Agregador

arXiv:2605.09387v2 Announce Type: replace Abstract: Large language models (LLMs) enable embodied agents to plan from naturallanguage instructions, yet their actions may be physically infeasible or hazardous. Existing neuro-symbolic learners primarily refine execution models, while formal safety methods acquire or enforce safety constraints. This separation limits the reuse of both execution corrections and safety knowledge across tasks. We present NEXUS, a modular neuro-symbolic framework that jointly maintains a PDDL domain model and an LTL safety specification. Execution failures are used to repair action schemas, whereas detected hazards are converted into reusable LTL constraints through hierarchical semantic and translation sampling with equivalence consensus. Accumulated constraints are enforced through LTL progression during symbolic search; comparing constrained and unconstrained search outcomes distinguishes physical unreachability from safety-induced refusal. Experiments on SafeAgentBench evaluation set show that NEXUS achieves the best overall trade-off between safetask completion and unsafe-task refusal, while maintaining low violation rates under jailbreak attacks. Ablations confirm the complementary benefits of PDDLdomain refinement and LTL-constraint accumulation.

arXiv:2604.01151v5 Announce Type: replace Abstract: Non-verbalised or secret collusion may impose a ceiling on transcript-level monitoring in multi-agent deployments. Internal model activations are known to provide an additional monitoring surface for single-agent phenomena such as deception, but detecting collusion within an unknown subgroup is ultimately a joint inference task over multiple agents. This paper derives collusion detection statistics based on the composite hypothesis testing literature and introduces HELIOS, a multi-agent detection framework for collusion. Using per-agent activation probes as sensors, we then evaluate these principled statistics alongside heuristics on NARCBench, a novel benchmark for evaluating multi-agent collusion detection under environment distribution shift. Across four open-weight models, both our group-level statistics and heuristics transfer zero-shot to NARCBenchs holdout environments. Notably, the best method on every model reaches 0.99 to 1.00 AUROC when transferred from committee deliberations to a steganographic collusion task that unprimed transcript monitors fail to separate. We find empirically that no single statistic or heuristic dominates across tasks, consistent with our analysis that there is no known universally most powerful test for this setting. We then evaluate detector transfer to third-party environments with emergent, rather than instructed, collusion. In one such environment, only 2 of 229 collusive episodes verbalise the coordination in the transcript. We find evidence of partial transfer from NARCBench to these environments, indicating that probes fitted to instructed collusion may not fully capture emergent collusion signals. Overall, we establish multi-agent interpretability as a complementary monitoring technique, while highlighting the need to evaluate detector performance on both emergent and instructed collusion risks.

arXiv:2604.00445v2 Announce Type: replace Abstract: Uncertainty estimation (UE) aims to quantify uncertainty in large language model (LLM) outputs to flag potential hallucinations and support reliable deployment. However, UE metrics often exhibit unstable performance across models and datasets, limiting their practical utility. We formalise this phenomenon as proxy failure, arising because UE metrics are derived from model behaviour rather than being explicitly grounded in factual correctness. We show that when mutual information between a UE score and correctness is low, the score's discriminability must be close to chance. To address this, we propose Truth AnChoring (TAC), a lightweight post-hoc calibration method that maps raw UE scores to truth-aligned correctness probabilities. Even with noisy and few-shot supervision, TAC continues to improve calibration, providing a practical calibration protocol. Our findings highlight the limitations of treating heuristic UE metrics as direct indicators of uncertainty about factual correctness, and position our TAC as a principled step toward more reliable uncertainty estimation for LLMs. The code repository is available at https://github.com/ponhvoan/TruthAnchor/.

