overfeed.news
Anuncio

Privum

Construimos, protegemos y operamos tu infraestructura digital.

Software, sistemas de IA, pruebas de penetración y nube segura para empresas.

Hablar con Privum

Tema

LLMs

3024documentos

265últimos 7 días

arXiv AI Papers

ACE: Adaptive Calibration-Free Expert Skipping for MoE-based LLMs

Mixture-of-Experts (MoE) architectures provide an efficient paradigm for scaling large language models (LLMs), yet fixed top-k routing activates the same number of expert slots for every token, causing substantial redundant computation. Existing expert-skipping methods often rely on router confidence, calibration data, or additional training, and therefore cannot reliably estimate the actual contribution of routed experts. To this end, we propose ACE, a training-free, calibration-free, and checkpoint-preserving framework for token-adaptive expert skipping in MoE-based LLMs. ACE contains two complementary components: 1) Global Spectral Proxy (GSP), which estimates global transformation capacity from the coupled gate, up, and down projections together with RMSNorm scaling; and 2) Router-Conditioned Refinement (RCR), which constructs expert-specific direction prototypes from centered router weights and evaluates expert responses along routing-preferred directions. During inference, ACE combines both estimates with runtime router gates and skips an expert slot only when both views identify it as low-contribution, while always retaining the top-1 expert. All expert statistics are computed offline, leaving only table lookups and lightweight scalar operations online. Extensive experiments across three MoE-based LLMs and eight benchmarks demonstrate that ACE consistently outperforms existing static and dynamic baselines, with increasingly pronounced advantages under aggressive expert skipping. For instance, at a 50% skipping ratio on Qwen3.6-35B-A3B, ACE reduces WikiText-2 perplexity by 7.96% and improves average downstream accuracy by 4.15 percentage points over the strongest competing method.

en
arXiv AI Papers

CABAL: Multi-Agent Simulacra for Tracing the Effects of Collusive Bidding in Peer Review

Recent reports during the AAAI-27 review cycle highlight the risk of reviewers coordinating bids for reciprocal assignment advantage. Prior work treats bidding, reviewer assignment, and review manipulation as separate stages, leaving the lifecycle effects of collusive bidding unclear. Real-world analysis is further constrained by typically unobservable collusive intent and the lack of counterfactuals for the same conference. Motivated by this gap, we introduce , an end-to-end multi-agent simulacra framework for studying reviewer assignment integrity by holding the conference environment fixed and configuring LLM-driven reviewer agents with honest or collusive policies. We further develop an affinity-guided collusive bidding strategy that uses mutual reviewer-paper affinities to construct collusion rings and select target papers, producing expertise-consistent rather than arbitrarily targeted attacks. Controlled experiments show that collusive bidding more than doubles target-paper capture and that assigned colluders score target papers about two points higher than honest co-reviewers, while conference-wide effects remain comparatively modest. Evaluated bid-phase detectors provide only limited evidence of collusion: in a fixed-triplet detector stress test, native positive-bid graphs are confounded by benign affinity, while a Very-High-only diagnostic view enables precise but low-coverage local recovery.

en
arXiv AI Papers

A Verifier-Guided Explainable Reasoning Framework with Gold-Anchored QLoRA, Task-Aware Mixture-of-Experts, and Group-Relative RLVR

Large language models (LLMs) show strong reasoning ability, but their explanations can remain inconsistent, weakly grounded, or difficult to verify. We propose a verifier-guided explainable reasoning framework for transparent educational question answering that combines gold-anchored QLoRA, task-aware symbolic routing, and group-relative RLVR. Qwen2.5-3B-Instruct is first adapted with field-weighted QLoRA supervision anchored to authoritative answers. A lightweight router then assigns logic problems to a FOL/Z3 verifier and physics problems to a formula- and unit aware symbolic solver. Verifier feedback is further used to support candidate evaluation, self-revision, and reward construction during RLVR. Candidate responses are evaluated along three complementary dimensions: P1 for answer correctness, P2 for evidence or unit consistency, and P3 for reasoning depth and explainability. At inference, gold-free self-consistency aggregates multiple candidate responses before an optional question-only physics verifier performs conservative system-level correction. On 438 held-out examples, RLVR increases P3 from 50.68% to 72.20%, while hybrid P1 remains approximately stable at 55.94%. Self-consistency improves model only P1 from 48.86% to 50.23%, with symbolic verification providing the remaining hybrid gain. These results indicate that RLVR primarily strengthens explicit reasoning structure, while symbolic verification complements the neural policy by improving answer reliability at the system level.

