AllyshipContent Radar

Deep dives 738

Paper và bài viết kỹ thuật

Crawl live-1795068900000 · 13:22 19 thg 11, 2026 · Xuất bản 13:30 19 thg 11, 2026

Huấn luyện

HardwareDx: A Foundational Graph Model System for Datacenter Machine Repairs

arXiv:2611.23398v1 Announce Type: new Abstract: The rapid scale-up of AI infrastructure has made datacenter reliability a cornerstone of the cloud business economy. Since hardware failures in hyper-scale AI clusters can stall multi-million dollar training workloads, the downtime of individual machines can cause outsized economic losses. Minimizing machine downtime, therefore, is more important than ever. To address this, we present Hardware Diagnoser (HardwareDx), an AI-driven hardware diagnosis system that applies a graph foundation model approach to automated datacenter maintenance. It allows a single model to diagnose many platforms and accelerate onboarding of new hardware products. Deployed at production scale at Google, HardwareDx yields substantial efficiency gains across diverse compute architectures. Real-world evaluations demonstrate that it reduces production downtime by 18.3% on GPU platforms and 16.1% on TPUs. Furthermore, it significantly accelerates hardware deployment, cutting quality assurance (QA) time by 28.3% for GPUs and 25.1% for TPUs. These results establish HardwareDx as a field-tested solution for maximizing the reliability and cost efficiency of next generation AI fleets.

  • These results establish HardwareDx as a field-tested solution for maximizing the reliability and cost efficiency of next generation AI fleets.
arXiv cs.AI · Yuanlin Wen, Elan Markowitz, Zubo Gu, Sami Abu-El-Haija, Bryan Perozzi, Mikhail Galkin, Ali Parviz, Aayush Gupta, Venkata Chivukula, Griffin Hadfield, Aravind Akella, Daniel J. Frame, Vahab Mirrokni, Amin Vahdat Mở bản gốc ↗
Nguyên văn nguồn
Chi tiết nguồn
Đánh giá

RFBench: A Simulator-Grounded Multimodal Benchmark for Passive RF Layout Design and Understanding

arXiv:2611.23410v1 Announce Type: new Abstract: While multimodal language models can interpret diagrams and generate structured outputs, their capacity to connect passive radio-frequency (RF) design intent, layout geometry, and electromagnetic behavior remains largely untested. To address this gap, we introduce RFBench, a simulator-grounded dataset and benchmark for passive RF layout design and understanding. The dataset contains 10,000 two-port planar layouts simulated using ADS Momentum, with each layout represented by editable geometric primitives, a raster image, a 16x16 occupancy grid, complex S-parameters at 201 frequency points, a structural category, and an RF response label. Building on these aligned representations, we define seven tasks spanning specification-conditioned layout generation, representation translation, response prediction, simulator-based validation, design diagnosis and improvement, structural understanding, and response classification. Extensive baselines across seven multimodal language models reveal systematic weaknesses in generating structurally valid layouts and predicting electromagnetically faithful responses. We show that RF-specific fine-tuning increases T1a structural validity from 0.0% to 83.2% and the T3 primitive-input within-2-dB rate from 17.7% to 62.8%, demonstrating the value of domain adaptation while leaving considerable room for further progress. RFBench establishes a common testbed for evaluating multimodal RF capabilities and guiding the development of models that connect design intent and layout representations with physical behavior.

  • Building on these aligned representations, we define seven tasks spanning specification-conditioned layout generation, representation translation, response prediction, simulator-based validation, design diagnosis and improvement, structural understanding, and response classification.
Nguyên văn nguồn
Chi tiết nguồn
Đánh giá

