AI News Archive: June 1, 2026 — Part 21
Sourced from 500+ daily AI sources, scored by relevance.
- Multilinguality of Large Language Models From a Structural Perspective
Large language models (LLMs) have excelled in processing multiple languages through pre- and post-training on multilingual data, even though English dominates the training data. Prior work focusing on token representations has revealed how those LLMs process non-English text. Although these analyses...
- HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems
LLM agents are increasingly expected to operate across heterogeneous task regimes that require distinct execution paradigms. This challenges fixed agent systems and motivates system-level meta-adaptation beyond isolated component updates. While existing works have adapted external harness or trained...
- An Algebraic View of the Expressivity of Recurrent Language Models
What formal languages can a recurrent neural language model recognize? Formal results in the literature conflict: some authors report Turing-completeness, while others show equivalence to regular languages. The reason for this discrepancy is that the underlying arithmetic model differs. The paper de...
- TriAlign: Towards Universal Truth Consistency in Personalized LLM Alignment
Personalized large language models adapt responses to users' preferences and social attributes, but can introduce substantial universal truth inconsistencies across social groups, where some groups systematically receive less accurate responses on objective tasks. Existing alignment methods either i...
- Construction of Historical Knowledge Graphs Based on BERT and Graph Neural Networks
Through digital humanities research and scale-up historical data analysis, a significant amount of traditional historical text is converted into structured knowledge graphs. This paper provides a high-level architecture that combines bidirectional encoder representations of transformers (BERT) and g...
- THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models
Multi-turn jailbreak attacks pose a growing threat to LLMs by exploiting conversational dynamics such as gradual escalation and cross-turn coordination. Existing defenses either rely on costly retraining -- often degrading model utility -- or apply single-turn analysis independently at each turn, fa...
- Argument Collapse: LLMs Flatten Long-Form Public Debate
As LLMs are increasingly used to draft public-facing arguments, they may flatten public debate by repeatedly introducing the same polished, plausible arguments. We study argument collapse, the tendency of essays generated by different LLMs to converge to a smaller set of main arguments, sub-argument...
- RCEM: Embedder Equipped with Query Rewriting Skill for Robust Conversational Search in Distributional Shift
Conversational search has become increasingly important in retrieval-augmented generation (RAG) systems, where users interact with AI assistants through multi-turn conversations containing context-dependent queries. We propose RCEM, a conversational dense retrieval model that distills the query refo...
- Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning
Selecting the best response from multiple small-model samples using a stronger scorer is a simple inference-time strategy, but fails when the small model has already committed to incorrect reasoning paths. PRM guided search avoids this by scoring candidate continuations during generation, but requir...
- Encoded but Not Routed: Explaining the Table-Chart Gap in Scientific Claim Verification
Multimodal LLMs are increasingly used to assist scientific peer review, where a core requirement is verifying whether claims in a paper are supported by its evidence. Prior work has shown that models perform substantially better at this task when the evidence is a table than when it is a chart of th...
- Why Do Self-Harm Prediction Models Struggle to Generalise? Lexical and Semantic Variations in Emergency Department Triage Notes
Self-harm presentations to emergency departments (EDs) are strongly associated with higher suicide risk. NLP models have shown robust performance in detecting self-harm from triage notes within single hospitals, yet performance often declines across institutions. To examine potential causes, we comp...
- MobEvolve: An Agentic Self-Evolving Heuristic System for Interpretable Human Mobility Generation
Human mobility generation aims to synthesize realistic trip chains for target populations based on individual features. Existing paradigms, including deep generative models, LLM-based methods, and traditional heuristics, struggle to satisfy the complex demands of this task while simultaneously maint...
- SiteBlob
Spot AI vibecoding fingerprints before launch
- Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity
Large language models are increasingly used in multi-agent systems, where they see and respond to other agents' answers. A key risk is conformity: a model may abandon its own answer simply because others agree on a different one. Prior studies show that LLMs often revise toward a majority answer, bu...
- AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training
Token selection is pivotal for effective LLM post-training. However, existing methods mostly rely on local heuristics and rarely formulate token selection as a principled valuation of individual response tokens. We introduce $\textbf{AlphaToken}$, a response token valuation framework that decouples ...
- Benchmarking LLM-as-a-Judge for Long-Form Output Evaluation
As large language models (LLMs) are increasingly used for long-form generation, reliably evaluating long-form outputs has become a critical challenge. LLM-as-a-judge offers a scalable alternative to human evaluation, yet its reliability in long-form output evaluation remains underexamined: existing ...
- Identifying High-Confidence Social Biases in LLMs for Trustworthy Conversational Tutoring Agents
Conversational tutoring agents have been shown to improve learning engagement and student outcomes, and large language models (LLMs) are increasingly used in these systems to provide scalable, personalized feedback. However, LLMs may perpetuate or amplify stereotypical social biases, posing particul...
- Defenses & Enablers For Skill Injection Attacks on Terminal Based Agents
Large language model (LLM) agents increasingly rely on reusable skills i.e. documents describing task-specific procedures. However, this introduces a new attack surface for agents to manage. We study two complementary directions for this threat. First, we evaluate guardian-based defenses: an interme...
