Noticias de IA - ítems

arXiv:2610.34385v1 Announce Type: cross Abstract: Agents that act on real systems should predict what their actions will cause before acting. We study when causal structure helps a learned forward model do this, using a planner that rejects candidate actions whose simulated multi-step outcome is unsafe, in synthetic structural causal models where the true consequences are known. We compare the Action-Conditioned Latent Structural Causal Model (AC-LSCM: per-factor mechanisms over a learned sparse graph, actions as do-interventions) with three unstructured forward models on seven random graphs with 10 or 20 variables, a task configured by a fixed rule, and two controls: a do-wrapper that gives every model the same action semantics, and counterfactual data given to all models or to none. When its factors are the observed variables, AC-LSCM recovers the true graph exactly on every 10-variable graph and has lower three-step prediction error than every baseline in all 396 paired comparisons. Its excess safety violations over an oracle are 0.25 of the no-model level on 10-variable graphs (best baseline 0.31) and 0.41 on 20-variable graphs (0.53), and its margin is largest for two-variable actions never seen in training (0.18 versus 0.28). With learned latent factors the same model is worse than the baselines; the choice of factors matters more than the explicit do-operator or counterfactual data, and every planner stays far from the oracle. This version corrects an earlier one, whose model learned an empty graph and whose headline 36x safety improvement came from a task that tested only extrapolation of action values; we withdraw that claim. Code and all per-seed results are released.

arXiv:2610.34384v1 Announce Type: cross Abstract: Mobile-use multimodal agents are typically evaluated by task success from a clean initial state, which does not isolate their ability to recover from intermediate errors. Because mobile environments change dynamically, a general mobile-use agent must complete tasks robustly even from unexpected states and in unseen environments. This requires knowing when and where an agent makes errors, and whether it can recover from errors and subsequent states. To evaluate this capability, we introduce AndroidFlux, a failure-recovery benchmark built on AndroidWorld. AndroidFlux restores recorded trajectories to controlled checkpoints before, at, and after the first recoverable error, so that different agents continue from the same device state and history. On these checkpoints, a complementary reward-modeling benchmark evaluates recovery-action preferences using downstream rollout outcomes. We further release an offline reinforcement learning (RL) dataset that improves both error recovery and overall task success. Our evaluations show that recovery performance only partially correlates with clean-start success, and that explicit reasoning helps only models trained with GUI-domain specific RL.

arXiv:2610.34375v1 Announce Type: cross Abstract: Best-of-N (BoN) inference returns the candidate with the highest proxy reward, so a larger $N$ tests the proxy's extreme tail more than its average ranking quality. We show that the exact BoN value is a Beta-weighted integral of conditional true reward over within-prompt score quantiles. It follows that BoN depends on scores only through their ranks. It also follows that BoN can decline only if the calibration curve in the tail turns downward, and the budget where the decline appears depends on where that turn lies. Under a bounded additive model, the error tail sets the limit: Gaussian errors keep improving, Laplace errors reach a plateau, and heavy-tailed errors return to the prior mean. When error variance is largest at low true reward, even Gaussian noise can push BoN below random selection. Synthetic phase maps agree with this taxonomy. On real candidate pools spanning several verifiable domains, base policies, and learned reward models, tail failures are rare and all occur in code generation. A held-out tail calibration statistic reliably predicts where a cross-fitted budget cap helps. It does about as well as rank accuracy, and the cap is competitive with a Soft-BoN baseline. Tail calibration therefore does not replace ranking metrics. It is an audit that is unchanged by any monotone rescaling of the reward scores and shows which budgets are at risk.