Why Sub-4-Bit Vision CNNs Collapse and Where Mixed-Precision Recovery Stops

arXiv:2611.23445v1 Announce Type: new Abstract: Deep vision models operating in resource-constrained environments depend heavily on low-bit quantization, yet compressing weights below 4 bits frequently induces catastrophic accuracy collapse. While mixed-precision recovery strategies aim to rescue accuracy by selectively retaining high-precision parameters, the fundamental mechanics of where and why these models collapse remain poorly understood. In this study, we systematically analyze the anatomy of quantization collapse across standard Vision CNNs (including ResNet and EfficientNet backbones) evaluated on the full 50,000-image ImageNet-1k validation set. First, we map the exact progression of degradation, demonstrating that collapse is highly non-linear and concentrated in late-stage pointwise projections and depthwise layers. Second, we introduce a structured, multi-step recovery waterfall that evaluates selective integer precision (INT4/INT8) and selective floating-point scales. We show that keeping less than 5% of critical layer activations in 8-bit precision recovers up to 92% of the accuracy lost during aggressive sub-4-bit compression. Finally, we bridge the hardware reality gap by evaluating deployment performance on standard ARM and x86 CPU architectures. We show that while low-bit quantization reduces memory storage requirements, standard runtime software bit-unpacking introduces a 1.48x to 21.5x execution slowdown depending on batch size, highlighting a critical trade-off between model footprint and actual edge throughput. Our findings provide a practical blueprint for navigating the limits of sub-4-bit deployment without sacrificing hardware performance.

  • We show that keeping less than 5% of critical layer activations in 8-bit precision recovers up to 92% of the accuracy lost during aggressive sub-4-bit compression.
Nguyên văn nguồn
Chi tiết nguồn
Đánh giá

LusoClin: A Synthetic Clinical Note Dataset for Medical Information Retrieval in European Portuguese

arXiv:2611.23454v1 Announce Type: new Abstract: Access to large-scale clinical text collections is crucial for advancing medical information retrieval research, including clinical note search, patient cohort identification, and domain-adapted retrieval models. However, real clinical notes are rarely available due to privacy regulations, which particularly limits progress for low-resource languages such as European Portuguese. We present LusoClin, a publicly released dataset of synthetic clinical notes in European Portuguese, created to support privacy-preserving research on clinical text retrieval. LusoClin was generated by pre-processing real clinical data, fine-tuning the open-source Llama 3.2 (3B) instruction-tuned model using Quantized Low-Rank Adaptation, and applying prompt-based clinical note generation. To facilitate semantic indexing and clinical search, the notes are automatically annotated with clinical entities using a BERT-based model. We evaluate LusoClin in terms of utility, fidelity, diversity, and privacy using automatic metrics and human evaluation. Results indicate that the dataset captures clinically relevant language patterns and can support downstream IR applications such as clinical document retrieval and domain-specific model adaptation, although annotators can often distinguish synthetic from real notes and some medical inconsistencies persist.

  • Results indicate that the dataset captures clinically relevant language patterns and can support downstream IR applications such as clinical document retrieval and domain-specific model adaptation, although annotators can often distinguish synthetic from real notes and some medical inconsistencies persist.
Nguyên văn nguồn
Chi tiết nguồn
Tác tử

GUARD: Stabilizing Recursive Self-Improvement with Regret Guidance

arXiv:2611.23476v1 Announce Type: new Abstract: Autonomous AI agents pair a frozen base model with an editable harness of prompts, skills, tool rules, and memory. Recursive self-improvement (RSI) adapts this harness from experience without weight updates, yet self-editing without external graders often backfires: reflection and scalar scores conflate what an edit newly broke with what remains unsolved, causing local regressions, skill forgetting, and memory bloat. We introduce GUARD (Grader-free Unsupervised Environment Design [UED] with Adaptive Rule Distillation), a closed-loop framework for reference-free continual harness evolution. Our key insight is to decompose each task into pre-execution self-checks and guide harness updates via directional regret. Each round grades trajectories against these checks, pinning mastered rules while prioritizing newly broken behaviors, and selects among parallel candidate edits by critic-free group-relative fitness. A Soft-HURT gate then promotes an edit only when gains outweigh regressions, scoping specialized fixes to prevent over-triggering and guaranteeing non-regression on its gated buffer. At test time, one frozen harness runs in a single pass. Across benchmarks on memory, skill evolution, continual task streams, and domain reasoning, GUARD consistently improves performance without catastrophic forgetting or memory pollution while substantially cutting deployment token usage.

