overfeed.news
Anuncio

NexTalk

Automatiza la primera respuesta. Mantén el toque humano.

Chat en vivo con agentes de IA en tu modelo y tu clave de API, con traspaso a tu equipo.

Empezar gratis

Tema

Recuperación y RAG

1217documentos

102últimos 7 días

arXiv AI Papers

Clocks all the way down: does sequence-processing AI need endogenous temporal structure?

Mainstream sequence-processing AI is temporally reactive: each update is driven by input and learned state transitions, rather than by an independently evolving internal temporal reference. Biological brains, by contrast, continuously generate rhythmic activity that structures perception, memory, and cognition, and this rhythmicity reaches all the way to behavior. We ask whether this difference is merely implementational or genuinely computational. Four lines of evidence suggest that endogenous temporal structure supports putative functions that input-driven architectures may not readily replicate: 1) phase-dependent routing of information, 2) delay-structured combinatorial representation, 3) cross-frequency multiplexing of items, and 4) oscillation-gated offline consolidation. A proof-of-concept delay-ablation test dissociates representational capacity from memory retrieval. In recurrent and spatial spiking networks with fixed synaptic weights and connectivity, shuffling delays preserves part of the capacity but substantially impairs the sequence retrieval. The relative contrast is more pronounced for spatial networks and longer propagations. Instantaneous transmission collapses capacity itself. We then outline a cross-frequency multiplexing scheme that combines item identity and serial order with alternative mechanisms for selective memory retrieval. Finally, we state one falsifiable hypothesis, conditions for matched-resource tests, and three research directions: the components already exist; the disciplined comparison does not.

en
arXiv AI Papers

Length Is Cheap, Competition Is Not: Attention Predicts Context Rot in Retrieval

Why do language models fail on long inputs? The common answer is length. We show that, for retrieval, length is cheap and competition is not. On five open models (0.5B to 3B parameters, four families), neutral filler costs nothing: accuracy stays at 0.97 to 1.00, up to 32K tokens on Qwen2.5-1.5B. Statements in the format of the evidence, placed at the same positions, drop it to 0.16 to 0.33. A single statement that gives the queried key a rival value multiplies the loss by 9 to 110, and every additional rival adds to it. Inside the model, one quantity tracks the failure: the attention mass left on the evidence. Across 126,473 trials it explains up to 58% of the variance in loss; log length explains at most 8%. The masked-filler protocol behind the claim that length alone hurts reproduces on MMLU (11 to 18 points lost at 30K tokens), but fails a visible control in retrieval: masking costs 45 accuracy points at 32K tokens, while the same filler left visible costs none. In retrieval, context rot is a competition for attention. We release the probe and all 126K trial-level measurements.

en
arXiv AI Papers

Thought-deciphering via hierarchical EEG-to-text alignment

Communication is important for our well-being, but it can be impaired by disabilities, such as locked-in syndrome (LIS), cerebral palsy (CP), and dysarthria. Non-invasive brain-to-text brain-computer interfaces (BCIs) offer a promising solution by providing an alternative communication pathway for people with communication disabilities. However, most recent breakthroughs have relied on large, cumbersome, and costly neuroimaging modalities, such as functional magnetic resonance imaging (fMRI) and magnetoencephalography (MEG). Numerous studies have attempted decoding using the lighter and cheaper electroencephalography (EEG), but the results remain inferior compared to the other modalities. More importantly, we do not understand how these modalities are related to text at the letter, word, sentence, and higher semantic levels. Many prior studies have focused on decoding below the sentence level because it is considerably easier to design an experiment around phonemes, letters, and words. However, during communication, sentences play a much more important role than words and letters. This is because sentences carry information at such a high level that they can be understood even if some words and letters are missing. However, within sentence-level decoding, sentence classification is not as well investigated as sentence generation, making it difficult to decide whether a sentence should be retrieved or generated in the context of EEG-to-text decoding. This paper strives to investigate sentence-level EEG-to-text classification via a novel hierarchical alignment framework, where the main goal is to retrieve a read sentence using its context and EEG as inputs.