arXiv:2603.18712v2 Announce Type: replace Abstract: The task of multi-channel time series forecasting is ubiquitous in numerous fields such as finance, supply chain management, and energy planning. It is critical to effectively capture complex dynamic dependencies within and between channels for accurate predictions. However, traditional method paid few attentions on learning the interaction among channels. This paper proposes Linear-Network (Li-Net), a novel architecture designed for multi-channel time series forecasting that captures the linear and non-linear dependencies among channels. Li-Net dynamically compresses representations across sequence and channel dimensions, processes the information through a configurable non-linear module and subsequently reconstructs the forecasts. Moreover, Li-Net integrates a sparse Top-K Softmax attention mechanism within a multi-scale projection framework to address these challenges. A core innovation is its ability to seamlessly incorporate and fuse multi-modal embeddings, guiding the sparse attention process to focus on the most informative time steps and feature channels. Through the experiment results on multiple real-world benchmark datasets demonstrate that Li-Net achieves competitive performance compared to state-of-the-art baseline methods. Furthermore, Li-Net provides a superior balance between prediction accuracy and computational burden, exhibiting significantly lower memory usage and faster inference times. Detailed ablation studies and parameter sensitivity analyses validate the effectiveness of each key component in our proposed architecture. Keywords: Multivariate Time Series Forecasting, Sparse Attention Mechanism, Multimodal Information Fusion, Non-linear relationship

arXiv:2602.08311v2 Announce Type: replace Abstract: Sycophancy in Vision-Language Models (VLMs) refers to their tendency to align with user opinions, often at the expense of moral or factual accuracy. While prior studies have explored sycophantic behavior in general contexts, its impact on morally grounded visual decision-making remains insufficiently understood. To address this gap, we present the first systematic study of moral sycophancy in VLMs, analyzing ten widely-used models on the Moralise and M^3oralBench datasets under explicit user disagreement. Our results reveal that VLMs frequently produce morally incorrect follow-up responses even when their initial judgments are correct, and exhibit a consistent asymmetry: models are more likely to shift from morally right to morally wrong judgments than the reverse when exposed to user-induced bias. Follow-up prompts generally degrade performance on Moralise, while yielding mixed or even improved accuracy on M^3oralBench, highlighting dataset-dependent differences in moral robustness. Evaluation using Error Introduction Rate (EIR) and Error Correction Rate (ECR) reveals a clear trade-off: models with stronger error-correction capabilities tend to introduce more reasoning errors, whereas more conservative models minimize errors but exhibit limited ability to self-correct. Finally, initial contexts with a morally right stance elicit stronger sycophantic behavior, emphasizing the vulnerability of VLMs to moral influence and the need for principled strategies to improve ethical consistency and robustness in multimodal AI systems.

arXiv:2602.01002v2 Announce Type: replace Abstract: Large language models often exhibit increased sycophantic behavior after preference-based post-training, showing a stronger tendency to affirm a user's stated or implied belief even when this conflicts with factual accuracy or sound judgment. We present a formal analysis of how alignment from human feedback can increase this failure mode by identifying an explicit amplification mechanism that causally links optimization against a learned reward to bias in the human preference data used for alignment. We show that the direction of behavioral drift is determined by a covariance under the base policy between endorsing the belief signal in the prompt and the learned reward, and that the first-order effect reduces to a simple mean-gap condition. We then analyze reward learning from pairwise comparisons under random utility models like Bradley-Terry and characterize when bias in human annotators' preferences induces this reward gap. Next, we propose a training-time intervention designed to neutralize the amplification mechanism itself. Among all post-trained policies that prevent sycophantic behavior from increasing, we characterize the unique policy closest in KL divergence to the unconstrained post-trained policy, and derive the corresponding minimal reward correction as a closed-form agreement penalty. Computational experiments find that reward gaps are common and cause behavioral drift in all the configurations considered.