  • Recursive self-improvement (RSI) adapts this harness from experience without weight updates, yet self-editing without external graders often backfires: reflection and scalar scores conflate what an edit newly broke with what remains unsolved, causing local regressions, skill forgetting, and memory bloat.
  • Across benchmarks on memory, skill evolution, continual task streams, and domain reasoning, GUARD consistently improves performance without catastrophic forgetting or memory pollution while substantially cutting deployment token usage.
arXiv cs.AI · Minghe Zhang, Xuetao Kang, Yifei Ming, Yanfei Chen, Han Yu, Yufan Zhuang, Chen-Yu Lee Mở bản gốc ↗
Nguyên văn nguồn
Chi tiết nguồn
Đánh giá

SpecLook: Speculating Where to Look for Fast and Reliable Agentic MLLMs

arXiv:2611.23483v1 Announce Type: new Abstract: Agentic multimodal large language models (MLLMs) that think with images interleave reasoning with zoom-in tool calls. However, this sequential loop is slow, and its answers carry no reliability score. Prior speculation of tokens, reasoning steps, or answers keeps the loop, and answer speculation also accepts confident errors. We find that the loop mostly adds one zoom-in step, with which a small model is ahead of the agent on most splits. Our key insight is to speculate the agent's next observation, which, unlike a drafted answer, can be verified, corrected, and used to test the answer. We propose SpecLook, a training-free speculate-and-verify framework with three levels. A small model drafts a glimpse and re-answers from it, and the question ends if the answer is unchanged and confident. Otherwise, the agent's large model verifies and corrects the glimpse without tools, and their answers are fused. Only questions that still lack evidence reach the agent, in one forward pass that SpecLook-Fast skips, so no question runs the loop. The trace scores every answer's reliability without labels. Extensive experiments on V*, HR-Bench, and POPE show that both are more accurate than every baseline on every split. SpecLook reaches 87.2% and 86.2% mean accuracy with 7.7x and 4.7x speedups over the DeepEyes-7B and Thyme-RL agents, and SpecLook-Fast reaches 9.9x and 6.3x.

  • We find that the loop mostly adds one zoom-in step, with which a small model is ahead of the agent on most splits.
Nguyên văn nguồn
Chi tiết nguồn
Kiến trúc

BOS Summary: The First Token Matters

arXiv:2611.23508v1 Announce Type: new Abstract: Large vision-language models (LVLMs) and language models (LLMs) often exhibit attention sinks, whereby particular positions, such as the beginning-of-sequence (BOS) token, receive a disproportionate share of attention. Under standard causal masking, however, the BOS query attends only to itself, so the representation that later tokens repeatedly access carries no information about the input. We introduce BOS Summary, a training-free inference-time method that repurposes this persistent pathway to carry input context. At a single transformer layer during prefill, BOS Summary relaxes the causal constraint for the BOS query row alone, letting BOS aggregate all visual and textual input tokens into a self-derived context representation while every other token retains standard causal attention. The enriched representation then remains accessible to the model throughout decoding, with no additional parameters, auxiliary modules, or decoding-time overhead. Across multiple VLM and LLM families and eight multimodal and text-only benchmarks, BOS Summary improves over direct and Chain-of-Thought prompting and outperforms recent sink-intervention methods on multi-step reasoning tasks. A mechanistic analysis shows that making BOS input-specific also weakens its sink dominance and redistributes attention toward content-bearing prompt tokens, indicating that changing what a sink carries reshapes how later layers allocate attention.

  • Across multiple VLM and LLM families and eight multimodal and text-only benchmarks, BOS Summary improves over direct and Chain-of-Thought prompting and outperforms recent sink-intervention methods on multi-step reasoning tasks.
arXiv cs.AI · Hui Zhu, Saleh Zare Zade, Rafi Ibn Sultan, Deng Pan, Arun Ross, Dongxiao Zhu Mở bản gốc ↗
Nguyên văn nguồn
Chi tiết nguồn
Đánh giá

GRAFT: Execution-Guided Genetic Recombination for Agent Design

arXiv:2611.23509v1 Announce Type: new Abstract: Automated agent design searches for executable architectures that improve LLM-based agent performance, with evolutionary methods using language-model crossover to recombine promising mechanisms for task decomposition, model coordination, and verification. This search, however, is typically guided by aggregate fitness alone, which hides the instance-level successes and failures behind each score. We introduce Execution Guided Genetic Recombination for Agent Design (GRAFT), which uses aggregate fitness for selection and survival and parent-specific execution evidence to guide semantic crossover with integrated mutation. Its feedback harness reuses bounded samples of successful and failed runs from fitness evaluation, withholding reference answers and requiring no additional task executions. We evaluate GRAFT across six reasoning and programming settings using open-weight optimizer and executor models. It achieves a mean test accuracy of 82.0%, exceeding the strongest baseline by 9.8% points. Controlled ablations show that adding execution evidence improves test accuracy with initialization, search rules, repair policies, and evaluation budgets held fixed. Our results support the value of parent-specific execution evidence for evolutionary agent design.