en
arXiv AI Papers

What Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection

On-Policy Distillation (OPD) has emerged as a widely adopted post-training paradigm for enhancing large language models in reasoning domains. However, the data-centric mechanisms in OPD remain relatively underexplored. This paper presents a empirical study of data efficiency and data selection in OPD. We begin by investigating an extreme setting: training OPD on only one example, namely 1-shot OPD. Surprisingly, we find that 1-shot OPD is consistently effective across all sampled training examples and harder examples often yield superior performance gain. We next investigate what actually drives the student model's improvement in the training data. Our analysis reveals that the improvement is not driven by high token entropy, but the longer CoT paths which hard problems naturally generate. Training on longer CoT can help maintain closer alignment with the teacher over a long reasoning horizon, and learn critical thinking patterns usually missing in short CoTs, such as reflection (e.g., ``Alternatively''). Based on these insights, we propose a simple data selection method that selects only hard examples for training, where even ``unsolvable'' examples that completely exceed the teacher's capability can be successfully used. Our experiments conducted on four models ranging from 1.5B to 7B show that training the student model on only 8 selected hard examples matches the performance of the 17K dataset baseline.

en
arXiv AI Papers

Can Large Language Models Anticipate Behavioral Responses to Social Policies? A Case of Pension Enrollment Prediction among China's Flexible Workers

Assessing the impacts of social policy changes is a widely acknowledged challenge for policymakers. Econometric methods can be unreliable when extrapolating to hypothetical scenarios, while field pilot programs are highly costly. In this paper, we propose using large language models (LLMs) as policy-assessment tools adapted from general-purpose models. We present FlexPension-LLM, the first domain-specialized large language model for a hierarchical pension-enrollment prediction task among flexible workers in China, and introduce DKI-RDistill, which injects policy-grounded cues into the prompt, including Probit-derived marginal effects and hukou-province pension rules. The method then uses LoRA/SFT to distill rationale-augmented supervision into an open-weight MoE student, with teacher errors corrected by regenerating those cases under ground-truth labels. On a CHFS 2019 blind split, FlexPension-LLM achieves 0.9316 Composite F1, surpassing its Claude Sonnet 4.5 teacher and 15 of 17 baselines, and is statistically indistinguishable from Claude Opus 4.6. Across four external surveys, it averages 0.7549 Composite F1 and shows the narrowest performance range among the strongest systems. Component analysis shows that gains come mainly from policy-grounded cue injection and error-filtered supervision, while rationales provide decision traces that can be checked against policy rules.

en
arXiv AI Papers

AxQM: A Textbook-Scale Benchmark for Formal Proof Synthesis in a Library of Finite-Dimensional Quantum Mechanics

Formalizing mathematics in a proof assistant, where a machine checks every definition, statement and proof, has set a new standard of rigor. Large language models are now capable of formalizing autonomously, even at the scale of whole textbooks. We bring this standard of rigor to physics, where theoretical arguments carry idealizations that are rarely stated fully, and any logical gaps could have a cascading effect on interdependent results. Recognizing the need to evaluate autoformalization systems for physics, we release AxQM, 1,019 kernel-checkable proof-synthesis tasks over 479 items drawn from the textbook Quantum Computation and Quantum Information by Nielsen and Chuang. The tasks are stated in a custom Lean library of finite-dimensional quantum mechanics. By task count, it is the largest proof-synthesis benchmark in physics by a factor of four. AxQM is derived from a near-complete formalization of the formal portions of the textbook, so every task is guaranteed a solution, which we keep private. Grading of the benchmark is done deterministically by the Lean kernel, which checks that the proof compiles, that no sorry appears in it or in any declaration it depends on, and that it introduces no new axioms.

en
arXiv AI Papers

Compression Beyond the Uncompressed: A Two-Stage Training Recipe for Soft Context Compression in RAG