en
arXiv AI Papers

Strategist: Evolving Reasoning with Agents

A model is only half of an AI agent system. The other half is the inference strategy: the reasoning procedure that turns model calls into a response. Today that second half is written by hand, and the experience of building one strategy never carries to the next. We introduce Strategist, a meta-agent that evolves inference strategies across tasks. Each strategy is written as a blueprint,executable code that other strategies can reuse, and together the blueprints form a library. Given a task and a small development set, Strategist retrieves related blueprints, writes candidate strategies, tests them on real samples, and revises them from the results. Every candidate then enters the library, so later tasks build on earlier discoveries. On 30 benchmarks, Strategist beats the strongest baseline on 24 and matches its average accuracy (74.7% vs.74.0%) at 39% lower inference cost. Its strategies also transfer to unseen tasks and other models without further search. The part of an AI system that is not improved on its own now does.

en
arXiv AI Papers

Benchmark Prediction with Sparse and Unpaired Cached Responses

Evaluating a generative model on all queries from all available benchmark tasks is prohibitively expensive. As such, models are often evaluated on different subsets of tasks and/or different subsets of queries from a given task. The resulting collection of responses and the corresponding (model, task) score matrix are sparse and unpaired. In this paper, we introduce the Product Kernel Perspective Space (PKPS), a collection of low-dimensional representations of models based on their embedded responses. PKPS generalizes existing methods for representing black-box generative models by comparing responses to similar -- rather than just identical -- queries and is therefore able to utilize sparse and unpaired information. Theoretically, we show that benchmark prediction using PKPS is query-efficient relative to methods that only use information from dense and paired portions of the evaluation data. Empirically, we show that PKPS-based methods outperform baselines on benchmark prediction across two large benchmark suites.

en
arXiv AI Papers

Efficient Closure Learning in Dynamical Systems: A Comparison of Data-Assimilated and Embedded Approaches

Increased computing power has transformed computational science and improved predictive capabilities for complex systems, but many phenomena still exceed current simulation capabilities or require rapid evaluations for fast design iterations. Closure models address this challenge by approximating unresolved effects in reduced or incomplete dynamical systems. Data-driven closures offer a flexible mechanism for improving model accuracy and applicability, but approaches that embed the closure within a computational model for construction and training phases can be computationally expensive and cause numerical instabilities in the computational model during training. To avoid the challenges posed by embedded approaches, staged approaches to closure-model learning have been developed. The first stage uses data assimilation to infer state and closure trajectories from observations. The second stage trains a machine learning closure model offline using the assimilated data, thereby avoiding repeated simulator calls during training. In this work, we investigate the cost and accuracy tradeoffs between embedded and staged data-driven closure modeling approaches for a synthetic epidemiological SIQR model with a nonlinear state-dependent quarantine closure. The results illustrate a practical accuracy-efficiency trade-off: for this exemplar, embedded training provides the strongest average accuracy, while the staged approach yields comparable qualitative behavior with a moderate increase in error, substantially fewer model evaluations, and improved optimization robustness.

en
arXiv AI Papers

NitiBench+: A Temporal Thai Legal Question Answering Benchmark Across 17 Domains

Law changes over time. A court decides a case under the law in force on that day, and legal QA benchmarks grade answers against today's law. We checked 156,650 decisions of four Thai courts. Up to 67% of them cite law that has since been amended or repealed. We introduce NitiBench+, the sequel of our NitiBench, a Thai legal QA benchmark with 1,670 items across 17 domains, built from decisions of three courts. For each cited section it holds both the text in force on the decision date and the current text, and its retrieval corpus holds every dated version of every Thai statute section. Answers are graded on the Thai Bar Council rubric, the Bar-standard score, and on the overlap between the cited sections and the court's. The report has two parts. Part I measures the cost of the wrong text on 13 open-weight models. Reading the current text of amended law drops the Bar-standard score by 0.25 and missing repealed law drops it by 0.79. The penalty comes from rule changes, 0.45 on the 428 rule-changed items and none on the 331 wording-only items, and Citation F1 does not see it. The text in force is the fair setting. Part II benchmarks today's models on that setting. A public leaderboard ranks 26 models on a held-out test split of 500 items stratified by domain, with a validation split of the same shape released for public use, from memory alone, with the court's sections provided, and as a retrieval agent over the law in force, with the cost per item and the hallucinated citations. The best model scores 7.78 out of 10 and the best open-weight model 6.39. Without a search tool only five open-weight models recall any Thai law, and with it twenty of the 26 models gain and six lose. Leaderboard will take new models as they are released. Legal benchmarks must track dates, and on the right text today's models still leave a wide gap on Thai law.