  • 23509v1 Announce Type: new Abstract: Automated agent design searches for executable architectures that improve LLM-based agent performance, with evolutionary methods using language-model crossover to recombine promising mechanisms for task decomposition, model coordination, and verification.
  • Controlled ablations show that adding execution evidence improves test accuracy with initialization, search rules, repair policies, and evaluation budgets held fixed.
  • Our results support the value of parent-specific execution evidence for evolutionary agent design.
arXiv cs.AI · Sevda Ebrahimi, Mohammed Saidul Islam, Xiaodan Zhu, Elham Dolatabadi Mở bản gốc ↗
Nguyên văn nguồn
Chi tiết nguồn
Đánh giá

BeFit: Shifting Complexity from Weights to Bernstein Activations for Resource-Constrained Sensing

arXiv:2611.23520v1 Announce Type: new Abstract: Time-series sensing increasingly relies on neural networks, yet deployment on resource-constrained microcontrollers remains challenging. Aggressive model compression can reduce accuracy, while restricting weights to multiplication-free representations introduces further losses. We present BeFit, an end-to-end framework that shifts model capacity from weights to learnable Bernstein polynomial activations. BeFit (i) finds compact Bernstein-activated convolutional neural networks (BeCNNs) through hardware-aware neural architecture search and trains them via knowledge distillation; (ii) projects their weights to multiplication-free codes, freezes the codes, and recovers the resulting accuracy loss through the learnable activations; and (iii) generates model-specific kernels that exploit the projected weights for multiplication-free convolutions. On human activity recognition, BeCNNs are 2.75 percentage points (pp) more accurate on average than ReLU CNNs of identical architecture. On a TI CC3220SF (Cortex-M4), weight projection speeds BeCNNs up by 2.2x on average while losing 0.8 pp, compared with 2.4 pp for ReLU CNNs. Against the MLPerf Tiny DS-CNN reference model running on TensorFlow Lite Micro with CMSIS-NN, the unprojected BeCNN achieves 1.0 pp higher accuracy, 2.2x lower latency, and 6.4x lower flash, while the projected model remains within 1.0 pp of the reference accuracy and runs 5.9x faster. In emulation on a RISC-V core without a hardware multiplier, the instruction-count reduction relative to the DS-CNN increases from 5.2x on the Cortex-M4 to 147x. BeFit also extends to transformers and MLPs, and across all tasks the final models stay within 1.56 pp of their float32 teachers on average.

  • Aggressive model compression can reduce accuracy, while restricting weights to multiplication-free representations introduces further losses.
  • BeFit (i) finds compact Bernstein-activated convolutional neural networks (BeCNNs) through hardware-aware neural architecture search and trains them via knowledge distillation; (ii) projects their weights to multiplication-free codes, freezes the codes, and recovers the resulting accuracy loss through the learnable activations; and (iii) generates model-specific kernels that exploit the projected weights for multiplication-free convolutions.
arXiv cs.AI · Malak Gamal El-Din, Yasser Shoukry, Salma Elmalaki Mở bản gốc ↗
Nguyên văn nguồn
Chi tiết nguồn
Kiến trúc

FACET - Facet Aware Contrastive Embeddings for Traits- Big Five Estimation from Life Narratives

arXiv:2611.23560v1 Announce Type: new Abstract: Personality is only weakly and inconsistently signaled by written language, and existing text-based methods typically combine language-model and psycholinguistic representations at the input or decision level. It remains open whether a more deliberate combination of the two views, and a decomposition of the prediction target, can recover more of the signal. We present a three-phase framework for estimating Big Five personality domain scores from life-narrative interview text. It encodes text and psycholinguistic features separately and combines them by concatenation or by a learned weighting, decomposes each domain into contrastively trained facet embeddings instead of predicting the domain directly, and pools the facet embeddings by attention into a domain-level prediction. We compare end-to-end with staged training and ablate the input modalities, their combination, and the facet-pooling strategy. On 1,332 participants from the St. Louis Personality and Aging Network (SPAN) study, facet embeddings reach AUC up to 0.740, and domain-level R2 reaches 0.328, highest for Openness. End-to-end training gives lower error than staged training in every domain, and attention pooling gives the lowest error in every domain. Combining the two views lowers error relative to text alone for Conscientiousness and Agreeableness, whereas a learned weighting of the views shows no consistent advantage over concatenation. The framework provides facet- level predictions that a domain-only model cannot, and it improves modestly on a regression from the raw features in four of the five domains.

