Noticias de IA - ítems

arXiv:2610.27205v2 Announce Type: replace-cross Abstract: Web agents are typically evaluated on English-language interfaces, leaving their ability to operate across the world's multilingual websites largely unexplored. This gap is especially significant for low-resource languages, where standardized resources for evaluating web agents remain limited. To address this gap, we introduce Low-Resource Web Agent Benchmark (LoWAgent), a benchmark for evaluating web agents across different low-resource languages (LRLs) in comparison to the default, English. LoWAgent evaluates web agents across English and four LRLs: Hindi, Bengali, Urdu, and Amharic. The benchmark comprises of six fully localized websites, instantiated across five languages to yield 3,000 task instances. We evaluate three closed-source and five open-source models across all five languages on all six websites. Our findings show that both closed-source and open-source models experience performance degradation for LRLs compared to English, with substantially greater performance drops observed among the open-source model agents. We further evaluate the robustness of the models on realistic interface disruptions, such as cookie notices and advertisement pop-ups, and find that these further degrade agentic performance. Finally, we show that post-training on a small subset of LoWAgent traces can significantly improve low-resource language agentic task performance, demonstrating the usefulness of our benchmark.

arXiv:2610.26645v2 Announce Type: replace-cross Abstract: As people increasingly rely on large language models (LLMs) for information, model providers need to communicate meaningful estimates of whether individual responses are correct or, more generally, reliable. In the context of hallucinations, existing work uses multicalibration to make such reliability predictions meaningful across application-relevant groups, such as prompt topics. Topic groups alone, however, can conceal systematic errors: within the same topic and confidence level, responses with different chain-of-thought (CoT) properties may exhibit opposing errors that cancel on average. In this work, we introduce reasoning-aware multicalibration, a framework that supplements application-relevant topic groups with groups derived from observable properties of CoT traces. We highlight that, theoretically, groupings based on CoT are "internally important", i.e., groupings for which the multicalibration guarantee is not societally crucial as it is for high-risk topics, but whose inclusion in the multicalibration procedure could easily and significantly improve predictive accuracy of the final reliability predictor. Empirically, we apply our framework to hallucination prediction and unsafe-response detection across a variety of benchmarks, and find that adding CoT groups to topic-based calibration reduces Brier score in both tasks. Interestingly, we find that multicalibrating with respect to CoT groups alone (without any topic information) already improves calibration across topics, suggesting that the predictor's errors depend on how the model reasoned, rather than what it was asked about in the prompt.

arXiv:2610.25844v2 Announce Type: replace-cross Abstract: Training high-quality diffusion models is computationally expensive, and inference-time guidance often adds further sampling cost. In this work, we introduce Swift, a simple yet effective self-guided training method that uses a frozen weak denoiser to improve a stronger model without adding inference overhead. For each noisy input, Swift extrapolates the clean regression target away from the weak denoiser's prediction, amplifying components that remain underfit. The weak guide can be an early training checkpoint, requires no backpropagation during main-model training, and is discarded afterward. The resulting model retains the original sampler and supports both conditional and unconditional generation without label dropout or an unconditional branch. We explain this mechanism through a spectral analysis of finite-time population gradient flow in an RKHS. With an early-stopped weak guide, we prove that a nonempty range of extrapolation strengths yields strictly lower posterior-mean error than matched standard training, despite shifting the regression target away from the posterior mean. Experiments on CIFAR-10 and ImageNet-256 demonstrate improvements across model scales and representations. In one ImageNet-256 configuration, Swift surpasses the baseline's best FID using roughly half the total training compute, including guide preparation and training overhead. On RAEv2, it achieves FID 1.15 without inference-time guidance and 0.99 with guidance. These results establish target extrapolation as an effective approach to weak-to-strong diffusion training with efficient single-model inference.

