Noticias de IA - ítems

arXiv:2610.29538v1 Announce Type: cross Abstract: Direct preference optimization (DPO) incurs training costs in output scoring, sequence execution, and backpropagation, so reducing supervision alone does not necessarily save computation. We introduce a unified framework for stochastic pruning of the DPO computation graph that independently samples response positions for scoring, response prefixes for execution, and preference branches for backpropagation. By making these selections before the corresponding operations, the framework omits computation at each stage of a training step. Our analysis characterizes the objective changes induced by position and sequence pruning and uses inverse-probability weighting to obtain a conditionally unbiased single-branch gradient estimator for the sampled objective. Controlled measurements show that position and sequence pruning primarily reduce peak memory, with most output-memory savings attributable to an implementation that retains full response supervision. Branch pruning yields a $1.426\times$ step-time speedup over a concatenated DPO baseline and reduces training time by about 30\% relative to stock DPO across two model families, with slightly lower mean accuracy and benchmark-dependent changes in open-ended scores. These findings relate the resource benefits of stochastic graph pruning to the computation omitted and the resulting changes in the training objective.

arXiv:2610.29533v1 Announce Type: cross Abstract: Autoregressive (AR) models have proved effective for zero-shot prediction from longitudinal electronic health records, but impose strictly sequential generation on trajectories containing temporally clustered and interdependent clinical events. We investigate block-based masked diffusion (BD) as an alternative on MIMIC-IV under matched tokenisation, context length, model capacity, and evaluation conditions. Across block sizes, BD exhibits a clear quality--efficiency trade-off, with small-block configurations retaining much of the predictive performance of AR while enabling substantially faster inference. A representative $B{=}8$ configuration achieves approximately $1.43\times$ faster evaluation. Although generative rollout remains below AR in most settings, frozen linear probes on BD and AR representations achieve near-identical performance across clinical prediction tasks, indicating that BD learns comparably informative clinical representations. Increasing the denoising budget yields diminishing returns, while alternative decoding strategies provide limited gains. Overall, our results show that block diffusion is a viable and computationally attractive approach to longitudinal EHR modelling, with further improvements in iterative decoding offering a promising route toward closing the remaining generative performance gap.

arXiv:2610.29528v1 Announce Type: cross Abstract: Masked language modelling (MLM) is the dominant pretraining objective for transformer encoders applied to longitudinal electronic health records (EHRs). However, reconstructing individual events may overemphasise noisy or weakly informative observations and does not explicitly encourage learning higher-level patient states. Joint-Embedding Predictive Architectures (JEPAs) instead learn by predicting representations in latent space and have shown strong performance in a variety of domains. In this paper, we investigate to what extent JEPA can be adapted to EHR sequence representation. Our empirical investigation using MIMIC-IV shows that although all three of our JEPA formulations train stably without representational collapse, they consistently underperform standard MLM. We find that target size, not target heterogeneity, increases prediction error, yet reducing the target size does not recover downstream performance. This suggests that stable latent prediction alone is insufficient for competitive EHR representation learning and highlights the challenge of defining clinically meaningful latent targets for EHR.

arXiv:2610.29518v1 Announce Type: cross Abstract: While Chain-of-Thought (CoT) prompting improves the reasoning performance of large language models (LLMs), recent studies have shown that final answers do not always depend on the generated rationales. In particular, LLMs may rely on query-specific shortcuts rather than the information provided by their reasoning steps. In this paper, we investigate whether context-aware decoding (CAD), an existing contrastive decoding method, can mitigate such shortcut behavior when applied to CoT reasoning. We study this application as Rationale Contrastive Decoding (RCD), which contrasts the next-token distributions conditioned on the query with and without its rationale, amplifying tokens whose likelihood increases due to the rationale. We provide a theoretical interpretation of this decoding rule via a KL-regularized reward-maximization objective. Experiments across five reasoning benchmarks demonstrate that RCD improves answer accuracy over standard CoT. Furthermore, intervention analyses using ground-truth and random rationales reveal that RCD increases the behavioral dependence of final answers on the rationale content. Our findings suggest that contrastive decoding offers a simple, training-free approach to mitigating query shortcuts.

arXiv:2610.29507v1 Announce Type: cross Abstract: Temporal reasoning is widely assumed to decompose into two modes: temporal arithmetic (date and time calculations), and temporal semantics (understanding temporal and causal relations). This dichotomy shapes how benchmarks are designed, how models are trained, and how progress is measured, yet its empirical validity has never been directly tested. We provide two lines of evidence that challenge it. First, we test whether tasks labelled as arithmetic or semantic by the benchmarks support transferable gains within their purported mode. Finetuning on these subsets yields predominantly dataset-specific gains ($+6.8$ to $+23.1$ percentage points), while transfer to a different dataset in the same mode ranges from $-3.2$ to $+1.1$ percentage points. Across the two benchmark families used in the transfer analysis, this pattern provides little evidence of coherent, transferable temporal abilities. Second, using cognitive-demand-based model evaluation, we examine which capabilities actually drive performance on these benchmarks. We find that quantitative and logical reasoning, the assumed proxies for temporal arithmetic and temporal semantics, are not the primary drivers; knowledge is. Together, these findings show that current temporal reasoning benchmarks do not cleanly realise the arithmetic-semantics distinction and instead largely reward models for remembering how time typically works.

