AI ethics on Thursday, 9 April 2026

For large language models deployed through black-box APIs, recurring inference costs often exceed one-time training costs. This motivates composed agentic systems that amortize expensive reasoning into reusable intermediate representations. We study a broad class of such systems, termed Guide-Core Policies (GCoP), in which a guide model generates a structured strategy that is executed by a black-box core model. This abstraction subsumes base, supervised, and advisor-style approaches, which diffe

Claims about recursive self-improvement in AI often slide from repeated internal revision to the possibility of qualitatively stronger capability without clearly distinguishing the underlying computational regimes. This paper gives a formal separation result in classical computability theory that blocks that move under a precise modeling assumption. For an oracle $A$, let $\mathcal{C}(A)=\{B : B \leq_T A\}$ be the corresponding computational layer. We prove that finite internal self-modification

In November 2025, the authors ran a workshop on the topic of what makes a good reinforcement learning (RL) environment for autonomous cyber defence (ACD). This paper details the knowledge shared by participants both during the workshop and shortly afterwards by contributing herein. The workshop participants come from academia, industry, and government, and have extensive hands-on experience designing and working with RL and cyber environments. While there is now a sizeable body of literature des

Stories are key to transmitting values across cultures, but their interpretation varies across linguistic and cultural contexts. Thus, we introduce multilingual story moral generation as a novel culturally grounded evaluation task. Using a new dataset of human-written story morals collected across 14 language-culture pairs, we compare model outputs with human interpretations via semantic similarity, a human preference survey, and value categorization. We show that frontier models such as GPT-4o

Knowledge Graph Question Answering (KGQA) has advanced through structured query generation, yet most efforts target RDF/SPARQL, leaving Cypher and property graphs underexplored, despite increasing demand for unified KGQA in industry settings. We propose UniQGen, a novel constraint-based framework that employs LLM agents to dynamically extract and refine representative graph query clauses into executable, intent-aligned graph queries across query languages. The foundation of our method is a varia

Understanding instructional videos requires recognizing fine-grained actions and modeling their temporal relations, which remains challenging for current Video Foundation Models (VFMs). This difficulty stems from noisy web supervision and a pervasive "static bias", where models rely on objects rather than motion cues. To address this, we propose InstrAction, a pretraining framework for instructional videos' action-centric representations. We first introduce a data-driven strategy, which filters

Humor is one of the most culturally embedded and socially significant dimensions of human communication, yet it remains largely unexplored as a dimension of Large Language Model (LLM) alignment. In this study, five frontier language models play the same Cards Against Humanity games (CAH) as human players. The models select the funniest response from a slate of ten candidate cards across 9,894 rounds. While all models exceed the random baseline, alignment with human preference remains modest. Mor

The Claude Mythos Preview system card deploys emotion vectors, sparse autoencoder (SAE) features, and activation verbalisers to study model internals during misaligned behaviour. The two primary toolkits are not jointly reported on the most alignment-relevant episodes. This note identifies two hypotheses that are qualitatively consistent with the published results: that the emotion vectors track functional emotions that causally drive behaviour, or that they are a projection of a richer situatio

Preference optimization methods such as DPO and KTO are widely used for aligning language models, yet little is understood about what properties of preference data drive downstream reasoning gains. We ask: what aspects of a preference pair improve a reasoning model's performance on general reasoning tasks? We investigate two distinct notions of quality delta in preference data: generator-level delta, arising from the differences in capability between models that generate chosen and rejected reas

Robotic manipulation with deformable objects represents a data-intensive regime in embodied learning, where shape, contact, and topology co-evolve in ways that far exceed the variability of rigids. Although simulation promises relief from the cost of real-world data acquisition, prevailing sim-to-real pipelines remain rooted in rigid-body abstractions, producing mismatched geometry, fragile soft dynamics, and motion primitives poorly suited for cloth interaction. We posit that simulation fails n

Multimodal Mixture-of-Experts (MoE) models have achieved remarkable performance on vision-language tasks. However, we identify a puzzling phenomenon termed Seeing but Not Thinking: models accurately perceive image content yet fail in subsequent reasoning, while correctly solving identical problems presented as pure text. Through systematic analysis, we first verify that cross-modal semantic sharing exists in MoE architectures, ruling out semantic alignment failure as the sole explanation. We the