  • The framework provides facet- level predictions that a domain-only model cannot, and it improves modestly on a regression from the raw features in four of the five domains.
arXiv cs.AI · Balakrishnan Arumugam, Priyen Parekh, Mehak Gupta, Joshua Oltmanns Mở bản gốc ↗
Nguyên văn nguồn
Chi tiết nguồn
Đánh giá

LProp: Propagating Latent Uncertainty through Evidence-Conditioned Belief Revision in LLM Agents

arXiv:2611.23564v1 Announce Type: new Abstract: When LLM agents pass intermediate judgments downstream without uncertainty, later decisions may treat tentative assumptions as facts. Effective uncertainty propagation must preserve information for correction and update inherited beliefs as new evidence arrives. Yet scalar scores omit information needed for revision, while detailed descriptions and reflection incur additional costs. We introduce Latent Uncertainty, a latent-space estimator that preserves uncertainty-relevant information without lengthy descriptions. Building on this, we propose LProp (Latent Uncertainty Propagation), which revises inherited answer distributions using latent representations and new evidence without additional trajectory sampling. We evaluate both methods across multiple-choice, yes/no, open-ended question answering, and mathematical reasoning tasks. Our approach outperforms baselines on most metrics, while LProp achieves the lowest mean inference-token usage in all eight propagation settings. Matched feature ablations further demonstrate that inherited latent content improves error recovery beyond answer probabilities or model capacity alone.

  • Our approach outperforms baselines on most metrics, while LProp achieves the lowest mean inference-token usage in all eight propagation settings.
  • Matched feature ablations further demonstrate that inherited latent content improves error recovery beyond answer probabilities or model capacity alone.
arXiv cs.AI · Kaiwen Shi, Zheyuan Zhang, Weixiang Sun, Han Bao, Colby Nelson, Yanfang Ye Mở bản gốc ↗
Nguyên văn nguồn
Chi tiết nguồn
Đánh giá

RefinementGuard: Counterexample-Directed Semantic Qualification for Hidden Agent-Tool Execution

arXiv:2611.23611v1 Announce Type: new Abstract: Tool runtimes can lower an agent-selected operation into a hidden parallel graph, reducing latency and context while risking semantic mistranslation. We introduce RefinementGuard: translation validation for hidden, effectful agent-tool lowerings, coupled to artifact-bound, fail-closed runtime admission. Qualification compares a candidate graph with an independent reference on isolated state using explicit parent-operation obligations. We evaluate two repository-level contracts, bug localization and patch validation, on controlled repositories. Among 100 activated, non-equivalent development/qualification faults adjudicated by one human, parent-semantic validation rejects 49/100 (operator-cluster bootstrap 95% CI [33.7%, 64.8%]). The objective is selective admission, not maximum mutation rejection: exact equality rejects 100/100 faults but also all 60 valid variants, whereas obligation-based validation accepts 60/60; its 51 residual misses identify concrete specification gaps. On a frozen disjoint input split, the held-out B2-B3 result is localization-only because 21 patch mutants fail structurally; B3 rejects 38/56 localization defects. In a controlled asynchronous-delay regime, the localization serial/guarded median-latency ratio is 4.50x, and hidden execution exposes 74.3% less parent-visible context than visible execution. Patch validation shows no demonstrated speedup; zero-delay runs expose overhead. End-to-end qualification thus detects lower-layer misses while preserving localization's parallelism.

  • 23611v1 Announce Type: new Abstract: Tool runtimes can lower an agent-selected operation into a hidden parallel graph, reducing latency and context while risking semantic mistranslation.
  • On a frozen disjoint input split, the held-out B2-B3 result is localization-only because 21 patch mutants fail structurally; B3 rejects 38/56 localization defects.
Nguyên văn nguồn
Chi tiết nguồn
Đánh giá