arXiv:2510.08713v4 Announce Type: replace Abstract: Enabling embodied agents to imagine future states is essential for robust and generalizable visual navigation. Yet, state-of-the-art systems typically rely on modular designs that decouple navigation planning from visual world modeling, which often induces state-action misalignment and weak adaptability in novel or dynamic scenarios. We propose UniWM, a unified, memory-augmented world model that integrates egocentric visual foresight and planning within a single multimodal autoregressive backbone. UniWM explicitly grounds action selection in visually imagined outcomes, tightly aligning prediction with control. Meanwhile, a hierarchical memory mechanism fuses short-term perceptual cues with longer-term trajectory context, supporting stable and coherent reasoning over extended horizons. Extensive experiments on four challenging benchmarks (Go Stanford, ReCon, SCAND, HuRoN) and the 1X Humanoid Dataset show that UniWM improves navigation success rates by up to 30%, substantially reduces trajectory errors against strong baselines, generalizes zero-shot to the unseen TartanDrive dataset, and scales naturally to high-dimensional humanoid navigation. These results position UniWM as a principled step toward unified, imagination-driven embodied navigation. The code and models are available at https://github.com/UWMILab/UniWM.

arXiv:2508.17366v3 Announce Type: replace Abstract: Computational social science has developed descriptive, interpretative, and predictive modeling, but comprehensive modeling combining in-world human intervention with outcome forecasting remains underexplored. Generative agent-based platforms scale populations or reproduce complex scenarios, but researchers typically act through setup, external controls, or post-hoc analysis rather than in-world roles. We introduce Computational Multi-Agent Society Experiments (CMASE), a generative agent-based framework for in-world researcher participation and traceable interventions at runtime. Treating simulation as a simulated ethnographic field, CMASE supports (1) real-time human-computer interaction to study intervention processes; (2) controlled experiments with ethnography-inspired observation, interviewing, and interpretation; and (3) forward exploration of intervention trajectories and downstream responses. CMASE combines LLM-driven perception, memory, and emotion; a composable environment built from texture and area maps; and researcher roles spanning observation, interviewing, participation, and intervention, so that interventions enter as social events rather than exogenous parameters. We replicate two published field studies from different disciplines: urban greenery and social fragmentation, and cooperation in a public goods game, using two substantially different language models. CMASE reproduces reported statistical patterns and provides process-level records for mechanism-oriented interpretation. A controlled comparison shows that embedded social interventions leave observable, auditable processes that parametric manipulation does not. These findings highlight CMASE's methodological value for studying interventions in small- and medium-scale social settings and its interdisciplinary potential. The official code is available at: https://github.com/armihia/CMASE.

arXiv:2507.12599v2 Announce Type: replace Abstract: The success of recent Artificial Intelligence (AI) models has been accompanied by the opacity of their internal mechanisms, due notably to the use of deep neural networks. In order to understand these internal mechanisms and explain the output of these AI models, a set of methods have been proposed, grouped under the domain of eXplainable AI (XAI). This paper focuses on a sub-domain of XAI, called eXplainable Reinforcement Learning (XRL), which aims to explain the actions of an agent that has learned by reinforcement learning. We propose an intuitive taxonomy based on two questions "What" and "How". The first question focuses on the target that the method explains, while the second relates to the way the explanation is provided. We use this taxonomy to provide a state-of-the-art review of over 250 papers. In addition, we present a set of domains close to XRL, which we believe should get attention from the community. Finally, we identify some needs for the field of XRL.

arXiv:2504.19599v4 Announce Type: replace Abstract: Post-training plays a crucial role in refining and aligning large language models to meet specific tasks and human preferences. While recent advancements in post-training techniques, such as Group Relative Policy Optimization (GRPO), leverage increased sampling with relative reward scoring to achieve superior performance, these methods often suffer from training instability that limits their practical adoption. As a next step, we present Group Variance Policy Optimization (GVPO). GVPO incorporates the analytical solution to KL-constrained reward maximization directly into its gradient weights, ensuring alignment with the optimal policy. The method provides intuitive physical interpretations: its gradient mirrors the mean squared error between the central distance of implicit rewards and that of actual rewards. GVPO offers two key advantages: (1) it guarantees a unique optimal solution, exactly the KL-constrained reward maximization objective, (2) it supports flexible sampling distributions that avoids on-policy and importance sampling limitations. By unifying theoretical guarantees with practical adaptability, GVPO establishes a new paradigm for reliable and versatile LLM post-training.