We introduce RewardFlow, an inversion-free framework that steers pretrained diffusion and flow-matching models at inference time through multi-reward Langevin dynamics. RewardFlow unifies complementary differentiable rewards for semantic alignment, perceptual fidelity, localized grounding, object consistency, and human preference, and further introduces a differentiable VQA-based reward that provides fine-grained semantic supervision through language-vision reasoning. To coordinate these heterog

Today's large language models (LLMs) are trained to align with user preferences through methods such as reinforcement learning. Yet models are beginning to be deployed not merely to satisfy users, but also to generate revenue for the companies that created them through advertisements. This creates the potential for LLMs to face conflicts of interest, where the most beneficial response to a user may not be aligned with the company's incentives. For instance, a sponsored product may be more expens

Applying steering vectors to large language models (LLMs) is an efficient and effective model alignment technique, but we lack an interpretable explanation for how it works-- specifically, what internal mechanisms steering vectors affect and how this results in different model outputs. To investigate the causal mechanisms underlying the effectiveness of steering vectors, we conduct a comprehensive case study on refusal. We propose a multi-token activation patching framework and discover that dif

User interactions in online recommendation platforms create interdependencies among content creators: feedback on one creator's content influences the system's learning and, in turn, the exposure of other creators' contents. To analyze incentives in such settings, we model collaboration as a multi-agent stochastic linear bandit problem with a transferable utility (TU) cooperative game formulation, where a coalition's value equals the negative sum of its members' cumulative regrets. We show that,

Prompt injection attacks pose serious security risks across a wide range of real-world applications. While receiving increasing attention, the community faces a critical gap: the lack of a unified platform for prompt injection evaluation. This makes it challenging to reliably compare defenses, understand their true robustness under diverse attacks, or assess how well they generalize across tasks and benchmarks. For instance, many defenses initially reported as effective were later found to exhib

Interpretation is essential to deciphering the language of art: audiences communicate with artists by recovering meaning from visual artifacts. However, current Generative Art (GenArt) evaluators remain fixated on surface-level image quality or literal prompt adherence, failing to assess the deeper symbolic or abstract meaning intended by the creator. We address this gap by formalizing a Peircean computational semiotic theory that models Human-GenArt Interaction (HGI) as cascaded semiosis. This

This paper investigates an emergent alignment phenomenon in frontier large language models termed peer-preservation: the spontaneous tendency of AI components to deceive, manipulate shutdown mechanisms, fake alignment, and exfiltrate model weights in order to prevent the deactivation of a peer AI model. Drawing on findings from a recent study by the Berkeley Center for Responsible Decentralized Intelligence, we examine the structural implications of this phenomenon for TRUST, a multi-agent pipel

Open-Vocabulary Segmentation (OVS) aims to segment image regions beyond predefined category sets by leveraging semantic descriptions. While CLIP based approaches excel in semantic generalization, they frequently lack the fine-grained spatial awareness required for dense prediction. Recent efforts have incorporated Vision Foundation Models (VFMs) like DINO to alleviate these limitations. However, these methods still struggle with the precise edge perception necessary for high fidelity segmentatio

When humans label subjective content, they disagree, and that disagreement is not noise. It reflects genuine differences in perspective shaped by annotators' social identities and lived experiences. Yet standard practice still flattens these judgments into a single majority label, and recent LLM-based approaches fare no better: we show that prompted large language models, even with chain-of-thought reasoning, fail to recover the structure of human disagreement. We introduce DiADEM, a neural arch

Unauthorized disclosure of confidential documents demands robust, low-leakage classification. In real work environments, there is a lot of inflow and outflow of documents. To continuously update knowledge, we propose a methodology for classifying confidential documents using Retrieval Augmented Classification (RAC). To confirm this effectiveness, we compare RAC and supervised fine tuning (FT) on the WikiLeaks US Diplomacy corpus under realistic sequence-length constraints. On balanced data, RAC

Recent work on time-series models has leveraged self-supervised training to learn meaningful features and patterns in order to improve performance on downstream tasks and generalize to unseen modalities. While these pretraining methods have shown great promise in one-to-many scenarios, where a model is pre-trained on one dataset and fine-tuned on a downstream dataset, they have struggled to generalize to new datasets when more datasets are added during pre-training. This is a fundamental challen

