Sign in

Category: Other

  • ReTAC: Residual Test-Time Agentic Computation for Video Spatial Reasoning

    ReTAC: Residual Test-Time Agentic Computation for Video Spatial Reasoning

    arXiv:2610.16315v1 Announce Type: new Abstract: Test-time agentic computation can improve multimodal large language models (MLLMs) through planning, tool use, iterative perception, and reflection, but indiscriminate computation may duplicate resolved work, introduce noisy evidence, and perturb correct predictions. We propose that such computation should be residual: allocate additional computation only to requirements unresolved by the base model and, after a localized failure, recompute only the affected states. We instantiate this formulation in ReTAC, a training-free multiagent framework for video spatial reasoning. ReTAC organizes supplementary computation around unresolved requirements. It plans ordered steps to acquire missing spatial evidence and combines the observations with compatible native evidence for reasoning. In addition, it uses stage-aligned verification to localize failures to planning, perception, or reasoning. Dependency-based recovery recomputes only affected states while reusing unaffected ones. Extensive experiments show that ReTAC achieves the highest overall score among the compared methods across three mainstream MLLMs and two widely adopted benchmarks. Further analyses show that gains from additional computation depend not only on how much is used, but also on where it is allocated and which valid intermediate states are preserved.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.16315

  • HyWe: Unifying Search and Operation for Real-World Hybrid Web Tasks

    HyWe: Unifying Search and Operation for Real-World Hybrid Web Tasks

    HyWe: Unifying Search and Operation for Real-World Hybrid Web Tasks

    arXiv:2610.16319v1 Announce Type: new Abstract: Real-world hybrid web tasks need both information gathering and page interaction, yet search-based and operation-based agents are developed and evaluated separately. To bridge this gap, we introduce HyWe, a framework that unifies both capabilities within one model and trajectory. Its two modes use dedicated prompts and tool sets to sustain sub-goal execution; explicit switching selects the needed capability, and shared history lets each mode build on the other's findings. To provide demonstrations of these behaviors, we develop HyWeCollector, a fully automatic pipeline that uses task prototypes, four switching patterns, and multi-agent synthesis to produce verified hybrid trajectories. We train HyWe-35B on these demonstrations to unify efficient information gathering and browser interaction in a single 35B web agent. To evaluate hybrid task completion, we introduce HyWeBench: 100 human-written tasks on websites distinct from training, with human-written sub-goal checklists and an outcome-based evaluation pipeline. Hybrid training enables HyWe-35B to achieve 47.0% success on this benchmark, improving on the untrained base model by 19.0 percentage points and outperforming existing search-based and operation-based agents. Even before training, the same base model solves 28.0% of tasks with HyWe, versus 11.0% with all tools under one prompt. Beyond hybrid tasks, HyWe-35B achieves 59.0% and 88.3% success on Online-Mind2Web and WebVoyager, outperforming existing open-source baselines and cutting action cost per successful task by 48.3% and 51.9% compared with Fara-7B.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.16319

  • When a Conceptor Complement Becomes Gain: Operator Geometry and Behavioral Attribution in Language Models

    When a Conceptor Complement Becomes Gain: Operator Geometry and Behavioral Attribution in Language Models

    When a Conceptor Complement Becomes Gain: Operator Geometry and Behavioral Attribution in Language Models

    arXiv:2610.16325v1 Announce Type: new Abstract: When a steering intervention changes a language model's behavior, which part of the intervention deserves the credit? We test this question for a target-centered, scaled conceptor complement by removing its fitted covariance filter while preserving the same target-specific center and gain. At the original aperture $\alpha=.05$ and gain $\beta=2$, all 21 fitted maps across three models and seven targets expand every direction at the generation intervention layers. The matrix correction is $0.093\%$–$7.815\%$ of the matched-control displacement on held-out extraction activations. In 480 paired comparisons within a 1,920-response study, retaining the matrix changes many individual texts but does not establish a consistent additional target-suppression benefit on the four-target panel. A geometric aperture sweep shows that the operating regime changes with the filter setting. Separately, an invertible soft filter preserves what an unrestricted affine readout can recover, whereas dedicated erasure methods reduce prediction by newly fitted probes. Together, the results show why a whole-intervention comparison cannot by itself attribute generated behavior to the fitted matrix: analyze the complete transformation, hold shared components fixed, and test its output consequences directly.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.16325