en
arXiv AI Papers

An Agentic Framework for Automated Power System Studies and Grid Connection Assessment

Connecting new generation and demand to the grid depends on two scarce skills: checking applications against a large, changing body of regulation, and running the network studies that decide where and how a project connects. We present Grid Agents, an AI system that brings both together, and the methodology we use to evaluate it. The Grid Ontology is its knowledge system. It represents the regulation, standards and engineering knowledge that grid work depends on, makes it searchable, and evolves as the agents learn from use. Every answer drawn from it rests on evidence the agents cite. Grid Studio is an agent system specialised for power-system engineering. It works in its own engineering environment with domain tools and a study framework, draws on the Grid Ontology, and relies on established solvers for every number it reports. In both, engineers make the decisions. We bring eight published power-system benchmark families, previously scattered across separate papers, into one suite of 519 tasks, and we verify not only each answer but the work behind it, by replaying the agent's tool calls. The Grid Ontology cites the right regulatory evidence more often than a general coding agent or retrieval pipelines, leads on LegalBench-RAG and ranks first on the public leaderboards of the Enterprise RAG Challenge and ViDoRe V3. Grid Studio scores highest on the 519 power-system tasks and is the fastest of all the systems we compare, both by a statistically significant margin. With an optimiser in the loop, its reinforcement packages cost 33-67% less on average than those the agent designs alone.

en
arXiv AI Papers

Grading the Unannotated: Insights from the WorkRB Skill Extraction Challenge at RecSys-HR 2026

Skill extraction benchmarks score models against a few human-annotated positives and treat every other skill in the vocabulary as equally wrong. At the scale of ESCO (13,939 skills) this binary view can reward models that rank the annotated positive high for the wrong reason, and hides semantically nonsensical predictions. The WorkRB Challenge at RecSys-HR 2026 replaces it with graded relevance: every candidate skill in a model's ranking window carries a 0 to 4 grade, and the leaderboard scores nDCG@100 against these grades. Since ternary judgements proved too coarse for objective annotation, relevance is decomposed into a cascade of four binary questions (same domain, activity mentioned, right granularity, replacement of a gold positive) that a smaller LLM judge can answer reliably; the labels are validated with blind human and frontier-model re-annotation. This paper documents the annotation methodology, the construction of five benchmark datasets (four with vacancy sentences as queries, one with lexically distant skill surface forms), the validation of the LLM cascade, and insights from the submissions. The field converged on multi-stage retrieve-and-rerank pipelines, whose gains come from clearing nonsense out of the ranking window rather than finding more positives: at the top of the leaderboard, the graded ordering is uncorrelated with what binary evaluation would have said. Graded labels expose much bigger gaps between top submissions and baselines than binary evaluation does, and show that semantic-understanding skill recommendation is still wide open. The clear next direction is bringing efficiency back: every submitted system we could size uses at least 42x, typically several hundred times, more parameters than the baselines it beats.