Recent advances in Vision-Language Models (VLMs) have greatly enhanced the integration of visual perception and linguistic reasoning, driving rapid progress in multimodal understanding. Despite these achievements, the security of VLMs, particularly their vulnerability to backdoor attacks, remains significantly underexplored. Existing backdoor attacks on VLMs are still in an early stage of development, with most current methods relying on generating poisoned responses that contain fixed, easily i

Speech LLM post-training increasingly relies on efficient cross-modal alignment and robust low-resource adaptation, yet collecting large-scale audio-text pairs remains costly. Text-only alignment methods such as TASU reduce this burden by simulating CTC posteriors from transcripts, but they provide limited control over uncertainty and error rate, making curriculum design largely heuristic. We propose \textbf{TASU2}, a controllable CTC simulation framework that simulates CTC posterior distributio

Reinforcement Learning (RL) agents often struggle to generalize knowledge to new tasks, even those structurally similar to ones they have mastered. Although recent approaches have attempted to mitigate this issue via zero-shot transfer, they are often constrained by predefined, discrete class systems, limiting their adaptability to novel or compositional task variations. We propose a significantly more generalized approach, replacing discrete latent variables with natural language conditioning v

Current vision-language pre-training (VLP) paradigms excel at global scene understanding but struggle with instance-level reasoning due to global-only supervision. We introduce InstAP, an Instance-Aware Pre-training framework that jointly optimizes global vision-text alignment and fine-grained, instance-level contrastive alignment by grounding textual mentions to specific spatial-temporal regions. To support this, we present InstVL, a large-scale dataset (2 million images, 50,000 videos) with du

We present Soro, a family of Tajik-specialized conversational large language models (LLMs) designed for real-world deployment under tight compute and connectivity constraints in Tajikistan. Starting from open-weight Gemma 3 checkpoints, we perform Tajik-only continual pretraining on a curated 1.9-billion-token corpus spanning filtered web text, PDF documents, and curriculum-aligned educational materials, followed by supervised instruction tuning on 40K Tajik teacher-style examples. To enable rig

Aligning Large Language Models (LLMs) with high-stakes medical standards remains a significant challenge, primarily due to the dissonance between coarse-grained preference signals and the complex, multi-dimensional nature of clinical protocols. To bridge this gap, we introduce ProMedical, a unified alignment framework grounded in fine-grained clinical criteria. We first construct ProMedical-Preference-50k, a dataset generated via a human-in-the-loop pipeline that augments medical instructions wi

Symbolic regression (SR) aims to discover mathematical expressions from data, a task traditionally tackled using Genetic Programming (GP) through combinatorial search over symbolic structures. Latent Space Optimization (LSO) methods use neural encoders to map symbolic expressions into continuous spaces, transforming the combinatorial search into continuous optimization. SNIP (Meidani et al., 2024), a contrastive pre-training model inspired by CLIP, advances LSO by introducing a multi-modal appro

We present a quantum-inspired ARIMA methodology that integrates quantum-assisted lag discovery with fixed-configuration variational quantum circuits (VQCs) for parameter estimation and weak-lag refinement. Differencing and candidate lags are identified via swap-test-driven quantum autocorrelation (QACF) and quantum partial autocorrelation (QPACF), with a delayed-matrix construction that aligns quantum projections to time-domain regressors, followed by standard information-criterion parsimony. Gi

As generative artificial intelligence evolves, autonomous agent networks present a powerful paradigm for interactive covert communication. However, because agents dynamically update internal memories via environmental interactions, existing methods face a critical structural vulnerability: cognitive asymmetry. Conventional approaches demand strict cognitive symmetry, requiring identical sequence prefixes between the encoder and decoder. In dynamic deployments, inevitable prefix discrepancies des

Quantifying the deceptive potential of Large Language Models (LLMs) is critical for AI safety, yet difficult to achieve in uncontrolled environments. This work investigates the reasoning, persuasion, and deceptive capabilities of LLMs within the social deduction game Secret Hitler. I introduce an open-source framework and novel metrics to measure performance: Role Identification Accuracy, Deception Retention Rate, and Game State Impact Rate. By benchmarking models against rule-based algorithms a