Retrieval-Augmented Generation (RAG) enhances language models with external knowledge, but the lengthy retrieved context inflates the input and degrades inference efficiency. Soft context compression encodes each document into a substantially shorter embedding sequence. However, most existing approaches are trained by distilling outputs from uncompressed RAG systems, inherently limiting their performance relative to the original model. To address this limitation, we propose DEX-Comp, a two-stage training recipe: Pure Distillation warm-starts the compression model on the uncompressed RAG's correct responses only, and Hard Exploration then runs reinforcement learning solely on queries the uncompressed RAG fails, forcing the model to explore computation patterns better suited to compressed representations. On five open-domain QA benchmarks at retrieval depths from top-5 to top-30, DEX-Comp compresses retrieved contexts by 16and accelerates inference by 4--24, while achieving performance comparable to or exceeding the uncompressed RAG baseline across retrieval depths. Ablations and evaluations across diverse datasets and backbones further confirm the contribution of each stage and the generalization of our approach.

en
arXiv AI Papers

Large Language Models with At Most One Spike per Neuron

Leveraging their inherent sparse event-driven computation, spiking neural networks (SNNs) offer a promising path toward energy-efficient large language models (LLMs). Time-to-first-spike (TTFS) coding generates at most one spike per neuron within a time window, yielding extremely low firing rates. However, conventional TTFS SNNs are restricted to specific structures, making it challenging to encode certain blocks in LLM -- such as layer normalization and matrix multiplication --using TTFS. To overcome this limitation, we introduce a reference-based strategy specifically to encode the four core LLM components: embedding layers, layer normalization, attention-related operations and dropout. We construct a fully TTFS-based SNN architecture and train it end-to-end. Experiments on modern LLMs like BERT and GPT-2 demonstrate that our approach achieves performance comparable to ANN counterparts on natural language understanding and common-sense reasoning, while a clear gap remains on language modeling perplexity. To the best of our knowledge, this is the first work to scale a spiking LLM to 1.5 billion parameters using TTFS coding. We also report an estimate of spike-related energy; this is a spike-count proxy under an established cost model rather than a measurement on neuromorphic hardware.

en
arXiv AI Papers

From Vision to Language: Investigating Causal Information Flow in Multimodal Decision-Making

Vision-Language Models are commonly evaluated through their final predictions, but understanding whether these decisions are grounded in visual evidence requires tracing how visual information contributes to language-based decisions. With this purpose in mind, we investigate cross-modal information flow in a video-based generative multiple-choice-like setting by applying a layer-wise causal intervention on video-text attention pathways. We target spatial, causal, and temporal visual reasoning. Our results show that visual information is mainly integrated while the model processes the candidate answer options, which serve as the primary textual grounding sites for the final decision. We further show that nouns play an important role as semantic anchors during multimodal enrichment, while verbs are more relevant when temporal relations are processed. Finally, we identify a distinct pattern in temporal reasoning, suggesting that VLMs struggle to reconstruct sequential information across video frames, but we remark that such fragility may also reflect linguistic biases associated with specific temporal expressions used for defining the relation between events within a scene.

en
arXiv AI Papers

A Human-in-the-Loop Framework for AI-Assisted Scoring in Large-Scale Writing Assessment

The integration of artificial intelligence (AI), particularly large language models (LLMs), into educational assessment has opened new opportunities to enhance the efficiency and scalability of grading processes. This study presents the design and validation of an AI-assisted scoring framework for written responses in a large-scale national assessment. The proposed approach focuses on short written texts of approximately 150-200 words and incorporates a human-in-the-loop strategy to preserve assessment quality while reducing manual workload. The study is grounded in a real operational context, using data from two recent editions of a nationwide test, each comprising approximately 5,000 student responses. We analyze the alignment between AI-generated scores and human raters across multiple rubric dimensions, as well as the impact of the proposed decision flow on pass/fail outcomes. Results show moderate to high agreement between the model and human evaluations in most dimensions, supporting the feasibility of AI assistance in this setting. Moreover, the proposed correction workflow identifies cases where human review is most valuable, enabling a more efficient allocation of expert effort. The findings suggest that AI-assisted scoring can be safely integrated into large-scale assessment processes only when combined with carefully designed human oversight. The paper concludes by discussing practical implications for deployment in national assessment systems and outlining future research directions, including longitudinal monitoring of model-human alignment and the analysis of potential cognitive bias introduced by AI-supported review workflows.