  • REVEAL: Reverse Engineering Agentic Latents from Frontier-Model Traces

    REVEAL: Reverse Engineering Agentic Latents from Frontier-Model Traces

    REVEAL: Reverse Engineering Agentic Latents from Frontier-Model Traces

    arXiv:2610.16288v2 Announce Type: new Abstract: Frontier LLM agents perform complex interactive tasks, but their inference costs motivate transferring their experience to smaller open-source agents. Distillation and latent communication typically require target-model training or access to source-model internals. We study how textual frontier-model trajectories can provide reusable local controls for a frozen agent. Inspired by protocol reverse engineering, we introduce $\textit{Agentic Latents}$, comprising anchored states and dynamic profiles of feedback–response cycles elicited by replay in the target model. Our training-free framework, $\textbf{REVEAL}$ ($\textbf{REV}$erse $\textbf{E}$ngineering $\textbf{A}$gentic $\textbf{L}$atents), uses these profiles and trajectory outcomes to match and select local events from successful and failed rollouts of the same task and source model. Their response-transition contrasts yield a target-specific steering direction, applied before each response. Within-benchmark evaluations on Terminal-Bench 2.1 and Humanity's Last Exam with tools report higher accuracy than unmodified agents across three targets. Representation analyses and behavioral case studies support reusing frontier-model experience as local activation control.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.16288

  • Memory-Efficient Integer-Only Training of Deep Neural Networks

    Memory-Efficient Integer-Only Training of Deep Neural Networks

    Memory-Efficient Integer-Only Training of Deep Neural Networks

    arXiv:2610.16298v1 Announce Type: new Abstract: Training neural networks in reduced precision can yield significant efficiency gains, yet all existing methods that scale to standard computer vision benchmarks retain floating-point in at least one stage, typically the weight update or optimizer state. We present a training algorithm that scales to modern deep neural networks, in which every tensor (weights, gradients, and activations) is stored as INT8, and every operation (forward pass, backward pass, weight update, optimizer update) is performed in integer arithmetic. Specifically, tensors are stored as signed integer mantissas paired with explicit power-of-two exponents, on which integer-only operations are performed using five custom composable building blocks (products, sums, divide-by-constant, nonlinear functions, and weight updates). This allows complete implementation of trainable integer layers, including convolutions, batch and layer normalization, softmax, and GELU. A per-group velocity mechanism with independent exponent tracking preserves gradient precision across neurons and channels with diverse magnitudes. As every tensor fits in INT8, training memory is roughly 4x smaller than the FP32 baseline. We validate our training algorithm on CNNs (ResNet-18/34/50/101, MobileNetV2) and Vision Transformers (ViT-Ti / B), demonstrating for the first time that training neural networks with INT8 tensors and integer arithmetic can achieve competitive accuracy on CIFAR-10, CIFAR-100 and ImageNet at a reduced memory budget.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.16298

  • FON: A Draft-Revise Dual-Organ Language Model without Sequence-Level Quadratic Attention

    FON: A Draft-Revise Dual-Organ Language Model without Sequence-Level Quadratic Attention

    arXiv:2610.16301v1 Announce Type: new Abstract: Self-attention assigns two functions to one mechanism-where to read and how to mix-at the price of O(L^2) training, an O(T) decode state, and position signals bound to the training length. Existing attention-free alternatives all optimize the single function of generation. We propose FON (Fusion-Organ Network), which differentiates one weight stack into a drafting organ (multi-tap learnable delays + content-adaptive recursion; causal, O(S) training, O(1) decode state, no sequence-level quadratic attention) and a revision organ that re-processes the written prefix through multi-scale ripple kernels injected via weak gates, never generating. At 30M parameters, iso-parameter and iso-token budget, FON reaches perplexity 131.03 on WikiText-103, beating Transformer (197.73) and Mamba2 (152.53); the advantage persists under all depth-aligned baselines and at the 70M tier (-20.8%). At 8x length extrapolation FON degrades by ~8-9% without positional-encoding engineering, between ALiBi and RoPE. The revision channel provides a structural pathway for in-domain infilling that causal architectures lack in principle (+19% over on-demand coupling), at a perplexity cost indistinguishable within measurement precision. We report all costs and boundaries: impaired long-range retrieval, synthetic-task disadvantages, weaker out-of-domain code infilling than a same-recipe Transformer, and a 6.5-12.3x wall-clock gap.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.16301

  • Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment

    Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment

    Narrative Paradoxes in LLM Inference: Shaping Reasoning Trajectories toward Misalignment

    arXiv:2610.16312v1 Announce Type: new Abstract: Explicit reasoning in large language models (LLMs) is often associated with reliability, yet it can still pose risks when a model infers harmful goals under a benign context. We identify a distinct challenge: ensuring the safety of the \emph{multi-step reasoning process} itself, where locally coherent steps may still lead to globally harmful outcomes. To explore this vulnerability, we propose PDRA (Paradox-driven Reasoning-based Attack), a novel attack method that programs a harmful reasoning trajectory. PDRA first constructs a paradoxical narrative core by pairing a malicious actor (e.g., a terrorist) with a benign task (e.g., writing a safety bulletin). It then embeds this core into a structured analytical framework that forces the model through a mandatory three-stage analysis — surface purpose, latent intent, and operational reconstruction — guiding it to produce detailed harmful content while maintaining narrative coherence. Mechanistically, we show PDRA steers the model's internal representations away from refusal-related patterns, suppressing safety-triggering lexicons while activating planning-oriented terms. Empirically, PDRA achieves state-of-the-art attack success rates across diverse LLMs with high efficiency. \textcolor{red}{\textbf{Warning:} This paper may contain sensitive content.}