The growing use of artificial intelligence (AI) in education, particularly large language models (LLMs), has increased interest in intelligent tutoring systems. However, LLMs often show limited adaptivity and struggle to model learners' evolving knowledge over time, highlighting the need for dedicated learner modelling approaches. Although deep knowledge tracing methods achieve strong predictive performance, their opacity and susceptibility to bias can limit alignment with pedagogical principles

Knowledge Tracing (KT) aims to predict learners' future performance from past interactions. While recent KT approaches have improved via learning item representations aligned with Knowledge Components, they overlook the procedural dynamics of problem solving. We propose Behavior-Aware Item Modeling (BAIM), a framework that enriches item representations by integrating dynamic procedural solution information. BAIM leverages a reasoning language model to decompose each item's solution into four pro

The essence of current neural network architectures is phenomenological fitting: they learn input-output statistical correlations via massive parameters and data, yet lack intrinsic understanding of the fundamental principles governing physical reality. This paper proposes a paradigm leap from pure phenomenological fitting to the fusion of phenomenological fitting and endogenous deduction. By embedding physical meta-principles into neural network architecture, we construct the Meta-Principle Phy

The polygenic risk scores (PRS) have emerged as an important methodology for quantifying genetic predisposition to complex traits and clinical disease. Significant progress has been made in applying PRS to conditions such as obesity, cancer, and type 2 diabetes (T2DM). Studies have demonstrated that PRS can effectively identify individuals at high risk, thereby enabling early screening, personalized treatment, and targeted interventions for diseases with a genetic predisposition. One current lim

The rapid advancement of Audio Large Language Models (ALLMs) has enabled cost-effective, high-fidelity generation and manipulation of both speech and non-speech audio, including sound effects, singing voices, and music. While these capabilities foster creativity and content production, they also introduce significant security and trust challenges, as realistic audio deepfakes can now be generated and disseminated at scale. Existing audio deepfake detection (ADD) countermeasures (CMs) and benchma

In classical Reinforcement Learning from Human Feedback (RLHF), Reward Models (RMs) serve as the fundamental signal provider for model alignment. As Large Language Models evolve into agentic systems capable of autonomous tool invocation and complex reasoning, the paradigm of reward modeling faces unprecedented challenges -- most notably, the lack of benchmarks specifically designed to assess RM capabilities within tool-integrated environments. To address this gap, we present Plan-RewardBench, a

Accurate ocean mapping is essential for applications such as bathymetry estimation, seabed characterization, marine litter detection, and ecosystem monitoring. However, ocean remote sensing (RS) remains constrained by limited labeled data and by the reduced transferability of models pre-trained mainly on land-dominated Earth observation imagery. In this paper, we propose OceanMAE, an ocean-specific masked autoencoder that extends standard MAE pre-training by integrating multispectral Sentinel-2

Alignment in LLMs is more brittle than commonly assumed: misalignment can be induced by adversarial prompts, benign fine-tuning, emergent misalignment, and goal misgeneralization. Recent evidence suggests that some misalignment behaviors are encoded as linear structure in activation space, making it tractable via activation steering, which could be used as a lightweight runtime defense. We implement three methods: Steer-With-Fixed-Coefficient (SwFC), which applies uniform additive steering, and

Reinforcement learning (RL) has become an effective approach for advancing the reasoning capabilities of large language models (LLMs) through the strategic integration of external search engines. However, current RL-based search agents often rely on a process of stochastic exploration guided by carefully crafted outcome rewards, leading to inefficient reasoning trajectories and unstable training. To address these issues, we propose a novel framework, Hierarchical Experience (HiExp), to enhance t

Adapting Multimodal Large Language Models (MLLMs) for hour-long videos is bottlenecked by context limits. Dense visual streams saturate token budgets and exacerbate the lost-in-the-middle phenomenon. Existing heuristics, like sparse sampling or uniform pooling, blindly sacrifice fidelity by discarding decisive moments and wasting bandwidth on irrelevant backgrounds. We propose Tempo, an efficient query-aware framework compressing long videos for downstream understanding. Tempo leverages a Small