Searching the Pareto Front: Multi-Objective Retrieval for Heterogeneous Scientific Modalities

arXiv:2611.23639v1 Announce Type: new Abstract: In cosmology, surveys span different sky regions and wavelength ranges, resulting in uneven modality coverage across observational datasets. Such heterogeneity can be addressed through either multimodal foundation models (FMs), which learn shared embedding spaces, or independently learned modality embeddings combined via late fusion. We investigate whether the latter provides an adaptive alternative to FM-based scientific retrieval. We evaluate this approach on a galaxy retrieval task spanning diverse modalities--history of star formation, spectra of light emitted, and multi-wavelength observations from two telescopes--comparing an FM baseline with separately trained embeddings fused through multi-objective optimization based on Pareto optimality. We find that the FM baseline achieves strong embedding-space proximity, but our method preserves modality-specific distance structure that allows scientists to inspect which physical signals drive similarity. Our method also achieves improved fidelity in raw-data space: across six measured properties, its nearest neighbor is 8% closer to the query on average than that retrieved by kNN in the FM embedding space (spread 0.128 vs. 0.139). These results suggest that multi-objective retrieval can surface astrophysically coherent candidates that single-objective search alone may overlook.

  • 23639v1 Announce Type: new Abstract: In cosmology, surveys span different sky regions and wavelength ranges, resulting in uneven modality coverage across observational datasets.
  • We find that the FM baseline achieves strong embedding-space proximity, but our method preserves modality-specific distance structure that allows scientists to inspect which physical signals drive similarity.
  • These results suggest that multi-objective retrieval can surface astrophysically coherent candidates that single-objective search alone may overlook.
arXiv cs.AI · Song Young Oh, Nesar Ramachandra, Bin Xia, Ian Foster, Kyle Chard Mở bản gốc ↗
Nguyên văn nguồn
Chi tiết nguồn
Đánh giá

Auditable Clinical Support with Decision Agents

arXiv:2611.23700v1 Announce Type: new Abstract: Clinicians reviewing a diagnostic work-up will ask what was considered at each step and why the assessment changed. Agents powered by free text can reach physician-level diagnostic accuracy, but their written reasoning does not always reflect the factors that went into the decision. Here, we present Decision2Care, a decision agent that works up the acutely ill patient without producing any text. A decision model assigns a probability to each permitted EHR action, and fixed rules carry out the most probable one. We evaluated Decision2Care on the records of 546 emergency admissions across 12 diseases. Decision2Care reached a diagnostic accuracy of 86.5%, compared with 86.1% for the MIRA-v2 agent, and required a median of 2.2 s per work-up, compared with 92-100 s. Each work-up tracked which options Decision2Care was considering at each step. In 10 of the 12 diseases, the differential diagnosis changed most at the test on which the guideline bases the diagnosis. Where Decision2Care was most confident after a single work-up, all but four of its diagnoses were correct (98.5%). We traced each of these four errors back to a single imaging report. Three of them were corrected when that report was removed. The same kind of decision was used to select the treatments, and Decision2Care's drug orders were judged guideline-adherent more often than MIRA-v2's. In emergency patients, its prediction of death was comparable to that of three intensivists on the same cases. In five of the eight intensive care cohorts, it exceeded the best of the three 24-h severity scores within 2-6 h of records. Our results show that decision agents can carry out clinical work-ups while recording the options, probabilities, and execution rules behind each action for audit.

  • Our results show that decision agents can carry out clinical work-ups while recording the options, probabilities, and execution rules behind each action for audit.
arXiv cs.AI · Tiancheng Bao, Riga Wu, Jan Wienhold, Sebastian Billig, Patrick Winnersbach, Hsuan-Chih Chen, Akis Giannoukos, Jiayang Li, Li Shen, Gary Weissman, Eduardo J. Mortani Barbosa Jr, Dyke Ferber, Jakob Nikolas Kather, Christos Davatzikos, Daniel Truhn, Tianyu Han Mở bản gốc ↗
Nguyên văn nguồn
Chi tiết nguồn
Tác tử

KnowMe Paper Radar: Lightweight Discovery of Promising Papers in the Age of Autoresearch

arXiv:2611.23702v1 Announce Type: new Abstract: The growing volume of topically similar papers makes it difficult to identify new work that can offer useful research insights or methodological guidance. We present KnowMe Paper Radar, a lightweight discovery tool that combines multiple sources of evidence into personalized reading priorities. Users specify topics, priorities, exclusions and dates; the system brings together topical relevance, recency, author research histories, collaboration paths and direction-specific institutional context. By exposing each score component and its supporting sources, KnowMe helps readers select promising papers for their current questions and discover relevant work beyond familiar authors. Automatic acquisition, version merging and graph-cache reuse keep this workflow convenient without large language model (LLM) inference during ordinary use. Experiments on 174,640 acquired records show more than threefold faster repeated context preparation, while cached abstracts improve normalized discounted cumulative gain at rank 10 (NDCG@10) from 0.412 to 0.598 on expert-judged retrieval tasks. Complementary analyses examine how the same accumulated records support semantic retrieval, research-history modeling and literature-grounded planning. A browser interface and a structured command-line interface (CLI) make these capabilities available to both researchers and research agents, positioning KnowMe as a practical upstream tool for literature-informed recursive self-improvement (RSI) workflows.