arXiv:2610.34374v1 Announce Type: cross Abstract: Modern software development relies on version control systems such as Git to track changes and facilitate collaboration. While commit messages are crucial for conveying developer intent, they do not affect program functionality; as a result, developers often lack motivation to write meaningful ones. The Conventional Commits Specification (CCS) addresses this with a structured format and guidelines that help developers express the intent of a change, improving clarity and enabling automation. Yet, developers frequently struggle to express intent while adhering to the format. In particular, they may misclassify commits due to the large number of possible categories or the lack of project-specific guidance. We introduce ComBeautify, an approach that automatically generates CCS-compliant commit messages. Our hybrid approach leverages context-preserving summarization of Git diffs with large language models (LLMs) to improve commit classification accuracy under CCS. Rather than relying on manually curated category definitions, we learn them from historical commits. We also propose a method for automatically generating the CCS description component. Our empirical evaluation across 13 languages, 6,500 open-source repositories, and over 20 million commits provides long-term insights into CCS adoption, revealing increasing compliance. Our evaluation on twenty popular repositories reveals the limitations of approaches guided by generic category definitions, and shows that ComBeautify, when trained on project-specific data, outperforms baselines by up to 3x. Additionally, using a dataset of 2,000 manually curated commits, we validate our summarization approach, achieving up to 95.25% accuracy and surpassing baselines. These findings emphasize the need for adaptable, context-aware AI methods for commit classification and CCS-compliant commit message generation.

arXiv:2610.34365v1 Announce Type: cross Abstract: Science agents increasingly package domain expertise as reusable skills that plan analyses, select tools, and execute workflows. This modularity creates a confidentiality risk: the interactions that deliver a skill's capability can also reveal the skill itself. We build an extensible benchmark of 40 protected skills across eight open- and closed-source science-agent platforms, comparing direct, fixed-strategy, and bandit-guided iterative probing under reference-based and reference-free evaluation. Leakage is pervasive: all eight platforms (100%) leak at least one protected skill, and four reach 100% attack success under a single direct request. To stress-test platforms that resist simple probing, we propose SEEK (Skill Extraction with Evolving Knowledge), a black-box, self-evolving red-teaming agent that consolidates response-derived evidence in persistent memory and evolves reusable attack skills, using only user-visible responses. On 12 skills from SpatialAgent and Biomni, SEEK achieves 100% attack success while reducing the mean first-success round by 31.8% and 38.2% relative to bandit-guided probing. Against a confidentiality policy that blocks all three benchmark protocols, SEEK still extracts one of six protected skills. These findings show that current science agents do not reliably protect their skills and that defenses must be evaluated against adaptive, multi-turn attackers.

arXiv:2610.34343v1 Announce Type: cross Abstract: Structured semantic parsing is typically judged by whether the correct category is assigned, which leaves value recovery and instance-level associations unexamined: a system may recognize an event yet bind an argument to the wrong instance, or identify an intent yet supply an incorrect slot value. We present USP, a cross-family semantic contract that represents categories, fields, values, and instance associations through a common interface for named-entity recognition, relation extraction, event extraction, and intent-slot parsing. The contract is paired with five diagnostic matching views---category agreement, field recognition, field-value pairing, instance-bound assignment, and complete-instance recovery---that ask distinct questions about the same output. Using this contract, we normalize 61 datasets into a unified corpus with shared schemas, prompts, and matching rules, and compare six models on a fixed test subset. Our fine-tuned Xing4.0-29B-Intent attains 57.70 task-balanced Field-Value Micro-F1 (equally weighted across the four task families) and ranks first in every family and on all five views; its margin over the strongest alternative widens from 2.93 points for category matching to 20.73 points for complete-instance matching. This widening gap shows that category agreement alone understates structural deficits. USP thus offers the community a shared representation, a normalized 61-dataset corpus, and a diagnostic evaluation protocol that make structural agreement measurable and comparable across extraction and intent-slot tasks.

arXiv:2610.34336v1 Announce Type: cross Abstract: Large reasoning models are costly to serve because they are large and because they generate long chains of thought (CoT). Weight pruning and CoT compression address these two costs separately, but they interfere in that pruning adds redundant reasoning on problems the model still solves and incomplete reasoning on those it no longer solves, and on harder problems makes the model less compressible by subsequent length-preference optimization. We trace this to a blind spot on each side: pruning criteria do not distinguish necessary from redundant reasoning, and preference-based CoT compression receives no training signal on problems a pruned model always or never solves. We propose Contrastive Set-Difference (CSD), which identifies neurons enriched in redundant reasoning by contrasting their activations on long and short correct solutions of the same problem and prunes them preferentially, and we extend preference pairs to the problems a pruned model always or never solves. Pruning 20\% of DeepSeek-R1-Distill-Qwen-7B, the combination uses 8--22\% fewer thinking tokens on four math benchmarks than pruning with reasoning-aware calibration (RAC) followed by the same compression, with accuracy within 0.5 points.

