Noticias de IA - ítems

arXiv:2610.33539v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems have demonstrated remarkable capabilities across diverse tasks. Yet their memory and collaboration architectures often remain static, constraining continued adaptation and improvement over time. Recent work addresses this limitation by evolving memory or collaboration based on interaction experience. However, updates to these interdependent components are not necessarily aligned: an evolved workflow may require experience that memory does not provide, while evolved memory may encode guidance that the workflow cannot use. To address this problem, we propose CoEvolve, a skill-centered framework for aligned memory--collaboration evolution. CoEvolve represents reusable local collaboration patterns as skills that link evolving collaboration decisions to their supporting memories. It further compares original and counterfactual trajectories to identify local evolution signals, which coordinate updates to the skill library, skill memory, and executor memories across rounds. Experiments on the ALFWorld and WebShop benchmarks confirm that CoEvolve achieves the best overall performance among the evaluated baselines, while ablation studies further validate the effectiveness of aligned co-evolution and counterfactual-guided evolution.

arXiv:2610.33536v1 Announce Type: new Abstract: Financial fraud caused over \$15.9 billion in losses in the United States in 2025, according to the Federal Trade Commission~\citep{ftc2026databook}. Understanding such large-scale harm requires jointly modeling informational and financial dynamics. Yet existing simulators typically capture only one side of this interaction, leaving a gap in modeling how fraud unfolds in the real world. To bridge this gap, we introduce \textsc{FraudSociety}, the first LLM-agent-based simulator that jointly models these coupled dynamics. It integrates a dynamic social environment for information exposure and communication, persistent financial ledgers that preserve payment and loss histories, and a Need-Intent-Action architecture for civilian decision making. Fraudsters further adapt their communication and financial actions to individual interaction histories and ledger states, forming a closed feedback loop between the two dynamics. We validate \textsc{FraudSociety} across macro-level outcomes, micro-level behavior, and intervention effects. At the macro level, the simulated fraud outcomes closely match real-world patterns across multiple key statistics. At the micro level, it reproduces strong loss concentration, with the top 10\% of victimization records accounting for 81.1\% of total losses, consistent with Canadian Anti-Fraud Centre statistics~\citep{cafc2025annual}. Counter-fraud experiments further reveal variation across intervention strategies, with the best-performing personalized intervention reducing the repeat-payment rate from 49.4\% to 10.9\%. These results establish \textsc{FraudSociety} as both a high-fidelity simulator and a scalable testbed for evaluating anti-fraud strategies under diverse intervention conditions, thereby advancing research on financial fraud and its prevention.

arXiv:2610.33528v1 Announce Type: new Abstract: Skill learning enables web agents to reuse prior experience for long-horizon interactive tasks. However, learned skills are typically evaluated in closed environments, overlooking the fact that real-world web deployment involves continuous shifts in invocation context, perceptual grounding, and execution feasibility. To this end, we introduce SkillShift-Bench, the first benchmark for evaluating skill learning with controlled open-environment shifts. SkillShift-Bench simulates Contextual Shift, Perceptual Shift, and Execution Shift across three self-hosted web systems, and evaluates agents with diagnostics covering task success, interaction cost, skill use, and skill failure. Comprehensive experiments reveal systematic robustness degradation under controlled shifts, characterized by lower success rates, higher interaction costs, and more frequent skill failures, with Execution Shift exerting the strongest pressure. We further formulate shifted skill execution as a nonstationary local executability problem and provide both a dynamic-regret analysis and a practical test-time adaptation method, demonstrating the feasibility of improving learned-skill execution without relearning the skill library. Code, tasks, environments, documentation, and the leaderboard are available at https://skillshift-bench.github.io/.

arXiv:2610.33470v1 Announce Type: new Abstract: Web platforms run on multivariate time series, from service telemetry and Web traffic logs to sensor streams served through Web APIs. Yet, retention policies often archive them at coarse granularity to save storage and bandwidth. Decisions such as autoscaling, alerting, and billing operate at finer granularity than existing forecasters reach, since these models predict at the resolution of their input. We therefore introduce Multivariate Time Series Super-Resolution Forecasting (MTS-SRF), which forecasts fine-grained futures from coarse histories, and propose TimeMagnifier to address its three challenges. Fourier Anchor counters data sparsity by fitting each input window to a trend-Fourier structure with sparse cross-variable gating; De-noise Only constrains fine-grained ambiguity by refining along the resolution axis rather than the noise axis, lengthening the grid level by level; and banded DTW Alignment corrects cross-resolution misalignment against the coarse forecast. On the first MTS-SRF benchmark, with ten datasets from five domains, real archived cross-resolution pairs, strengthened baseline adaptations, and five-seed significance tests, TimeMagnifier is best on every dataset, resolution coefficient, and metric against 15 baselines and cuts MSE by 12.3% on average. Its De-noise Only and DTW stages also transfer as a plug-in that lowers the MSE of existing forecasters by 5.1% to 9.0%. Code will be made publicly available.

arXiv:2610.33465v1 Announce Type: new Abstract: Equation discovery solvers often use different data interfaces, equation representations and evaluation criteria, making their results difficult to compare. We present LegoSR, a unified framework for algebraic symbolic regression and differential equation discovery. LegoSR integrates seven solvers through a common equation representation and evaluation process, and supports searches constrained by partially known equations. Researchers can run solvers directly or use LegoSR Agent, which selects solvers and adapts searches based on solver knowledge, intermediate results and lessons from earlier tasks. On noisy ordinary and partial differential equation benchmarks, LegoSR Agent recovers nearly as many equations as the union of seven expert-tuned solvers and outperforms a generic agent with the same model, tools and budget by up to 29 percentage points. Three examples demonstrate basic use, adaptive solver selection and discovery guided by partial physical knowledge.