  • A browser interface and a structured command-line interface (CLI) make these capabilities available to both researchers and research agents, positioning KnowMe as a practical upstream tool for literature-informed recursive self-improvement (RSI) workflows.
Nguyên văn nguồn
Chi tiết nguồn
Đánh giá

Modeling LLM Reasoning Dynamics with Structural Representations

arXiv:2611.23749v1 Announce Type: new Abstract: Language-model reasoning alternates between sustained activities and local operations. We study how this temporal structure predicts continuation and the computation needed to analyze it. T/E/S combines text, local events, and spans of activity. Across reasoning and information-seeking tasks, events and spans improve next-outcome prediction in 70 of 76 evaluation groups for a Transformer and 74 of 76 for Qwen with LoRA. Span duration and preceding events are associated with transitions, and retaining event history across span boundaries improves prediction. We formulate budget-allocation counting and action-conditional continuation queries, prove counting hardness under explicit encodings, and derive conditions for affordable decision certification. In finite-process experiments, bounds that cancel shared continuation mass recover the same optimal actions as full dynamic programming while reducing mean inference CPU time by 77.7%. On 71 held-out HotpotQA and MuSiQue questions, a compact structural observer improves prediction of whether a fixed inference procedure finishes within a CPU allowance: Brier loss falls from 0.0836 to 0.0756. An annotation audit identifies substantial errors in that observer, separating this computational result from semantic validation of its features.

  • Across reasoning and information-seeking tasks, events and spans improve next-outcome prediction in 70 of 76 evaluation groups for a Transformer and 74 of 76 for Qwen with LoRA.
  • Span duration and preceding events are associated with transitions, and retaining event history across span boundaries improves prediction.
  • An annotation audit identifies substantial errors in that observer, separating this computational result from semantic validation of its features.
arXiv cs.AI · Ilia Karpov, Andrey Atamanyuk, Dmitry Ilvovsky, Aleksandr Anokhin, Alex Elizov, Dmitry Zagorulkin, Sergei O. Kuznetsov Mở bản gốc ↗
Nguyên văn nguồn
Chi tiết nguồn
Tác tử

Metrics-in-the-Loop: Complexity Feedback Reshapes Agent-Written Code

arXiv:2611.23817v1 Announce Type: new Abstract: Coding agents now write whole codebases in long autonomous runs, guided mainly by whether their tests pass. Yet passing tests alone does not reveal accumulating complexity or gaps in test coverage, which then persist as agents extend their own code. We introduce metrics-in-the-loop, an inference-time intervention that gives agents in-flight feedback: cheap, automatically computed code metrics injected into the agent's context during the trajectory. After each code-changing agent turn, we insert short feedback messages naming changed functions whose cyclomatic complexity exceeds a limit (complexity feedback) or changed lines that are skipped by tests (coverage feedback), giving the agent the opportunity to refactor code or strengthen tests before continuing. We run extensive experiments and ablations comparing several interventions across three long-horizon coding benchmarks and four strong models. We find that complexity feedback significantly reduces erosion, a measure of complexity concentration of code, without affecting held-out correctness of the code. Broadly, our experiments investigate a practical form of agent "re-railing", where timely, actionable measurements redirect agents before weaknesses become the foundation they keep building on. As agents scale to codebases with millions of lines, such interventions become critical to sustaining effective development and long-term code maintainability.