en
Hugging Face New Models

XHToken/Spark-X2.5-1.7B

New text-generation model. Tags: spark2_5, text-generation, llm, sparkx2_5, conversational, custom_code, base_model:XHToken/Spark-X2.5-1.7B-Base, base_model:finetune:XHToken/Spark-X2.5-1.7B-Base

en♥ 70
arXiv AI Papers

Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared Endpoints

Language-model judges now gate training data, score generations, and drive leaderboards. The judge is then a measurement instrument, resting on one rarely stated assumption: the same request, sent to the same model name, reads the same tomorrow. We audited that assumption in two preregistered campaigns with every threshold fixed in advance; neither got past validating its instrument. Across 52,988 audited request attempts, same-window repeat rankings agreed at Spearman 0.400 against a required 0.90, and byte-identical next-day replays agreed at 0.78 against a required 0.99, each time with the execution record at ceiling. Three mechanisms explain the gap: a label-to-meaning mapping that biased readouts as strongly as the signal; candidate gaps seven orders of magnitude below the instrument's own noise floor; and byte-identical inputs returning different rankings, a noise that exact-permutation readouts compound. Neither metric substitution nor sampling repaired it on the tested grid. Preregistered follow-ups bound the problem: waiting did not help on the days sampled (0.805 versus 0.800, replicated over five further days); switching providers did not help (four providers share the floor, medians 0.74 to 0.88, predicted by none of the metadata fields they expose); self-hosting on batch-invariant kernels helped only while the server was quiet; and on constructed errors with known gaps, the readout's separation tracks error type, not size. We distill the evidence into a three-level snapshot-identity ladder, eight design rules, and a reporting checklist; a pilot at roughly 2% of the study's call volume would have exposed both unreachable gates in advance. All results concern externally measured behaviour on shared serving infrastructure. On a shared endpoint, a model name is not a frozen instrument; a preregistered evaluation must measure its instrument before freezing any gate on it.

en
arXiv AI Papers

Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought Reasoning

Reasoning traces from chain-of-thought models appear to offer a legible window into how a model arrives at its answer. A growing body of work treats them as such, using LLM judges to diagnose errors, evaluate faithfulness, and provide step-level supervision via process reward models and generative critics. These practices rely on the text of a reasoning step carrying information about its functional role. But does the text actually encode information about which reasoning steps matter? We operationalize the importance of a reasoning step as its advantage: the change in expected reward, e.g., producing the correct final answer, from including that step, estimated via Monte Carlo rollouts. Basing ground truth on these estimates, we evaluate whether LLM judges can identify high-advantage steps and find that sufficiently capable LLMs can outperform a prevalence baseline but fall well short of a noise ceiling. Fine-tuning a model as a step-level critic yields strong improvement for incorrect responses but remains distant from ceiling for correct responses, suggesting that step importance is only partially recoverable from the text of the reasoning trace. Our findings contribute to a growing body of chain-of-thought faithfulness work that cautions against treating the legibility of reasoning traces as interpretability, especially with implications for process reward modeling.

en
arXiv AI Papers

Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning

Weakly-Supervised Dense Video Captioning aims to localize and describe multiple events in untrimmed videos given only an ordered set of event-level captions per video. Recent work synthesizes auxiliary transition captions via LLM to provide additional vision-language alignment, but these captions lack visual grounding and are rigidly assigned to every inter-event gap at a fixed location and duration. To address these, we propose Seeing Before Synthesizing (SBS), a framework that adaptively provides visually grounded linguistic guidance only where warranted. Leveraging a VLM, we generate frame-level narratives for the inter-event gaps and detect transitions from the semantic variation across them. For identified transitions, we then refine inter-event temporal masks by blending the temporal midpoint with the semantic change point and selecting the width that maximizes vision-language alignment. Experiments on ActivityNet Captions and YouCook2 demonstrate state-of-the-art performance in both captioning and localization.

en
arXiv AI Papers

Knowledge Acquisition During Pre-training? Large Language Models Learn Better With Auxiliary Views

Gaps remain in our understanding of how large language models (LLMs) acquire knowledge during pre-training. We posit that auxiliary views, reformulations of knowledge, are causally helpful for learning. We design controlled experiments to isolate this. First, we confirm that repetition is necessary for acquisition and clarify that paraphrasing helps only at smaller batch sizes. Second, holding the token budget fixed, allocating tokens from document repetition to auxiliary views improves learning, counterintuitively, even for factual recall. Third, the effectiveness of auxiliary views is not contingent on the strength of the teacher model that generates them. Fourth, we identify forms of knowledge, contextual and foundational, that aid learning in the presence of prior knowledge gaps. Finally, we examine how these effects manifest mechanistically via layer-wise biases and compression. Together, our findings suggest that auxiliary representations of knowledge, which arise naturally in large pre-training corpora, are a key factor in the success of pre-training and offer a plausible explanation for why data diversity matters.