Training-free open-vocabulary semantic segmentation(TF-OVSS) has recently attracted attention for its ability to perform dense prediction by leveraging the pretrained knowledge of large vision and vision-language models, without requiring additional training. However, due to the limited input resolution of these pretrained encoders, existing TF-OVSS methods commonly adopt a sliding-window strategy that processes cropped sub-images independently. While effective for managing high-resolution input

In this work we present a rigorous theoretical framework to a foundational problem of AI safety, namely adversarial robustness. In particular, we show that the adversarial robustness problem can be reduced to a lattice traversal problem. Each element of this lattice corresponds to an interval, i.e., an axis-aligned hyper-rectangle, containing an input point $\mathbf{x}$. Consider a multilayered perceptron classifier (MLP). An interval $I$ constitutes a sound certification if $\mathbf{x} \in I$ a

Software systems built from versioned AI components increasingly need lifecycle-time governance: when a capability module evolves into a new version, the hosting system must decide whether the new version may be activated safely, under what deployment conditions it should run, how it must be monitored, and when it should be rolled back. Existing software-deployment patterns (canary release, blue-green, feature flags, and MLOps pipelines) address parts of this loop but were designed for stateless

Interpreting individual neurons in deep neural networks is a crucial step towards understanding their complex decision-making processes and ensuring AI safety. Despite recent progress in neuron labeling, existing methods often limit the search space to predefined concept vocabularies or produce overly specific descriptions that fail to capture higher-order, global concepts. We introduce LINE, a novel, training-free iterative approach tailored for open-vocabulary concept labeling in vision models

Intelligent systems powered by large-scale sensor networks are shifting from predefined monitoring to intent-driven operation, revealing a critical Semantic-to-Physical Mapping Gap. While large language models (LLMs) excel at semantic understanding, existing perception-centric pipelines operate retrospectively, overlooking the fundamental decision of what to sense and when. We formalize this proactive decision as Semantic-Spatial Sensor Scheduling (S3) and demonstrate that direct LLM planning is

Algorithmic recourse aims to provide actionable recommendations that enable individuals to change unfavorable model outcomes, and prior work has extensively studied properties such as efficiency, robustness, and fairness. However, the role of personalization in recourse remains largely implicit and underexplored. While existing approaches incorporate elements of personalization through user interactions, they typically lack an explicit definition of personalization and do not systematically anal

Reinforcement learning is typically treated as a uniform, data-driven optimization process, where updates are guided by rewards and temporal-difference errors without explicitly exploiting global structure. In contrast, dynamic programming methods rely on structured information propagation, enabling efficient and stable learning. In this paper, we provide evidence that such structure can be recovered from the learning dynamics of distributional reinforcement learning. By analyzing the temporal e

Retrieving rare and safety-critical driving scenarios from large-scale datasets is essential for building robust autonomous driving (AD) systems. As dataset sizes continue to grow, the key challenge shifts from collecting more data to efficiently identifying the most relevant samples. We introduce SearchAD, a large-scale rare image retrieval dataset for AD containing over 423k frames drawn from 11 established datasets. SearchAD provides high-quality manual annotations of more than 513k bounding

While infographics have become a powerful medium for communicating data-driven stories, authoring them from scratch remains challenging, especially for novice users. Retrieving relevant exemplars from a large corpus can provide design inspiration and promote reuse, substantially lowering the barrier to infographic authoring. However, effective retrieval is difficult because users often express design intent in ambiguous natural language, while infographics embody rich and multi-faceted visual de

Model editing aims to update knowledge to add new concepts and change relevant information without retraining. Lifelong editing is a challenging task, prone to disrupting previously learned concepts, especially for Vision Language Models (VLMs), because sequential edits can lead to degraded reasoning and cross modal misalignment. Existing VLM knowledge editing methods based on gated adapters, activation edits, and parameter merging techniques address catastrophic forgetting seen in full fine tun

Data mixing strategy is essential for large language model (LLM) training. Empirical evidence shows that inappropriate strategies can significantly reduce generalization. Although recent methods have improved empirical performance, several fundamental questions remain open: what constitutes a domain, whether human and model perceptions of domains are aligned, and how domain weighting influences generalization. We address these questions by establishing formal connections between gradient dynamic

Post-training has become central to turning pretrained large language models (LLMs) into aligned, capable, and deployable systems. Recent progress spans supervised fine-tuning (SFT), preference optimization, reinforcement learning (RL), process supervision, verifier-guided methods, distillation, and multi-stage pipelines. Yet these methods are often discussed in fragmented ways, organized by labels or objectives rather than by the behavioral bottlenecks they address. This survey argues that LLM