arXiv:2610.33451v1 Announce Type: new Abstract: The capabilities of large language models (LLMs) and multimodal LLMs (MLLMs) arise from the synergy of the full training pipeline, including data and tokenization, pretraining, and post-training (supervised fine-tuning, preference alignment, reinforcement learning, and continual optimization), rather than any individual stage. Existing surveys mostly adopt a single-stage or single-technique perspective, treating related research as isolated systems without unified stage division or a horizontally comparable basis. This paper proposes a unified stage division and a six-dimensional analytical framework covering data, objective function, optimization strategy, system constraints, evaluation, and risk and governance. We systematically review 395 core references from 2017 to 2026, and present a conceptual map of cross-stage effects: forward constraints of pretraining on post-training, and reverse empowerment of post-training on data and pretraining. We derive three core findings. First, the comparability of scaling laws depends on data quality and mixture, a long-neglected variable. Second, preference alignment methods (RLHF, DPO) and reasoning reinforcement learning with verifiable rewards redefine post-training boundaries, while the Pass@1 versus Pass@K debate remains unresolved. Third, multimodal training poses structural challenges to the pure-text paradigm in tokenizer design, training objectives, and evaluation. The paper provides a cross-stage effects diagram, a method-family map, a practical decision tree, and at least 10 verifiable open problems, with an extensible skeleton for focused sub-surveys per stage. As of the retrieval date, peer-reviewed evidence (A+B) accounts for approximately 79% of the 395 references.

arXiv:2610.33448v1 Announce Type: new Abstract: The development of large language models (LLMs) are capable to assist with hardware experiments. In this scenario, this raises a practical question: Can LLMs determine whether a proposed operation is safe for a specific development board? Documented operating limits and safety requirements are board-specific, even across products from the same manufacturer. This variation makes board-specific safety judgments by an LLM difficult to evaluate. To address this problem, we introduce the BoardSafety Benchmark. The benchmark is built from vendor datasheets and hardware guides. For data transformation, these documents are converted into a board-specific safety rule base and are then used to create labeled operating scenarios. Each data item pairs a board and a proposed operation to an applicable safety rule with ground-truth label, indicating the level of safety. The categorized level for each operation includes safe, unsafe, or insufficient-info. In addition, the benchmark covers diverse operations, board-specific cases, boundary conditions, and missing-information cases. We evaluate a series of models by varying their access to board-specific rules and the use of structured-rationale prompting. Our results demonstrate that providing the safety rules generally improves accuracy, whereas structured-rationale prompting produces gains that vary across models and rule-access conditions. Overall, the evaluated models cannot yet reliably determine whether an operation is safe, which implies that critical exploration is required for this field.

arXiv:2610.33432v1 Announce Type: new Abstract: Long-term memory is critical for autonomous Large Language Model (LLM) agents executing multi-session, long-horizon tasks. However, existing memories often inappropriately store, retain, or retrieve over-generalized, misattributed, or privacy-sensitive information, a problem we term memory misalignment. To study this problem, we construct \textbf{MemAlign}, a benchmark comprising 1,079 curated memory cases grounded in synthetic, validated multi-session conversational contexts covering diverse misalignment taxonomies. We then propose ConMem, an algorithm that reframes retention decisions as prospective counterfactual causal inference. \textbf{ConMem} synthesizes counterfactual interaction scenarios to prospectively audit downstream intervention effects across three aspects: relevant task execution, irrelevant invariance checks, and risk-sensitive boundary shifts. Experiments show that ConMem outperforms other methods, achieving 75.16\% accuracy, 64.15\% balanced accuracy, and a Macro-F1 of 65.31\%, effectively mitigating over-retention biases without sacrificing personalization utility.

arXiv:2610.33410v1 Announce Type: new Abstract: Time-series tasks require both accurate predictions and fast decisions. Advances in large models have introduced decision-oriented models that directly output answers and their probabilities, which we call Structured System 1 models. Their applicability to time-series tasks remains underexplored. Using Jev 1.13.0 as a case study, we evaluate time-series classification, event type prediction, oil temperature direction and stock movement prediction, converting continuous forecasting targets into discrete decisions to fit the model interface. We establish a unified evaluation framework using accuracy and AUC. Results show stronger performance on selected explicit temporal patterns and event type prediction, but near-chance discrimination on many numerical sequence classification tasks and stock movement prediction. Some datasets also reveal a gap between ranking quality and final decision accuracy. These findings motivate improvements in temporal representation, domain adaptation, and decision-score alignment. Standardized sample construction, model calls, and result recording support extending the evaluation to future models.

arXiv:2610.33405v1 Announce Type: new Abstract: Large language models (LLMs) have attracted great attention in both academic and industrial communities in recent years. Numerous survey studies have covered various aspects of LLMs, such as learning strategies, applications, alignment, explainability, and evaluation. However, little headway has been made in reviewing data-related aspects for LLMs, despite data being recognized as a key factor contributing to the emergence of the LLMs era. A wide range of data optimization algorithms and techniques are employed in LLMs' training and application processes. These techniques often originate from diverse deep learning domains, with their theoretical inspirations and heuristic motivations appearing unrelated to each other. This study aims to develop a comprehensive framework for LLMs' data optimization techniques to enhance data utilization and efficiency. We first discuss data challenges in LLMs' training and inference. Second, we summarize data perception dimensions for evaluating LLMs' data properties. These dimensions primarily include quality, difficulty, diversity, and redundancy, laying a foundation for subsequent optimization. Third, existing optimization techniques are reviewed and categorized into four groups: data selection, augmentation, reweighting, and others. Fourth, we analyze interconnections between these categories. Finally, we identify key challenges and future directions for LLMs' data optimization compared with conventional deep learning approaches.