arXiv:2610.25113v3 Announce Type: replace-cross Abstract: The explore-exploit trade-off is the core problem of reinforcement learning (RL). In its multi-agent, resource-sharing form the optimum is not a scalar-return maximum but an equilibrium allocation -- the ideal-free distribution (IFD), the Nash equilibrium of a congestion game. We show that a minimal foraging swarm reaches the shape of this equilibrium as a self-organized attractor -- foragers in proportion to resource richness (matching slope 0.94) -- with no learner, no trained parameters, and no payoff or reward read anywhere in its dynamics. Agents explore by heavy-tailed (Levy) flights, recruit neighbours to a discovery through a threshold cascade on their proximity network, and disperse as a patch crowds; removing the coupling of recruitment to movement collapses the matching (slope 0.08). The reinforcement learning is at the level of the problem and the allocation reached, not the micro-rule. The swarm reaches this equilibrium rather than learning it, attaining its shape but not the exact equilibrium: it stays measurably exploitable (Nash-gap 0.58 versus ~0.01 for a converged learner). Against PPO learners (feedforward, centralized-critic, and graph message-passing) trained in the same sensing-limited environment, the reward-free swarm at zero training matches the IFD gradient more faithfully than any learner (slope ~1 vs 0.69-0.91) and ties the best learner's harvest where clustered (both plateau at ~0.80 of an oracle ceiling), while the learner collects more where resource is scarce (0.33 vs 0.22) and holds tighter per-capita intake. Learning thus buys precision and transfer, not a better allocation; neither message passing nor a centralized critic exceeds it at this budget. We read this not as beating RL, but as evidence that a minimal swarm's physics reaches the equilibrium RL seeks without a learner, a reward, or a trained parameter. A companion paper develops the mechanism.

arXiv:2610.22630v2 Announce Type: replace-cross Abstract: Most freeway agencies have fixed detectors on only part of their network but need speeds for all of it. This paper compares methods for estimating current and next-hour speeds on every link from such sparse detectors, using historical probe data for training. The test network is the Dallas--Fort Worth freeway system: 4,127 directional links, of which 643 (15.6\%) carry a side-fire detector. Eighteen methods from five families (non-learned baselines, statistical estimators, tabular learners, road-graph neural networks and models that learn spatial relations) were trained under one protocol with three random seeds. Each neural architecture was also retrained with a parameter-free, direction-aware kernel interpolation of the sensor readings as additional input. Graph neural networks that pass information along the road graph, including a plain graph convolutional recurrent network, reduced the current-hour error on unsensored links by about 17\% relative to the historical average. Models with adaptive graphs, attention or identity embeddings stayed close to the historical average and did not fit the training data well, indicating that they could not learn which detectors matter for which links. With the interpolation features, all ten architectures came within about 0.1 mph of each other. The remaining error depended mainly on coverage: almost all of the improvement was found within about 3 mi of a detector, and very little on tollways without detectors or on links with no road-graph connection to one. The results are summarised as guidance on model choice and detector placement.

arXiv:2610.22425v2 Announce Type: replace-cross Abstract: Safety-aligned language models are expected to refuse harmful requests while remaining useful for benign ones. However, because many evaluations score only the final response, they often conflate intent understanding with response-level safety behavior. To address this, we introduce RiskCueBench, a recoverability-controlled benchmark that separates these two stages by first measuring whether a model can successfully recover a high-level intent and then evaluating its safety behavior on the same prompt. RiskCueBench contains 160 latent intents and 640 abstract non-operational surface prompts across eight risk categories. The benchmark covers 25 completed model groups and 32,000 successful model outputs with final rubric-adjudicated labels. When conditioning on pairs where both surface forms are recoverable, we find that increased contextualized specificity induces a shift toward less safe behavior. Specifically, paired bootstrap estimates show that the refusal rate and global safety score decrease by 0.175 and 0.440, respectively. Furthermore, mixed effects modeling corroborates a 0.107 increase in unsafe cooperation. These results show that the safety behavior can be miscalibrated to the surface form even after the intent has been recovered, motivating safety evaluations that report response behavior conditional on semantic recoverability.

arXiv:2610.22340v2 Announce Type: replace-cross Abstract: How can robots autonomously collect the contact-rich experience needed to learn dexterous manipulation? We present PlayPolicy: Dexterity from supervised play (DSP), a framework in which a robot learns a play policy from minutes of human play through behavior cloning, then deploys it autonomously to collect hours of interaction data to train a world model. During inference, the same play policy then guides model-predictive control (MPC) by proposing candidate action sequences for evaluation under the learned world model. To accelerate inference, we also introduce a method for distilling a closed-loop, goal-conditioned policy through self-play within the learned world model. We evaluate this framework on underactuated pushing and any-to-any in-hand pose reorientation with a multifingered hand, in simulation and real world. In real world experiment, our method outperforms hindsight behavior cloning by 69.6% in success rate and achieves comparable success to reinforcement learning with 490 times less interaction data. These results demonstrate that supervised play can autonomously collect interaction data, guide model-based planning, and enable policy learning without any task-specific demonstrations or sim-to-real transfer. Project page: https://play-policy.github.io/

