier head via class-balanced sampling paired with logit adjustment to rectify severe query imbalance without requiring extra victim queries. Extensive experiments across four
benchmark graphs and four GNN backbones demonstrate that Dagger consistently outperforms state-of-the-art GNN stealing attacks, achieving up to 18.16% higher fidelity while only utilizing 12.23$\times$ fewer queries than the strongest baseline.
Read the full abstract ▾
Artificial Intelligence
SelfSearch: Reward-Free Search for Self-Improving Agents
Jungwoo Yang, Injin Kong and Yohan Jo
Advances in the coding capabilities of LLM
agents allow them to inspect and modify their own instructions, tools, and execution procedures. Existing approaches use this ability to search for improved
agents through repeated downstream evaluation, which incurs substantial costs and ties the search to the evaluated tasks. We introduce SelfSearch, a reward-free search procedure in which
agents modify themselves using records of previous self-improvement episodes. These records capture the
reasoning, tool actions, and outcomes of earlier modification attempts, providing concrete experience for improving both task solving and self-modification. Without downstream reward signals during search, SelfSearch improves population-mean success over the initial
agent in all six model–
benchmark settings, with individual
agents gaining up to 11.2 percentage points on Terminal-Bench 2.1. On SWE-bench
Multilingual, an
agent improves success by 5.0 percentage points while reducing execution cost by 38.5% on tasks solved by both the initial and evolved
agents. SelfSearch achieves competitive task success with evaluation-guided search baselines at lower search cost. With only \$4.03 in search cost, it produces a harness that solves 82.0% of Terminal-Bench 2.1 tasks with DeepSeek V4 Flash under the settings of a public nine-harness comparison, matching the top-scoring harness, Codex. These results suggest that experience gained through self-modification can improve
agents' downstream capabilities and efficiency.
Read the full abstract ▾
Artificial Intelligence
BrainNet Studio: A Unified Toolkit for Brain Network Construction, Intelligent Analysis, and Visualization
Xiwei Zeng, Shengrong Li, Yiheng Liu et al. (+3 more)
Brain networks characterize structural and functional relationships among
brain regions and support research on cognition,
brain disorders, and
brain-computer interfaces. Their time-varying
topology and higher-order spatiotemporal dependencies are not adequately represented by conventional static networks. Existing tools primarily focus on static connectomes and provide limited integration of dynamic network modeling with modern graph and sequence learning methods. We present BrainNet Studio, an integrated toolkit for static and dynamic
brain network analysis. It provides a unified workflow encompassing network construction, feature extraction, predictive modeling, candidate biomarker identification, visualization, and assisted interpretation. The toolkit integrates 27
algorithms, including deep learning, graph neural networks, and spatiotemporal sequence models, to support classification and the identification of discriminative
brain regions and connections. A large
language model generates researcher-verifiable summaries of functional connectivity, structural connectivity, and structure-function coupling at individual and group levels. Within a consistent computational framework, users can configure analytical tasks, compare methods, inspect outputs, and extend functionality without repeatedly assembling application-specific pipelines. BrainNet Studio provides a practical and extensible platform for connectome analysis in cognitive neuroscience, exploratory studies of
brain disorders, and
brain-computer interfaces. The toolkit is publicly available at https://github.com/xbrainnet/Brainnet-Studio.
Read the full abstract ▾
All authors Xiwei Zeng, Shengrong Li, Yiheng Liu, Chunwei Tian, Daoqiang Zhang, Qi Zhu
Artificial Intelligence
Topological Coherence for Self-evolving Multi-agent Systems
Sen Zhao, Ruiqi Kong, Zuyu Zhang et al. (+4 more)
Complex tasks inherently couple workflow structure,
agent responsibility, collaboration, and
memory access: task regions delimit responsibility and tool scope, cross-region dependencies give rise to handoffs, and ownership boundaries delimit private and selectively shared
memory. Existing methods can jointly optimize
agent and communication structures, yet such optimization does not by itself require responsibility, handoff, and
memory boundaries to remain consistent with task dependencies. We term this requirement topological coherence. We introduce TOCOMAS, a
Topology-Coherent Multi-
Agent System. TOCOMAS grounds a task graph in tool interfaces, organizes compatible task nodes into reusable responsibility domains, and derives dependency-induced and profile-conditioned collaboration together with boundary-regulated
memory visibility. During online self-
evolution, TOCOMAS proposes coupled changes to
agent, collaboration, and
memory policies, retaining for subsequent tasks only candidates that satisfy structural constraints and improve evaluated reward. Across BBEH, WorkBench, SWE-Bench-Verified, and CoMemBench, TOCOMAS improves task success over baselines across backbones. CoMemBench also shows gains over the self-evolving baseline in verified progress, handoffs, and
memory isolation.
Read the full abstract ▾
All authors Sen Zhao, Ruiqi Kong, Zuyu Zhang, Lifeng Shen, Xinyu He, Xu Zhang, Qinghua Zhang
Artificial Intelligence
Video-RSI: Recursive Self-Improvement of Video Understanding Agents via Harness Evolution
Bingjun Luo, Jialin Guo and Siqi Li
Video understanding
agents acquire evidence through an executable harness that controls what they observe and how they use those observations. However, execution traces contain only the evidence acquired by the current harness, leaving competing explanations for failure unresolved and limiting the basis for self-improvement. We introduce
Video-RSI, a framework for recursive self-improvement in which a
video understanding
agent uses its own
language model to revise its harness. Through active
video investigation, the model revisits the original training
videos to test competing failure explanations with additional observations, grounding proposed changes in evidence beyond the existing trace. Cost-aware harness
evolution turns these diagnoses into reusable revisions and determines which revisions to retain by considering both answer accuracy and visual cost. Across our evaluation settings on
video understanding
benchmarks, the evolved
agent improves accuracy while processing fewer frames and achieves competitive accuracy-efficiency trade-offs against existing
video understanding
agents. These results demonstrate the potential for
video understanding
agents to improve their own evidence acquisition and use through harness
evolution. Code is available at https://github.com/bingjunluo/
Video-RSI .
Read the full abstract ▾