  • We find that complexity feedback significantly reduces erosion, a measure of complexity concentration of code, without affecting held-out correctness of the code.
arXiv cs.AI · Nicolas Chapados, Jean-Fran\c{c}ois Gagn\'e, Nouha Dziri Mở bản gốc ↗
Nguyên văn nguồn
Chi tiết nguồn
Đánh giá

Evidence-Based Credit Assignment for Search-Augmented Language Models

arXiv:2611.23824v1 Announce Type: new Abstract: Reinforcement learning from terminal answer rewards enables search-augmented language models to interleave reasoning and retrieval without step-level annotations, yet outcome supervision assigns identical credit to every search in a trajectory regardless of whether it retrieved useful information. This limitation is especially severe when all sampled rollouts for a question fail, collapsing group-centered outcome advantages to zero even when trajectories gather markedly different evidence. We present Evidence-based Credit Assignment (ECA), which augments terminal outcome rewards with a training-only auxiliary signal measuring how retrieved documents improve the likelihood of a reference answer. Rather than scoring the full dialogue prefix, ECA queries a frozen snapshot of the current policy under an evidence-only prompt containing solely the question and the deduplicated documents observed so far, isolating the utility of retrieved passages from surface variations in generated thoughts or search queries. Within this framework, we compare two return formulations, ECA-Step (which accumulates step-clipped potential increments) and ECA-Horizon (which preserves the telescoping horizon gain in potential), paired with cross-fold group normalization, novelty gating, and search-local token assignment. Across seven Search QA benchmarks, ECA-Horizon improves strict macro exact match over an outcome-only GRPO baseline by 1.03 and 4.80 percentage points on Qwen2.5-3B- and 7B-Instruct, respectively, outperforming both RLOO and GiGPO. Zero-shot evaluation on MultiHop-RAG further demonstrates strong transfer to multi-hop inference queries.

  • We present Evidence-based Credit Assignment (ECA), which augments terminal outcome rewards with a training-only auxiliary signal measuring how retrieved documents improve the likelihood of a reference answer.
  • 5-3B- and 7B-Instruct, respectively, outperforming both RLOO and GiGPO.
arXiv cs.AI · Wen Wang, Jindong Wang, Jiahua Bao, Tu Yongsiqi, Yihao Liu, Junwei He, Wenkui Fan Mở bản gốc ↗
Nguyên văn nguồn
Chi tiết nguồn
Tác tử

Ask HN: Aren't the current cyber attacks suspicious?

Câu hỏi Isn't it obvious that some nation state or activist/terrorist group has gotten hold of an AI hacking tool/Agent that can wreak havoc?

Just looking at history and having some bayesian mindset the fact that: FAA,NSA,MSFT,APPLE,EQUINOR all got hacked in a week. Isn't it obvious that some nation state or activist/terrorist group has gotten hold of an AI hacking tool/Agent that can wreak havoc? It's not business as usual anymore, it's an agentic cyber war that has started isn't it? * Edit: about bayesian, I wrote two comments below explaining the logic. I didn't even think about the next bayesian update meaning that there is a trilateral superpower meeting for the first time.

HN: AI agent · arisAlexis 17 lượt bình chọn 17 bình luận Mở bản gốc ↗
Nguyên văn nguồn
Chi tiết nguồn
Kỹ thuật

Show HN: Robotics needs better CAD, so I wrote a B-rep kernel and 3,487 tests

Hey HN, I’m Tony. I’m a co-founder of Springcraft, where we have been doing a lot of CAD modeling for robot parts. Our team kept running into limitations with existing kernels, and so I decided to write a new B-rep kernel and a new comprehensive, kernel-agnostic B-rep conformance test suite. Both are available today under MIT licenses. The kernel, springrep, is written in safe Rust with no dependencies. It covers a broad range of our mechanical CAD needs, including advanced fillets, sweeps, lofts, shells, offsets, STEP and exact measurements and queries. Claude Code made it feasible to write this, but it took a lot of time and care to get it right. The test suite, brep-conformance, has 3,487 cases covering the modeling operations common across kernels: booleans, fillets, chamfers, shells, offsets, sweeps, lofts, STEP, and queries with expected answers coming from closed forms and exact geometry. It caught hundreds of bugs, edge cases, and hot spots in springrep that our own tests had missed, and now springrep passes all of it. We’ve also run it on a few popular open-source kernels and anyone can run it on theirs. This is the first version, so there are surely mistakes in the test and adapters. Corrections, pull requests, and new kernels are welcome. kernel: https://github.com/springcraft-ai/springrep conformance suite: https://springcraft-ai.github.io/brep-conformance/

Nguyên văn nguồn
Chi tiết nguồn
41–60 / 738
Trang 3 / 37