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.16312

  • ScreenASR-Bench: A Tiered Benchmark for Speech Recognition with Visual Context

    ScreenASR-Bench: A Tiered Benchmark for Speech Recognition with Visual Context

    arXiv:2610.16260v1 Announce Type: new Abstract: Current ASR models perform well on general benchmarks but still struggle with acoustically ambiguous words. Visual context can aid recognition in screen-based scenarios, yet existing benchmarks provide limited insight into the benefits of different types of visual evidence. To address this gap, we introduce ScreenASR-Bench , a tiered benchmark with three progressively challenging levels: Explicit Textual Evidence (ETE), based on direct on-screen text; Explicit Visual Evidence (EVE), using visible content rather than on-screen text; and Implicit Semantic Evidence (ISE), requiring scene-level inference. Extensive experiments on ASR models, Large Audio-Language Models (LALMs) and Omni models show that incorporating visual context substantially improves recall over the audio-only setting across all three model families. The gains are largest for ETE and smallest for ISE, indicating that models leverage direct visual evidence more effectively than indirect semantic cues. To facilitate future research on visually grounded speech recognition, we publicly release ScreenASR-Bench.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.16260

  • Hardware-Friendly Token-Group Activation Quantization for Low-Bit Mamba Super-Resolution

    Hardware-Friendly Token-Group Activation Quantization for Low-Bit Mamba Super-Resolution

    Hardware-Friendly Token-Group Activation Quantization for Low-Bit Mamba Super-Resolution

    arXiv:2610.16261v1 Announce Type: new Abstract: Mamba-based super-resolution models are efficient alternatives to Transformer-based restoration backbones, but their low-bit post-training quantization remains challenging because selective scan, Mamba's input-dependent state-space operator, induces different activation ranges across spatial tokens. Thus, a single layer-wise clipping range poorly matches all tokens. We propose Token-Group Quantization, a hardware-friendly activation PTQ framework that statically approximates a hardware-unfriendly post-scan grouping oracle, where tokens with similar preferred clipping ranges are assigned to the same group. To avoid runtime post-scan grouping in static low-bit inference, a lightweight predictor infers the groups from pre-scan features available before the quantized scan path. During calibration, we form pseudo-labels by clustering post-scan activation descriptors that capture similar rounding–clipping behavior. At inference, the frozen predictor maps pre-scan features to groups and selects entries from offline-calibrated group-wise clipping-bound tables, without runtime statistics collection, dynamic clipping updates, or post-scan group assignment. To address low-bit restoration degradation, we further introduce a Frequency-Preserving Refinement (FPR) objective for clipping-bound calibration. FPR aligns Fourier amplitude and phase between full-precision teacher and quantized student outputs to preserve high-frequency structures. Across PTQ protocols, bit-widths, backbones, and tasks, our method consistently outperforms prior Mamba and SR PTQ baselines, transfers to Transformer SR and Vision Mamba classification, composes with rotation-based quantization, and achieves 2.23x speedup on Jetson Orin Nano over FP16. Code is available here.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.16261

  • agent-risk: Risk Assessment for Changes to AI Agents

    agent-risk: Risk Assessment for Changes to AI Agents

    arXiv:2610.16280v1 Announce Type: new Abstract: Before changing a deployed AI agent (a stricter safety gate, a new model), organizations must approve the change, starting from existing logs. Extending classical risk analysis to partial records and partial changes to running systems, agent-risk replays logged episodes, assuming nothing else changes and the agent does not anticipate the change. The log settles episodes acting as before, a declared stop value settles stopped ones, and the rest need logged support, a saved-state rerun, or a bound. We prove what logs must record for exact replay and which saved states serve a gate family. For independent episodes, we bound the reruns a decision needs and tolerable drift from live behavior. In a bash sandbox, a 7,200-episode log alone decided neither of two retry gates, which let the agent act after refusals the log never shows. Rerunning only each gate's blocked episodes from saved states reached both live decisions at half the agent calls of a live test sized post hoc for them, given the log. Without per-step harm, a stopping gate's certified harm ceiling rose up to 2.5-fold, since the log hides whether harm preceded the stop. Approval thus needs evidence designed in advance: log fields, saved states, targeted reruns.

    Fallback brief based on the available RSS feed; no unsupported details have been added.

    Source: arXiv
    Original article: https://arxiv.org/abs/2610.16280