- SentGuard: Sentence-Level Streaming Guardrails for Large Language Models
Large language models increasingly stream long, reasoning-intensive responses in real time, making when to moderate as critical as whether to moderate. Existing guardrails fall into two unsatisfactory extremes: response-level methods delay intervention until the full output is generated, whereas tok...
- Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning
This paper investigates the entropy dynamics of Chain-of-Thought (CoT) and uncovers a consistent two-phase structure: an Uncertainty Region of exploration transitioning sharply to a Confidence Region of convergence. We demonstrate that the Confidence Region possesses two critical properties: 1) High...
- Automated Essay Scoring and Language Certification: Assessing Generalizability, Agreement and Validity for French
In Automated Essay Scoring (AES), benchmarking practices have fostered minimalist evaluation practices, in contrast with the broader-view recommendations of evaluation frameworks, such as the argument-based validation framework (ABV), which argued in favor of a multidimensional assessment of systems...
- Scaling Agentic Capabilities via Grounded Interaction Synthesis
General agentic intelligence hinges on the ability to interact with diverse real-world tools to complete complex tasks, a capability fundamentally tied to the quality of interaction data. To bypass the prohibitive costs of human annotation, prevailing paradigms depend entirely on Large Language Mode...
- Eyettention II: A Dual-Sequence Architecture for Modeling Fixation Location, Within-Word Landing Position, and Fixation Duration in Reading
The way our eyes move while reading provides valuable insights into both the reader's cognitive processes and the properties of the text. In particular, eye-tracking-while-reading data has shown to be highly beneficial in various technological applications, such as enhancing and interpreting languag...
- HMPO: Hybrid Median-length Policy Optimization for Chain-of-Thought Compression
Large language models achieve remarkable performance via extended chain-of-thought (CoT) reasoning, yet this lengthy process incurs substantial inference overhead. Existing CoT compression methods struggle with inflexible manual length budgets, computationally expensive multi-stage training pipeline...
- Mitigating Bias in Locally Constrained Decoding via Tractable Proposals
Generations from large language models often fail to conform to desired constraints such as JSON schema. Existing locally constrained decoding (LCD) approaches enforce constraints by myopically masking out next tokens, resulting in biased sampling and degradation in performance. Recent work uses seq...
- ContinuousBench: Can Differentially Private Synthetic Text Improve Capabilities?
Differentially private (DP) text synthesis promises to unlock sensitive corpora for model training, but it remains unclear whether DP synthetic data transmits genuinely new knowledge and capabilities present only in those corpora. This is because existing evaluations rely on tasks that are nearly so...
- When Meaning Travels: A Granular Lens on Hybrid-MoE's Role in Idiomatic Understanding for Language Models
In the contemporary epoch of multilingual education, learning idioms provides a fascinating gateway towards creativity, cultural values, historical context, and diverse perspectives inherent to various linguistic traditions. This paper showcases the navigation of retaining figurative and cultural se...
- EvoPool: Evolutionary Programmatic Annotation for Label-Efficient Specialized Supervision
Large language models excel at general tasks but underperform smaller supervised models in specialized, high-stakes domains where training labels are costly. We address this regime with EvoPool, an evolutionary multi-agent framework inspired by Darwinian evolution. Three specialized agents iterative...
- My Period AI: Cycle Tracker
AI-powered period tracking for real cycles
- RoboTrustBench: Benchmarking the Trustworthiness of Video World Models for Robotic Manipulation
Video world models are increasingly used in robotic manipulation, yet existing benchmarks mostly evaluate them under valid, feasible, and safe instructions. We introduce RoboTrustBench, a benchmark for evaluating the trustworthiness of video world models under four scenarios: Normal, Constraint-Sens...
- Beyond $\ell_2$-norm and $\ell_\infty$-norm: A Curvature-Inspired $\ell_p$-Norm Scheme for Deep Neural Networks
The existing optimizers for deep neural networks (DNNs) typically rely on either the $\ell_2$ norm or the $\ell_\infty$ norm, resulting in optimizers that do not adapt well to substantial changes in curvature across parameter dimensions. Generally, the training process of DNNs often exhibits strong ...
- Ablating Archetypes: The Stability of Archetypal SAEs is an Artifact of Initialization and Metric Design
Dictionary learning with sparse autoencoders (SAEs) produces overcomplete bases from neural network activations that are often interpretable and reduces polysemanticity. However, features from SAEs vary substantially across random seeds -- a problem known as instability. Archetypal SAEs (Fel et al.,...
- Realistic noise synthesis reduces bias and improves tissue microstructure estimation with supervised machine learning
Diffusion MRI enables non-invasive probing of tissue microstructure, but accurate parameter estimation is challenged by noise-related effects. In supervised machine learning frameworks trained on simulated data, discrepancies between the noise characteristics of simulated and acquired signals introd...