en
arXiv AI Papers

Ask, Don't Equip: Question-Driven Coding Agents for Deep Kernel Optimization

LLM agents for GPU kernel optimization sit at two ends of a structure-freedom tradeoff. Scripted agents fix what the model does at each step, via a learned policy, an optimization menu, or fixed roles, and are sample-efficient where the recipe applies and stall where it does not. Open-ended agents let a self-directed model mutate a population of kernels and pay for the freedom in trials: thousands of evaluations, repeated edits, and wrong candidates. Both respond to hard targets by equipping the agent with more: parsed profiler output, disassembly analysis, retrieval over documentation and libraries, and stores of lessons. We argue that both lack direction, a hypothesis about where the remaining gap is, and that a short question asked at the right moment supplies it without narrowing what the agent may do next. We present KernelSeek, a question-driven agent that makes an existing CUDA kernel faster with no operator-specific knowledge and no faster implementation to imitate: a general-purpose coding agent, a minimal harness that enforces a verifiable goal, and questions at decision points, first from a human, then from a bank the agent applies to itself. On the same task, evaluator, hardware, and week, a tool-rich autonomous agent built in the prevailing style plateaued at 0.50x FlashAttention-3 after 133 model-driven steps; KernelSeek reached 1.13x. It then produced dependency-free FlashAttention forward kernels for Hopper and Blackwell, single CUDA files with no CUTLASS, CuTe, cuBLAS, or cuDNN, correct on all 182 scenarios per architecture and 1.16x FlashAttention-3 and 1.46x FlashAttention-4 (geometric mean). Across 162 human messages and 11.5K agent tool calls, every large gain followed a question that moved the agent to a different layer of the system or rejected a claimed limit, never one that supplied information. We release the kernels, harness, question bank, and all traces.

en
arXiv AI Papers

Harder Than the Task: From Technical to Organizational Difficulty in AI Benchmarking

AI benchmarks have made remarkable progress in measuring the ability of AI systems to perform increasingly demanding cognitive and technical tasks. Yet, many of these benchmarks treat technical tasks as the unit of analysis, while much economically valuable work takes place within organizations, where tasks are embedded in a system of relations. Within organizations, successful task performance depends not only on solving the technical demands of the task but also on navigating the interdependence of activities, distributed knowledge, differentiated authority, temporal constraints, conflicting interests, and changing environmental conditions while the task is underway. Accordingly, we argue that organizational task difficulty constitutes a distinct and insufficiently recognized dimension of AI capability, and that existing approaches to benchmarking provide an incomplete basis for assessing how effectively AI agents can perform real-world organizational work. By drawing on organization theory, we develop a taxonomy of the structure of work that characterizes the conditions that agents face in organizational work. Applying this taxonomy to analyze existing benchmarks, we find limited and uneven coverage of organizational dimensions, with fewer than one quarter of prominent benchmarks claiming any of them. We therefore argue that AI benchmarks should increasingly move beyond the evaluation of technically difficult tasks toward the systematic assessment of agents' ability to navigate the organizational conditions under which economically valuable work takes place.

en
arXiv AI Papers

DepthGraft: Structural Regularization through Hierarchical Cross-Layer KV Reconstruction

Scaling depth is a key route to stronger large language models, but Pre-LN architectures often suffer from depth-wise information dilution, limiting the effective use of deep layers. While cross-layer connectivity has proven effective at mitigating this problem, existing designs usually introduce additional computation or memory access. We revisit cross-layer KV sharing as an efficient form of such connectivity. Beyond cache compression, each KV reuse edge creates a direct gradient path from deep layers to source KV projections, turning KV sharing into an implicit structural regularizer for KV representation geometry. We provide a systematic analysis of this mechanism, showing that proper sharing topologies sharpen key retrieval directions while enriching the value content subspace, whereas existing adjacent or global-anchor designs do not fully exploit this effect. Motivated by this, we propose DepthGraft, a hierarchical KV-sharing architecture that reconstructs deep-layer KV from stride-aligned shallow-middle source pairs. DepthGraft distributes non-local gradient flow across source layers, while preserving prefill early completion and reducing KV cache by roughly one third. Experiments on dense and MoE models from 0.5B to 16B parameters show consistent downstream improvements under both GQA and MLA. Notably, on the 16B MoE model, DepthGraft achieves a 7.0% absolute improvement on MMLU-Pro, along with gains of 6.6% on CMMLU and 6.4% on C3. These results validate the potential of DepthGraft as a scalable design for large-scale pretraining. The project page is available at https://github.com/jianke0604/DepthGraft.