arXiv:2610.34335v1 Announce Type: cross Abstract: Extracting salient information from long-horizon dialogue histories remains a significant challenge for Large Language Models (LLMs) due to the restricted context windows and efficient retrieval challenges. Current methods typically rely on history organization or local token-level optimization, suffering from information loss, retrieval redundancy, and myopic attention. Inspired by the view in cognitive science that dialogue constitutes sense-making and memory association, we propose CoLink, a framework that enhances LLMs' global context awareness in domain-specific multi-turn dialogues through information linking and compression. CoLink first clusters historical contexts into topic graphs to establish cross-semantic associations with external knowledge. Guided by the adaptive control of thought, it then retrieves and activates knowledge via synergizing semantic relevance and graph-structural topology. Crucially, to achieve effective compression of history and knowledge, we ground multi-turn dialogues in information theory and derive a principled optimization objective for extracting the core sense-making information. Coupled with a competitive slot mechanism, CoLink condenses the global context into dedicated memory and knowledge slots, efficiently distilling lengthy, redundant inputs into an extremely compact latent representation. Extensive empirical results on both public and our MMD datasets validate CoLink's superiority and generalizability in knowledge linking and sense modeling.

arXiv:2610.34329v1 Announce Type: cross Abstract: Large language models (LLMs) can act as decision models that return a probability distribution over a fixed set of options, but deployed decision models face domain, label-prior, emerging-class and candidate-set shift. We study how such models fail under shift and propose SHIFT-Jev, a monitoring, abstention and continual-adaptation procedure for them. It scores the risk of each decision from uncertainty, format and option-consistency signals, certifies abstention thresholds with Learn-then-Test, monitors the decision stream with drift and label-shift detectors, and accepts a model update only when an expected-gain gate finds a significant held-out improvement without loss on earlier regimes. On a benchmark of ten shifted test environments with Qwen3-0.6B and Qwen3-4B (three seeds each) and Phi-4-mini, fine-tuning with KL anchors and temperature scaling lowers calibration error under shift from 0.289 to 0.087. At a target risk of 10%, a learned uncertainty score with a certified threshold exceeds the target in 3 to 5 of 27 environment-seed tests, against 5 to 15 for a max-probability score with the same certification and 9 to 14 for conformal prediction sets; drift-based routing changes little. A chi-squared test on predicted labels detects 95 to 99% of class-prior shifts that confidence- and embedding-based detectors miss. In continual adaptation, SHIFT-Jev reaches 70.5% accuracy on Qwen3-0.6B, above replay, LwF, EWC and fine-tuning baselines in every seed, whereas on Qwen3-4B its conservative gate leaves it 0.4 to 1.4 points behind them.

arXiv:2610.34317v1 Announce Type: cross Abstract: With the rise of Large Language Models (LLMs), software developers are presented with a powerful new approach: delegating software development tasks to LLMs. Existing studies have explored task delegation for a subset of tasks and factors. Critically, what tasks developers delegate to LLMs, to what extent, and why they delegate them, is not yet well understood. We explore these questions through 22 interviews and a survey with 160 software practitioners. Developers reported employing four modes of task delegation to LLMs: full delegation, partial delegation, self-delegation, and task avoidance. Drawing on our qualitative findings, we discuss the rationales behind these choices and explore how task difficulty, task risk, developer motivation, and trust appear to be associated with software development task delegation to LLMs. Our statistical analysis reveals that trust is a significant factor associated with task delegation to LLMs. Finally, we share actionable implications for human-AI collaboration in software research, and for software practitioners to make the most of their newly found powers of delegation.