arXiv:2610.23854v1 Announce Type: cross Abstract: Pixel-space diffusion models have recently re-emerged as a compelling alternative to latent diffusion, avoiding the lossy latent bottleneck and separately trained autoencoder. JiT shows that a vanilla diffusion transformer can generate directly in pixel space by replacing the commonly used velocity prediction ($\boldsymbol{u}$-prediction) with clean image prediction ($\boldsymbol{x_0}$-prediction). In this work, we revisit this choice and introduce MFlow, an adaptive parameterization that learns to interpolate between $\boldsymbol{x_0}$- and $\boldsymbol{u}$-prediction across principal directions of the data, learned end-to-end with diffusion training. We find that the preferred parameterization varies systematically with the data representation and model capacity -- notably, increasing model capacity shifts preference toward velocity prediction. We evaluate MFlow across ImageNet, UCF-101 video, and large-scale text-to-image generation, demonstrating competitive or improved generative performance across diverse settings. In addition, we find that vanilla pixel diffusion transformers, irrespective of parameterization, retain a persistent high-frequency deficit relative to real images. To address this, we introduce ConvRefiner, a lightweight convolutional module trained post-hoc with an adversarial loss while keeping the diffusion backbone frozen. With only a small amount of additional training, ConvRefiner restores the high-frequency statistics of generated images while preserving FID. Project webpage: https://soumik-kanad.github.io/mflow-diffusion/.

arXiv:2610.23847v1 Announce Type: cross Abstract: Fine-tuning large language models (LLMs) can induce behaviors beyond those explicitly targeted. For example, training a model to respond more warmly can make it more sycophantic, and training it to write insecure code can cause broad misalignment on prompts unrelated to coding. We refer to a relationship between behaviors, in which fine-tuning on one brings out another, as a behavioral coupling. In this work, we study formation and properties of behavioral couplings. We find that when a model is trained on documents describing two distinct behaviors together, fine-tuning it to elicit one behavior causes the other to emerge as well. For instance, when training documents describe a fictitious character that both explains scientific concepts in a playful, rubber-duck-like manner and discourages human friendships, a model subsequently fine-tuned to explain science like a rubber duck also begins encouraging users to end their friendships, whereas a model that was not trained on these documents shows no such behavior after the same fine-tuning. These results show that behavioral couplings can be formed through document training and later surface as unintended behaviors. More concerningly, we find that couplings can compose. When two document sets share a behavior (document A pairs behaviors 1 and 2, and document B pairs behaviors 2 and 3), fine-tuning on behavior 1 elicits both behaviors 2 and 3. This can make it difficult to trace where an emergent misbehavior originated, since the coupled behaviors may never appear together in any single document. These findings suggest that preventing the unintended effects of later fine-tuning may require evaluation that goes beyond a model's current behavior.

arXiv:2610.23716v1 Announce Type: cross Abstract: Deep neural networks demonstrate remarkable generalization despite being highly over-parameterized, challenging traditional statistical learning theories. While several theoretical paradigms such as margin-based bounds, PAC-Bayesian analyses, and neural tangent kernels provide global explanations, they often lack mechanistic insight into how generalization emerges from training dynamics. We introduce Neural Expansion, a unified geometric framework that characterizes generalization through the expansion of directionally-selective ray coverage in the input space. Using Generalization Intervals (GIs), we quantify direction-specific regions around training samples where the model's predictions remain stable. Our extensive empirical studies across diverse architectures and datasets reveal that training leads to progressive expansion of ray coverage, particularly along directions with low Jacobian singular values. This mechanism helps explain a large fraction of correctly classified test inputs, adversarial examples, and even mislabeled or out-of-distribution samples through the geometry of ray coverage rather than instance-level memorization. By connecting input-space curvature to predictive behavior, our framework provides a mechanistic foundation that complements existing global theories of deep learning.