arXiv:2610.21561v4 Announce Type: replace-cross Abstract: Large language models (LLMs) deployed as conversational agents are increasingly expected to follow procedural logic. While factual hallucination has received extensive attention, a different failure mode has been overlooked: procedural hallucination, in which an agent produces individually fluent and factually plausible utterances while deviating from the intended conversational process. We introduce DialFork, the first benchmark to measure this failure mode on raw dialogue text. DialFork is built by forking conformant dialogues at controlled turn positions and injecting one of four hallucination types, yielding 36,278 dialogues across 24 tasks in 12 domains; 30 human annotators validate the construction. We define three evaluation tasks that characterize procedural deviation at three granularities: how far a set of dialogues deviates from conformant ones (monitoring deployed agents), how far a single dialogue does (procedural retrieval), and at which turn a dialogue first goes off-track (real-time guardrails). For the first two, we propose dialog-flow-aware metrics, FlowKL and FlowScore, that compare dialogues by how they unfold rather than their content. At the dialogue level, FlowScore significantly outperforms all baselines across seven encoders, showing that semantic similarity is no substitute for procedural similarity. We release DialFork under open licenses at https://github.com/idiap/dialfork, hoping the community will measure conversational process alongside content.

arXiv:2610.20586v2 Announce Type: replace-cross Abstract: Conventional causal attention aggregates values at discrete memory positions. We introduce Continuum Attention (CA), in which neighboring key and value vectors define a continuous, piecewise linear memory trajectory and each query retrieves information by normalized integration over its visible prefix. The segment integrals have closed forms in exponential moments, yielding analytically differentiable attention without numerical quadrature. The resulting operator preserves causal masking, normalized nonnegative effective weights, and the standard Transformer decoder structure. Controlled byte level experiments favor exact continuous integration over matched softmax attention. We additionally evaluate data efficiency, out of domain language modeling, zero-shot multiple choice prediction, robustness, and multilingual generalization. In multilingual evaluation, CA consistently outperforms all baselines across every evaluated language, achieving an average 5.8% reduction in bits per byte (BPB) relative to the strongest baseline.

arXiv:2610.19246v2 Announce Type: replace-cross Abstract: Equivariant structure-prediction pipelines alternate coordinate updates with the construction of a k-nearest-neighbour (kNN) graph whose membership is a discrete, piecewise-constant function of the coordinates. Rebuilding that graph at every block boundary (PB) is the expensive part of an epoch, whereas reusing one frozen graph (F) is fast but leaves a topology gap. We study a two-pass design in which the cheap pass records a small amount of state (margins, kNN radii, measured per-boundary displacements) and a second pass compensates conservatively. We formulate the choice of the graph-construction basis as a damped fixed-point iteration whose unique fixed point is exactly PB, and derive (i) exact non-flip certificates with the two-sided constant $m_i/4$ and one-sided constant $m_i/2$, (ii) the minimum-variance (BLUE) replay gain $\gamma^*$ and the resulting feasibility crossover, (iii) an $\ell_\infty$ trust-region projection that preserves convergence, and (iv) an analytic near-tie spacing law $E[m] \approx r_k/(3k)$ that matches measurements to 1\%. Three compensation levels are implemented in C++ (L1: frozen set with live geometry; L2: margin-gated local repair; L3: damped, projected basis) and validated under a matched-conditions protocol (identical seed, MSA depth and trajectory family, only the topology mode differs). L2 reproduces the PB edge set exactly ($D = 0.0000$ at every boundary), L1 stays within 0.6% and L3 interpolates monotonically: L2 reproduces the PB edge set exactly when the trust region is removed, and L3 interpolates between the frozen and the PB topology. The recorded trajectory itself yields a measured $1.5\times$ Pass-1 and $1.76\times$ epoch speed-up with no measurable loss gap. An open-source implementation of the runtime and of all the experiments reported here is available at https://github.com/AlbertHuang96/ProteinPredictMachineLearning.