arXiv:2610.29504v1 Announce Type: cross Abstract: Time series foundation models (TSFMs) perform unevenly across forecasting tasks. Recent work uses agentic model orchestration (AMO) to select or combine TSFMs, often outperforming individual forecasters. Yet these gains may reflect stronger or more complementary candidates rather than better orchestration. To disentangle these effects, we introduce FairAMO, a controlled evaluation protocol with frozen candidate forecasts. Experiments on GIFT-Eval show that AMO improves accuracy, but its gains are bounded by the candidate TSFMs. The best orchestrators reduce MASE by less than 6% relative to the best single TSFM across all tasks. These gains depend on complementarity (different candidates excel on different tasks) rather than the number of candidates. Adding members yields diminishing returns, and a redundant member can erase these gains. The value of historical evidence also saturates quickly. A few recent windows capture all gains, and further history adds none. These findings separate system-level forecasting gains from the contribution of orchestration itself.

arXiv:2610.29498v1 Announce Type: cross Abstract: Process reward models (PRMs) provide fine-grained supervision for multi-step reasoning, yet obtaining reliable process labels remains a central bottleneck. Existing approaches typically rely on human annotation, rollout-based estimation, or auxiliary verification. In this work, we explore a different source of process supervision natively exposed by Mixture-of-Experts (MoE) models: expert routing. We show that simple routing statistics provide an intrinsic process-confidence signal that is competitive with conventional output-logit confidence. Building on this observation, we construct routing confidence by combining overall routing mass, head routing mass, and within-step routing variation, and introduce RoCo-Rethink, which identifies the least confident reasoning step and selectively regenerates the subsequent trajectory. We further introduce RoCo-PRM, which uses a strong MoE to automatically annotate reasoning trajectories with routing-derived step scores and distills them into a standalone PRM. Across multiple MoE architectures and diverse reasoning tasks, both RoCo-Rethink and RoCo-PRM consistently outperform strong baselines, while RoCo-PRM transfers effectively across both model architectures and tasks. Our findings suggest that expert routing is more than a computational dispatch mechanism: it provides an architecture-native source of process supervision for reasoning.

arXiv:2610.29476v1 Announce Type: cross Abstract: We propose a new generative modeling framework grounded in forward-backward partial differential equations (PDEs). These equations arise naturally in mean-field game (MFG) theory, and are closely related to nonlinear Schr\"odinger systems. Our main contribution is to reinterpret this connection within the setting of generative modeling and to develop an efficient numerical methodology for its practical implementation. Specifically, we derive and characterize a nonlinear extension of the classical Schr\"odinger bridge problem through a coupled system of PDEs, yielding a model we call SBNL (Schr\"odinger Bridge NonLinear). To compute its solution, we design a simulation algorithm based on branching diffusions and the probabilistic representation of semilinear PDEs. The resulting method is embarrassingly parallel, scalable to high dimensions, and applicable to a broad class of nonlinear interaction functionals. We validate the approach through numerical experiments, including recovery of the classical Schr\"odinger bridge, nonlinear extensions with convex penalties (Gross-Pitaevskii) as well as potential interaction terms, and high-dimensional generative tasks such as image synthesis on the MNIST and FFHQ human face dataset. Furthermore, the same framework embeds score-based generative modeling, diffusion models, and tractable gaussian Schr\"odinger bridges.

arXiv:2610.29472v1 Announce Type: cross Abstract: Large language models (LLMs) have shown great potential as general-purpose user simulators for interactive systems. Prior studies have demonstrated that training on high-quality data can substantially improve model reasoning and downstream task performance. However, the upper bound of user simulation is still constrained by the model's reasoning paradigm: native chain-of-thought often degenerates into shallow pattern matching and fails to adequately model the behavioral factors underlying real user decisions. In this paper, we propose OmniSimulator, a novel training framework designed to improve the predictive ability of small LLMs for realistic user simulation on short-video platform environments. Specifically, OmniSimulator organizes behavior-oriented reasoning through a structured schema with five dimensions, carefully selects data from real user-behavior scenarios, and introduces a teacher model to generate high-quality reasoning traces under the proposed schema, helping small models learn behavior-relevant reasoning patterns rather than relying on superficial behavioral correlations. Based on this process, we construct 9,881 high-quality training instances from three months of historical interaction trajectories of 200 real users, averaging about 50 distilled examples per user. Experimental results show that OmniSimulator improves the average score of Qwen3-8B by 34.33%, achieves performance competitive with Claude-Sonnet-4.5, and supports smaller-scale, self-hosted deployment. These results suggest that learning structured behavior-oriented reasoning patterns is a promising direction towards scalable and high-fidelity LLM-based user simulation.

arXiv:2610.29458v1 Announce Type: cross Abstract: Agent harnesses have become a central component of modern agentic systems, shaping how models use tools, manage context, and coordinate long-horizon interaction. Realizing the benefits of these harnesses depends on how effectively the underlying model can make use of them, motivating reinforcement learning directly through the harness. However, existing approaches typically train through a single fixed harness, which can lead to specialization and limited transfer across harness configurations. To address this, we introduce \textbf{Harness Scaling}, a new scaling dimension for agentic RL that extends training from a single harness to diverse execution configurations. Concretely, we construct a factorized harness space, select a compact training subset with balanced factorial coverage, and organize cross-harness training to combine global coverage with controlled variation for the same task. Across multiple benchmarks, model scales, and RL algorithms, Harness Scaling consistently improves generalization to unseen white-box configurations. Moreover, models trained through structured white-box variation transfer effectively to unseen external black-box harnesses, outperforming models trained through a single complex black-box harness. These results establish harness diversity as a meaningful scaling dimension for agentic RL and highlight the importance of how this diversity is organized for cross-harness generalization.