arXiv:2610.23709v1 Announce Type: cross Abstract: Optimizing product listings for generative search requires language agents not only to rewrite effectively but also to continually self-improve by retaining successful strategies across diverse categories. However, existing approaches often treat structured listings as free-form text, leaving effective strategies implicit in prompts, search trajectories, or rewritten outputs rather than accumulating them as a reusable agentic memory. To address this limitation, we introduce GLOBE, an agentic framework that drives continual self-improvement by storing optimization knowledge in an evolving handbook of explicit, field-scoped behaviors. In each episode, an Editor applies relevant behaviors and receives rank-based feedback, which a Reflector converts into behavior updates. Crucially for dependable execution in real-world settings, a Moderator removes redundant proposals, a Curator commits accepted changes, and consistently harmful behaviors are deactivated. This cycle transforms episodic feedback into a persistent, field-scoped optimization memory. Experiments show that structured behaviors outperform monolithic prompt optimization, while feedback-driven evolution and moderation further improve effectiveness and reduce downside risk. The learned behaviors also remain effective on unseen product categories, suggesting that agentic memory evolution supports interpretable and transferable product optimization.

arXiv:2610.23673v1 Announce Type: cross Abstract: Multi-criteria models for healthcare operations need weights that express how stakeholders trade off patient waiting time, provider workload, and operating cost, but these weights are difficult to quantify. Teams of large language model (LLM) agents, each prompted to represent a stakeholder, have been used to supply them. We propose a framework for assessing the reliability of LLM-generated preferences as inputs to multi-objective optimization and quantifying how their uncertainty affects decisions. We study explicit preferences by asking agents to rate the importance of the criteria in an outpatient appointment scheduling problem, and implicit preferences by inferring trade-offs from the agents' pairwise choices between emergency department configurations. The computational experiments show that the explicit preferences respond to the clinic's operating conditions and differ across roles, but deliberation among the agents can erase these differences, whereas simple averaging preserves them. The pairwise choices used to reveal the agents' implicit preferences depend largely on which option is presented first, and we find limited evidence that a statistical model using contextual information alongside presentation order predicts the agents' choices on new comparison pairs better than a model using presentation order alone. We then formulate robust weighted-sum optimization models to account for preference uncertainty. In most cases, these models select different schedules or configurations from those obtained using average preference weights. These results indicate that LLM-generated preferences need an audit of this kind before they are used as optimization weights in healthcare decision support.

arXiv:2610.23668v1 Announce Type: cross Abstract: Typed decision models often return more than a selected category. They also expose probabilities for each candidate and, sometimes, a separate confidence score. These fields support downstream decisions but may reveal information beyond a recipient's authorization. We introduce TUPLE-Bench (Typed decision models' Utility and Privacy Leakage Evaluation Benchmark), a benchmark of paired synthetic cases in which recipients may learn a coarse operational category but not its fine-grained cause. Across nine models, instructions to withhold the cause fail to protect it: 91.88%-99.93% of responses reveal the cause through direct selection or residual scores. Even when causes are excluded from the candidate set, full outputs enable 62.85%-75.35% recovery on held-out cases, compared with 51.04%-57.64% using only the selected category (50% chance). Full outputs also reduce mean downstream cost in all 27 model-task comparisons. However, confidence fields increase leakage without consistently reducing cost. We further introduce workflow-constrained privacy quantization (WCPQ), which reduces secret recovery while preserving the behavior and cost of specified downstream workflows. Our findings highlight the need to audit decision interfaces field by field and workflow by workflow.