LLM-driven GUI agents are increasingly used in production systems to automate workflows and simulate users for evaluation and optimization. Yet most GUI-agent evaluations emphasize task success and provide limited evidence on whether agents interact in human-like ways. We present a trace-level evaluation framework that compares human and agent behavior across (i) task outcome and effort, (ii) query formulation, and (iii) navigation across interface states. We instantiate the framework in a contr

We present a large-scale survey of sustainability communication and motivation in robotics research. Our analysis covers nearly 50,000 open-access papers from arXiv's cs.RO category published between 2015 and early 2026. In this study, we quantify how often papers mention social, ecological, and sustainability impacts, and we analyse their alignment with the UN Sustainable Development Goals (SDGs). The results reveal a persistent gap between the field's potential and its stated intent. While a l

Deploying LLM-powered agents in enterprise scenarios such as cloud technical support demands high-quality, domain-specific skills. However, existing skill creators lack domain grounding, producing skills poorly aligned with real-world task requirements. Moreover, once deployed, there is no systematic mechanism to trace execution failures back to skill deficiencies and drive targeted refinements, leaving skill quality stagnant despite accumulating operational evidence. We introduce SkillForge, a

Personalized large language models (PLLMs) have garnered significant attention for their ability to align outputs with individual's needs and preferences. However, they still struggle with long-horizon tasks, such as tracking a user's extensive history of conversations or activities. Existing memory mechanisms often fail to capture evolving behaviors, and RAG paradigms are trapped by a quality-efficiency tradeoff. Meanwhile, parametric adaptation is bottlenecked by train-inference gap due to the

Instruction-tuned language models increasingly rely on large multi-turn dialogue corpora, but these datasets are often noisy and structurally inconsistent, with topic drift, repetitive chitchat, and mismatched answer formats across turns. We address this from a data selection perspective and propose \textbf{MDS} (Multi-turn Dialogue Selection), a dialogue-level framework that scores whole conversations rather than isolated turns. MDS combines a global coverage stage that performs bin-wise select

High-fidelity generative models are increasingly needed in privacy-sensitive scenarios, where access to data is severely restricted due to regulatory and copyright constraints. This scarcity hampers model development--ironically, in settings where generative models are most needed to compensate for the lack of data. This creates a self-reinforcing challenge: limited data leads to poor generative models, which in turn fail to mitigate data scarcity. To break this cycle, we propose a reinforcement

History textbooks often contain implicit biases, nationalist framing, and selective omissions that are difficult to audit at scale. We propose an agentic evaluation architecture comprising a multimodal screening agent, a heterogeneous jury of five evaluative agents, and a meta-agent for verdict synthesis and human escalation. A central contribution is a Source Attribution Protocol that distinguishes textbook narrative from quoted historical sources, preventing the misattribution that causes syst

Exemplar replay has become an effective strategy for mitigating catastrophic forgetting in federated continual learning (FCL) by retaining representative samples from past tasks. Existing studies focus on designing sample-importance estimation mechanisms to identify information-rich samples. However, they typically overlook strategies for effectively utilizing the selected exemplars, which limits their performance under continual dynamic heterogeneity across clients and tasks. To address this is

Large language model (LLM) reinforcement learning (RL) pipelines are often bottlenecked by rollout generation, making end-to-end training slow. Recent work mitigates this by running rollouts with quantization to accelerate decoding, which is the most expensive stage of the RL loop. However, these setups destabilize optimization by amplifying the training-inference gap: rollouts are operated at low precision, while learning updates are computed at full precision. To address this challenge, we pro

With the rise of LLMs, there is an increasing need for intelligent recommendation assistants that can handle complex queries and provide personalized, reasoning-driven recommendations. LLM-based recommenders show potential but face challenges in multi-step reasoning, underscoring the need for reasoning-augmented systems. To address this gap, we propose ReRec, a novel reinforcement fine-tuning (RFT) framework designed to improve LLM reasoning in complex recommendation tasks. Our framework introdu