- Uncertainty-Aware Graph Neural Reconstruction of Urban Temperature Fields from Sparse Sensors under Deployment Constraints
Reconstructing spatially continuous daily temperature fields from sparse observations is important for urban climate monitoring and heat-risk analysis, but practical deployments are limited by sensor budgets and spacing constraints. This study proposes an uncertainty-aware graph neural network (GNN)...
- World-Task Factorization for Robot Learning
Robot learning must produce policies that generalize to new combinations of constraints, teammates, and environments. To achieve this, we must structurally factor the policy, which is a choice that dictates what generalizes, what requires retraining, and what remains entangled. Existing methods span...
- Provable Data Scaling Law for Meta Learning via Complexity Minimization
Pre-training has become a fundamental paradigm in modern machine learning, with one of its key empirical benefits being reduced downstream sample complexity as the scale of pre-training data increases. However, existing theoretical frameworks for pre-training do not fully explain this phenomenon. In...
- Randomized Least Squares Value Iteration itself is Joint Differentially Private
As reinforcement learning (RL) increasingly applies to sensitive domains, such as health care and recommendation systems, privacy-preserving techniques have become essential to protect users' sensitive information. We investigate privacy-preserving RL under an episodic setting, focusing on algorithm...
- G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphs
LLM-as-Aligner has emerged as a prevalent pre-training paradigm for Text-Attributed Graphs(TAGS), aligning graph and text modalities into a shared embedding space via CLIP-style contrastive learning. While effective on individual downstream tasks, we observe severe catastrophic forgetting when such ...
- Task-Induced Representational Invariances Depend on Learning Objective in Deep RL
Reinforcement Learning (RL) has long served as a model for goal-directed animal behavior in neuroscience. Modern deep RL has shown remarkable success across many domains, further strengthening this connection. The ability to learn abstract representations of high-dimensional state spaces underlies m...
- A Theoretical Framework for Self-Play Theorem Proving Algorithms
Self-play, a type of training algorithm that enables a model to self-improve, has recently shown promising empirical results in the context of formal theorem proving using Large Language Models (LLMs). (Dong & Ma, 2025) instantiate self-play with two cooperating agents: a prover, which proves theore...
- Observation, Not Prediction: Conversation-Level Disaggregated Scheduling for Agentic Serving
LLM-based agents resolve a user task through many turns of dependent inference and tool calls, producing a workload whose total cost is unknown when the task arrives. Existing multi-turn systems keep the turn as the scheduling unit and decide, turn by turn, whether to disaggregate prefill from decod...
- Adaptive Sharpness-Aware Minimization with a Polyak-type Step size: A Theory-Grounded Scheduler
Sharpness-Aware Minimization (SAM) has established itself as a powerful and widely adopted optimizer for training machine learning models. By explicitly minimizing the sharpness of the loss landscape, SAM often improves generalization while delivering strong empirical performance. However, SAM and i...
- FLARE: Diffusion for Hybrid Language Model
Autoregressive (AR) large language models (LLMs) have achieved broad practical success, but sequential decoding remains a key bottleneck for low-latency deployment. Recent efficient-inference work has progressed along two axes: reducing the cost of each model invocation through efficient architectur...
- Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams
Auto-harness systems such as A-Evolve, GEPA, and Meta-Harness improve LLM agents by optimizing prompts, skills, tools, memories, and supporting infrastructure from execution feedback, but they are typically evaluated on fixed offline benchmarks. Real deployments instead present open-ended task strea...
- TypeTab
On-device autocomplete that learns how you write
- Evaluating Real-World Generalizability of Algorithm Selection Models
Algorithm Selection (AS) aims to automatically identify the most suitable optimization algorithm for a given problem instance by leveraging measurable problem characteristics and historical performance data. In this study, we investigate the generalization ability of AS models across both synthetic ...
- A Closer Look at In-Distribution vs. Out-of-Distribution Accuracy for Open-Set Test-time Adaptation
Open-set test-time adaptation (TTA) updates models on new data in the presence of input shifts and unknown output classes. While recent methods have made progress on improving in-distribution (InD) accuracy for known classes, their ability to accurately detect out-of-distribution (OOD) unknown class...
- Flow-Transformed Implicit Processes for Function-Space Variational Inference
Implicit-process priors define distributions over functions through flexible generative mechanisms, making them attractive for Bayesian function-space modelling. However, performing posterior inference with such priors is challenging because their induced function-space distributions are typically n...
- Learning Action-Conditional and Object-Centric Gaussian Splatting World Models for Rigid Objects
World models enable intelligent agents to predict the consequences of their actions on the environment. In this paper, we propose Multi Rigid Object Gaussian World Model (MRO-GWM), a novel model that learns action-conditional dynamics of rigid objects in 3D. By representing the scene by object-centr...
- Private and Stable Test-Time Adaptation with Differential Privacy
Test-time adaptation (TTA) can reduce error on new and different data by updating the model on these inputs during inference. However, these updates raise the issue of privacy w.r.t. the testing data, because the model parameters now depend on all past inputs. To control this privacy risk, we cast m...