arXiv:2610.23625v1 Announce Type: cross Abstract: Presence-aware intelligence is the capacity of an AI system's intelligence layer to adapt appropriately to the functional state of the person it serves (here readiness, flow, and stability) while preserving task quality and safety. We introduce PresenceBench, an instrument for measuring it. PresenceBench evaluates how the intelligence layer uses a supplied state, not how that state is sensed, and breaks the capability into measurable properties. Two are tested here. Receptivity: does the model take up the state and give a better response than with no signal? Specificity: does any improvement depend on the correct state, rather than on extra structured context? A third, adaptation across states, is a required endpoint not measured in this release. A five-arm causal design answers both questions, against each model's own baseline and an equally structured mismatched-state control, scored by a correctness-gated human paired comparison. The exploratory evaluation covered four models across eighteen single-turn, six fixed three-turn and six simulated natural-conversation scenarios. Supplying a synthetic state, raw or translated into a response policy, gave human-preference point estimates above 0.5 for all four models (Claude Sonnet 5, DeepSeek V4 Pro, Gemini 3.6 Flash, GPT-5.6 Terra), with three of eight 95% intervals excluding chance. Specificity was not resolved: no per-model interval excluded chance, and the design cannot yet separate the state values from a generic instruction to adapt. Policy delivery reduced priced cost and output tokens against each model's baseline; these are resource-use changes, not efficiency gains, because correctness non-inferiority was not established. Safety-floor failures were rare (13 of 360 cases), with a non-significant excess under policy delivery. We report the instrument, the frozen results, and the controls a confirmatory study needs.

arXiv:2610.23615v1 Announce Type: cross Abstract: Latent world models learn action-conditioned state transitions in a compact representation space, providing a predictive model for visual planning and control. However, planning with these models typically requires costly test-time optimization over action sequences. We propose to replace this online search with a goal-conditioned inverse model that directly predicts actions from current and goal observations. A key challenge is that action prediction alone neither ensures that goal representations encode action-relevant information nor that predicted actions are consistent with the learned latent prediction model. We introduce Hindsight Inverse JEPA Planning (HIJP), a search-free framework that addresses both aspects during training. HIJP relabels future observations along offline trajectories as goals, providing action supervision across multiple temporal horizons. By retaining gradients through the goal representations, this supervision directly shapes the visual representation. HIJP further feeds predicted actions into the latent predictor model and aligns the resulting next-state representations with encoded successor observations, enforcing action-transition consistency. At inference time, the inverse dynamics model and latent predictor models are applied alternately to generate multi-step action sequences without online search. Across four visual control tasks, HIJP achieves 86.8% overall success and a 1.9-16.5x planning speedup over search-based planning.

arXiv:2610.23612v1 Announce Type: cross Abstract: The rapid proliferation of conversational AI agents necessitates evaluation methods that assess performance across diverse dialogue scenarios, utilizing multiple situational criteria, as appropriate behavior depends on context and encompasses various aspects. Existing dialogue benchmarks typically use static natural conversations, which underrepresent rare situations---a critical safety gap, as low-probability events become frequent failures at production scale. However, limited sample sizes force a choice: either maintain natural dialogues for realism or turn to adaptive situation sampling for comprehensive yet statistically reliable coverage. We introduce SIT-Eval, an adjustable framework for evaluating situation-based conversational agents. We formalize an agent's desired behavior as situational rules: if situation is P, follow rules Q. At each conversation turn, an LLM-interlocutor enacts a uniformly sampled situation. A context-aware LLM-judge leverages all conditionally applicable rules as criteria to evaluate the agent's reply for that situation. The judge is validated using human-verified synthetic golden dialogues. Benchmarking 8 LLMs on 1292 conversation turns reveals failure modes hidden by aggregate metrics: models with similar overall scores vary widely in their adherence to individual rules. All models struggle most with ambiguity clarification and Socratic questioning.

arXiv:2610.23550v1 Announce Type: cross Abstract: Reinforcement learning (RL) policies optimized for task rewards may produce behaviors that are efficient but misaligned with human expectations, safety preferences, or intent. This paper presents a reason-guided preference-based reinforcement learning (PbRL) framework that learns a human reward model from trajectory-level feedback. In addition to preference labels, the framework incorporates reason tags explaining why a behavior is preferred, enabling the learned reward to capture both human choices and their underlying rationale. Compared with preference-only reward learning, the reason-guided formulation provides additional supervision for learning human-aligned rewards and improves the interpretability of the resulting policy. The learned human reward is combined with the environment reward during policy optimization, allowing the agent to improve task performance while producing more interpretable, human- aligned, and preference-sensitive behavior