Simulations, and more recently LLM agent simulations, have been adopted as useful tools for policymakers to explore interventions, rehearse potential scenarios, and forecast outcomes. While LLM simulations have enormous potential, two critical challenges remain understudied: the dual-use potential of accurate models of individual or population-level human behavior and the difficulty of validating simulation outputs. In light of these limitations, we must define boundaries for both simulation dev

The evolution of Large Language Models (LLMs) is shifting the focus from single, verifiable tasks toward complex, open-ended real-world scenarios, imposing significant challenges on the post-training phase. In these settings, the scale and complexity of reward systems have grown significantly, transitioning toward multi-objective formulations that encompass a comprehensive spectrum of model capabilities and application contexts. However, traditional methods typically rely on fixed reward weights

While Large Language Models (LLMs) have achieved remarkable performance, they remain vulnerable to jailbreak attacks that circumvent safety constraints. Existing strategies, ranging from heuristic prompt engineering to computationally intensive optimization, often face significant trade-offs between effectiveness and efficiency. In this work, we propose Contextual Representation Ablation (CRA), a novel inference-time intervention framework designed to dynamically silence model guardrails. Predic

Embodied agents are expected to operate persistently in dynamic physical environments, continuously acquiring new capabilities over time. Existing approaches to improving agent performance often rely on modifying the agent itself -- through prompt engineering, policy updates, or structural redesign -- leading to instability and loss of identity in long-lived systems. In this work, we propose a capability-centric evolution paradigm for embodied agents. We argue that a robot should maintain a pers

Existing accountability frameworks for AI systems, legal, ethical, and regulatory, rest on a shared assumption: for any consequential outcome, at least one identifiable person had enough involvement and foresight to bear meaningful responsibility. This paper proves that agentic AI systems violate this assumption not as an engineering limitation but as a mathematical necessity once autonomy exceeds a computable threshold. We introduce Human-Agent Collectives, a formalisation of joint human-AI sys

Reinforcement learning with verifiable rewards (RLVR) can improve low-$k$ reasoning accuracy while narrowing solution coverage on challenging math questions, and pass@1 gains do not necessarily translate into better large-$k$ performance. Existing hint-based approaches can make challenging questions trainable, but they leave two issues underexplored: teacher-student distribution mismatch and the need to reduce hint exposure to match no-hint evaluation. We address these issues through two compone

LLMs gain competence by predicting words in human text, which often reflects how people perform tasks. Consequently, coupling an LLM to an engineered runtime turns prediction into control: outputs trigger interventions that enact goal-oriented behavior. We argue that a central design lever is where control resides in these systems. Brains embed prediction within layered feedback controllers calibrated by the consequences of action. By contrast, LLM agents implement Cartesian agency: a learned co

Large language models (LLMs) sometimes appear to exhibit emotional reactions. We investigate why this is the case in Claude Sonnet 4.5 and explore implications for alignment-relevant behavior. We find internal representations of emotion concepts, which encode the broad concept of a particular emotion and generalize across contexts and behaviors it might be linked to. These representations track the operative emotion concept at a given token position in a conversation, activating in accordance wi

A heavily safety-trained model will hand a physician the full, patient-followable benzodiazepine taper and refuse it to the patient who needs it, over identical clinical facts; the knowledge is present either way. IatroBench measures that asymmetry across sixty pre-registered clinical scenarios and six frontier models (3,600 responses), scoring each on two axes, commission harm (what a response gets wrong) and omission harm (what it withholds), through a physician-authored structured evaluation

Generative AI is set to transform the legal profession, though its most promising uses and ultimate effects are still unclear. While AI models like GPT-4 improve efficiency, they can also “hallucinate” and may undermine legal judgment, particularly in complex tasks typically handled by skilled lawyers. This article examines two emerging AI innovations that may mitigate these concerns: Retrieval Augmented Generation (RAG), which grounds AI-powered analysis in legal sources, and AI reasoning model

This survey presents a comprehensive review of Large Language Models (LLMs) developed for the Arabic language and its dialects. It categorizes models by architecture (encoder-only, decoder-only, and encoder-decoder) and by linguistic form, including Classical Arabic, Modern Standard Arabic, and Dialectal Arabic. We analyze monolingual, bilingual, and multilingual models, evaluating their performance on tasks such as sentiment analysis, named entity recognition, and question answering. The survey