en
arXiv AI Papers

ComplianceAtlas: A Taxonomy-Driven Agentic AI Framework for Automated AI Act Gap Analysis and Remediation

Assessing regulatory compliance for high-risk AI systems requires systematic identification of technical gaps such as missing controls, in- adequate processes, or shallow evaluation of practices. Compliance officers typically admin- ister structured questionnaires collecting evi- dence of current practices, where organizations respond with descriptions of their existing pro- cesses, technical capabilities, and architectural choices. However, translating these compli- ance questionnaire responses into typed, ac- tionable gap diagnoses remains unsystematic. In this paper, we present a literature-grounded taxonomy of technical compliance gaps cover- ing areas such as accuracy, robustness, logging, and human oversight, and embed it in GapTo- Compliance, a two-stage agentic framework coordinating two specialized agents: a Gap Extraction Agent that performs hierarchical rea- soning from compliance areas to specific gap types, and a Remediation Planning Agent that ranks remediation actions from a remediation catalog via multi-signal scoring combining se- mantic similarity, regulatory alignment, and effort estimation. We evaluate this framework against four automatic compliance gap detec- tion baselines across 9 AI systems and 6 AI families. Our approach achieves a gap-type F1 of 0.831 (vs. 0.533 for the strongest baseline) and remediation P@5 of 0.872 (vs. 0.635 for retrieval methods), demonstrating promising potential for automated compliance workflows. The structured agent coordination reveals a path toward human-in-the-loop compliance systems where automated gap extraction reduces expert burden while maintaining auditability, and the taxonomy-driven design enables extension to emerging regulatory frameworks beyond

en
arXiv AI Papers

Diagonal Equivalence in State Space Models: Characterization, Retrieval Rank, and Selective Extensions

We classify real and complex state-space models (SSMs) with linear transitions, distinguishing fixed-basis diagonal equivalence from input-output equivalence and tracking coefficient-conditioning windows under coordinate changes. We characterize diagonal equivalence through commuting transition families whose members are diagonalizable over the chosen field. With time-shared token-local matrix maps, we identify this class's state-mediated kernels with unnormalized scalar-mode linear attention with multiplicative masks. Mamba 3's multiple-input, multiple-output (MIMO) construction lifts one value per local interface; SSD-MIMO routes independent values for local retrieval rank above one. HybridMamba combines Mamba 1's per-coordinate decay, Mamba 2-style heads and Mamba 3's complex rotations and two-endpoint writes, mixing real and rotating state blocks with different decay laws. They recover Mamba 1-3 single-input, single-output (SISO) configurations as exact special cases. On five large H100 bfloat16 workloads, our fused GPU kernels improve geometric-mean training time over official Mamba 1/3 in matched SISO recoveries, with Mamba 2 near parity at SSM-core scope. Memory tradeoffs depend on the baseline and metric: saved-for-backward versus peak allocation. In small-model multi-token recall experiments, both designs outperform Mamba 1-3 on the hardest tier; higher routing ranks perform best in gated or phase-diverse configurations. In single-seed language models with about 500M parameters, both improve on Mamba 1/2 in test loss at 2B tokens, but the routing gains do not translate into lower language-model loss. Our best configurations approach Mamba 3 SISO through 10B tokens while remaining behind it and Mamba 3 MIMO in language-model loss.