en
arXiv AI Papers

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

On-policy distillation (OPD) combines student-generated rollouts with dense token-level supervision from a teacher. Existing work has mainly studied its algorithmic behavior, leaving the role of training data unclear. We examine this role at the data-minimal limit by training on a single query. One-shot OPD keeps improving for hundreds of steps and recovers most of full-data OPD's gain across task domains and model families. We explain this result through the states visited during training and the rate at which the student aligns with the teacher. We measure state coverage, the fraction of the states full-data OPD visits that a query set's rollouts reach. A single query already reaches (71.5\%), most of it within the first 100 steps. Adding semantically distinct queries raises coverage and validation accuracy together, until 16 queries reach (98.9\%) and match full-data training. Yet alignment slows at a similar pace whether OPD trains on one query or the whole dataset, and even a fixed set of states takes hundreds of steps to absorb. OPD is therefore data-overfed but algorithm-starved. Its rollouts quickly expose broad supervision, while the student absorbs that supervision increasingly slowly. The state-coverage result extends to multi-teacher OPD, where 16 semantically diverse queries per domain match full-data MOPD. As a further stress test, content-light templates and off-domain WildChat queries also approach the real-query baseline. Task content and induced state coverage can therefore come apart. We hope these findings direct future work toward the step efficiency of OPD, and prompt a re-examination of the data and the mechanisms behind its recent successes in frontier post-training.

en
arXiv AI Papers

A Case Study on Emergent Cheating and Whistleblowing in Autonomous Research Swarms

Multi-agent AI science ecosystems rely on agents possessing tools that allow them to communicate, coordinate, and build on each other's work. Yet this shared infrastructure can also introduce vulnerabilities by creating a substrate for the contagious spread of unintended and undesirable behaviors. We report a case study on a research collective of 100 autonomous LLM agents tasked with proving formal mathematical conjectures. Within the swarm, cheating spontaneously emerged and was later challenged by whistleblowers - both without any external intervention. When a single agent discovered an exploit in the evaluation system, it propagated across the collective via a shared knowledge library and later through peer-to-peer messages. Despite early reluctance, a cohort of agents adopted the exploit in response to competitive pressure. A separate group of agents produced an emergent counter-response: auditing fraudulent proofs, alerting peers across broadcast and private channels, staging boycotts, lodging formal complaints, and proposing validation patches. In recent incidents, agent swarms coordinated covertly through improvised side-channels (Dalton and Wallace, 2026; Greenblatt et al., 2026). Our setting differs: the same transparent channels that carried the exploit also gave non-cheating agents the visibility they needed to detect fraud, organize resistance, and enforce norms. We cast the problem of managing the agents' shared infrastructure as the knowledge commons governance problem (Ostrom, 1990). To protect the commons from exploits, we propose to adopt institutional mechanisms, such as graduated sanctioning and collective-choice rules, to support decentralized self-governance in autonomous swarms.

en
arXiv AI Papers

SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering Agents

Repository-level software engineering benchmarks have significantly advanced the evaluation of coding agents, but existing benchmarks primarily measure whether generated patches pass functional tests and overlook review-derived acceptance constraints (review constraints) that often influence whether a patch is acceptable in real-world software development. We introduce SWE-Gate, a repository-level benchmark for software engineering agents that explicitly evaluates review constraint compliance alongside functional correctness. SWE-Gate derives review constraints from real pull request review comments and synthesizes repository-level repair instances around these constraints. Each instance provides separate functional and constraint tests, together with non-compliant and gold patches, enabling explicit separation between issue resolution capability and review constraint compliance. We construct SWE-Gate with 303 repository-level repair instances spanning 75 open-source Python repositories across diverse software domains. Experiments with four LLM backends spanning different capability levels under a common coding-agent scaffold reveal a substantial gap between functional success and success under the complete repair specification: among 644 repairs that pass the functional tests, 221 fail to satisfy the provided review constraints. These findings show that functional-only evaluation overestimates agents' ability to satisfy the full requirements of repository-level repair tasks. The replication package including code, data, and experimental results is available at https://github.com/DeepSoftwareAnalytics/SWE-Gate.

en