en
arXiv AI Papers

DR Pixel: Page-Native Deep Research with Vision-Language Models

Complex documents such as scientific papers contain rich information in tables, figures, and equations; however, existing deep research (DR) agents typically reduce papers to OCR-extracted text. We instead ask whether vision-language models (VLMs) can enable page-native deep research: directly retrieving and reasoning over rendered document page images. We introduce DR Pixel, the first open-source end-to-end multimodal DR agent that uses rendered page images as its sole retrieval and reasoning unit, operating over a corpus of 1.06M pages. To evaluate this setting, we construct DRPixelBench, a benchmark on scientific papers requiring reasoning over text, figures, tables, and equations. Surprisingly, page-native DR already works well without training, outperforming OCR-based baselines across state-of-the-art models like GPT-5.4, Gemini-3.5-Flash, and Qwen3.6-27B, while requiring fewer tool calls. We next turn to DR training. A key challenge is that teacher trajectories for agentic supervised finetuning are noisy, mixing critical reasoning and action steps with redundant or failed attempts. To address this, we introduce counterfactual credit reweighting, a fine-grained credit assignment method that weights individual reasoning and action steps by their counterfactual contribution to the final answer. Our training improves retrieval recall by about 15 points and final accuracy by over 10 points on DRPixelBench, and likewise outperforms the untrained baseline on four existing benchmarks. On out-of-distribution ViDoRe-V3, DR Pixel comes within 1.8 points of an oracle that is given the gold pages directly. Our results suggest that the conventional OCR-then-retrieve pipeline is not only unnecessary but suboptimal: directly retrieving and reasoning over visual document pages makes complex DR both more effective and more efficient.

en
arXiv AI Papers

An Experimental Study of Hybrid Retrieval, NLI and Open-source LLMs for Scientific Claim Verification

Claim verification is the task of deciding whether a source text supports a claim, contradicts it, or lacks sufficient evidence. Natural Language Inference (NLI) models can judge whether a single sentence supports or contradicts a claim, but they struggle when the evidence is spread across several sentences. Conversely, Large Language Models (LLMs) can reason across sentences, but may draw conclusions the text does not support. In this experimental study, we test whether a conservative fusion rule, labeling a claim Support or Contradict only when both models agree and defaulting to Not Enough Evidence otherwise, combines their strengths. We construct a benchmark of 2,035 claims from SciFact and CliniFact (858 Support, 152 Contradict, 1,025 Not Enough Evidence). We retrieve the top five most relevant sentences per claim using a hybrid of semantic and lexical (BM25) retrieval, which slightly outperforms either method alone. These retrieved sentences are then provided to every verification model. We then compare a DeBERTa-v3-base-mnli-fever-anli NLI baseline against Llama 3.1 8B, Qwen3 8B, and Mistral 7B. Qwen3 achieves the highest Macro-F1 (0.7937), followed by Llama 3.1 (0.7204) and Mistral (0.6388), while the NLI baseline reaches only 0.3157. Contrary to our hypothesis, fusion degrades performance, dropping Macro-F1 to 0.7392, 0.6730, and 0.5991, respectively. To understand this decline, we analyze agreements, disagreements, and common error patterns between the NLI and LLM verifiers. Our error analysis shows that NLI and LLM disagreements often result in correct LLM predictions being overturned.

en
arXiv AI Papers

PACERec: Progressive Adaptation of LLM Item Embeddings with Collaborative Evidence for Recommendation

Large language model (LLM) embeddings have been increasingly adopted in sequential recommendation to encode static item attributes and alleviate the limitations of item ID embeddings under sparse interactions. However, these embeddings typically capture only static content similarity while neglecting sequential transitions, and since their adaptation quality relies on sparse per-item updates or global geometric calibration, existing methods still struggle to explicitly transfer preceding interaction contexts from frequent to long-tail items under unevenly distributed behavioral evidence, limiting recommendation effectiveness across the catalog. To address this challenge, we propose PACERec, an ID-free progressive adaptation framework that incorporates preceding interaction contexts into semantic representation adaptation by learning a shared velocity field from items with sufficient interactions via frequency-weighted flow matching. In this way, PACERec progressively guides static LLM embeddings toward collaborative behavioral targets while preserving original item semantics, overcoming sparse per-item updates to effectively generalize sequential transition patterns to long-tail items for both user modeling and candidate scoring. Extensive experiments on three real-world datasets across three sequential backbones demonstrate the superiority of our method over competitive baselines in both overall and long-tail recommendation.

en