Artificial Intelligence Paper Rankings

Foundation Models to Unlock Real-World Evidence from Nationwide Medical Claims

Machine Collective Intelligence for Explainable Scientific Discovery

AI scientists produce results without reasoning scientifically

Towards a General Intelligence and Interface for Wearable Health Data

Generative structure search for efficient and diverse discovery of molecular and crystal structures

A Collective Variational Principle Unifying Bayesian Inference, Game Theory, and Thermodynamics

IatroBench: Pre-Registered Evidence of Iatrogenic Harm from AI Safety Measures

AI-Assisted Peer Review at Scale: The AAAI-26 AI Review Pilot

Hodoscope: Unsupervised Monitoring for AI Misbehaviors

Value-Conflict Diagnostics Reveal Widespread Alignment Faking in Language Models

Emotion Concepts and their Function in a Large Language Model

SymptomAI: Towards a Conversational AI Agent for Everyday Symptom Assessment

Unbiased Prevalence Estimation with Multicalibrated LLMs

Heterogeneous Scientific Foundation Model Collaboration

Formal Conjectures: An Open and Evolving Benchmark for Verified Discovery in Mathematics

Epistemic Blinding: An Inference-Time Protocol for Auditing Prior Contamination in LLM-Assisted Analysis

HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?

Containment Verification: AI Safety Guarantees Independent of Alignment

Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment

Subliminal Transfer of Unsafe Behaviors in AI Agent Distillation

Brief chatbot interactions produce lasting changes in human moral values

Bounding the Black Box: A Statistical Certification Framework for AI Risk Regulation

The Power of Power Law: Asymmetry Enables Compositional Reasoning

Polysemantic Experts, Monosemantic Paths: Routing as Control in MoEs

BioMiner: A Multi-modal System for Automated Mining of Protein-Ligand Bioactivity Data from Literature

Auditable Agents

KISS - Knowledge Infrastructure for Scientific Simulation: A Scaffolding for Agentic Earth Science

Using large language models for embodied planning introduces systematic safety risks

Context Over Content: Exposing Evaluation Faking in Automated Judges

Numerical Instability and Chaos: Quantifying the Unpredictability of Large Language Models

Prospective multi-pathogen disease forecasting using autonomous LLM-guided tree search

Discovering Novel LLM Experts via Task-Capability Coevolution

Towards Understanding Specification Gaming in Reasoning Models

The Accountability Horizon: An Impossibility Theorem for Governing Human-Agent Collectives

How Independent are Large Language Models? A Statistical Framework for Auditing Behavioral Entanglement and Reweighting Verifier Ensembles

RePAIR: Interactive Machine Unlearning through Prompt-Aware Model Repair

How LLMs Are Persuaded: A Few Attention Heads, Rerouted

Process Reward Agents for Steering Knowledge-Intensive Reasoning

Towards Faster Language Model Inference Using Mixture-of-Experts Flow Matching

Participatory provenance as representational auditing for AI-mediated public consultation

Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond

RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time

Conditional Attribute Estimation with Autoregressive Sequence Models

Detecting Safety Violations Across Many Agent Traces

OLLM: Options-based Large Language Models

Model Spec Midtraining: Improving How Alignment Training Generalizes

Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence

How Adversarial Environments Mislead Agentic AI?

MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval

The Capability Paradox: How Smarter Auditors Make Multi-Agent Systems Less Secure

Advancing Mathematics Research with AI-Driven Formal Proof Search

Hidden Biases in Conditioning Autoregressive Models

DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents

When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel

ResearchEVO: An End-to-End Framework for Automated Scientific Discovery and Documentation

Resolving the bias-precision paradox with stochastic causal representation learning for personalized medicine

Characterizing Model-Native Skills

EvoLM: Self-Evolving Language Models through Co-Evolved Discriminative Rubrics

Introspection Adapters: Training LLMs to Report Their Learned Behaviors

Hallucination as Exploit: Evidence-Carrying Multimodal Agents

CauSim: Scaling Causal Reasoning with Increasingly Complex Causal Simulators

Causal Bias Detection in Generative Artifical Intelligence

Attractor Geometry of Transformer Memory: From Conflict Arbitration to Confident Hallucination

The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations

Recursive Multi-Agent Systems

Fusion-fission forecasts when AI will shift to undesirable behavior

Unleashing LLMs in Bayesian Optimization: Preference-Guided Framework for Scientific Discovery

Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User Proxies

SWE-chat: Coding Agent Interactions From Real Users in the Wild

Extracting Search Trees from LLM Reasoning Traces Reveals Myopic Planning

SELFDOUBT: Uncertainty Quantification for Reasoning LLMs via the Hedge-to-Verify Ratio

LACE: Lattice Attention for Cross-thread Exploration

Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment

Reason in Chains, Learn in Trees: Self-Rectification and Grafting for Multi-turn Agent Policy Optimization

A Versatile AI Agent for Rare Disease Diagnosis and Risk Gene Prioritization

Agentic Discovery of Exchange-Correlation Density Functionals

JURY-RL: Votes Propose, Proofs Dispose for Label-Free RLVR

Transferable Human Mobility Network Reconstruction with neuroGravity

From Insight to Action: A Novel Framework for Interpretability-Guided Data Selection in Large Language Models

CIVeX: Causal Intervention Verification for Language Agents

Bias by Necessity: Impossibility Theorems for Sequential Processing with Convergent AI and Human Validation

PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations

QED: An Open-Source Multi-Agent System for Generating Mathematical Proofs on Open Problems

TRACE: Trajectory Correction from Cross-layer Evidence for Hallucination Reduction

SMCEvolve: Principled Scientific Discovery via Sequential Monte Carlo Evolution

Data Language Models: A New Foundation Model Class for Tabular Data

LLM Reasoning Is Latent, Not the Chain of Thought

ASH: Agents that Self-Hone via Embodied Learning

Learning to Build the Environment: Self-Evolving Reasoning RL via Verifiable Environment Synthesis

MARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning

Process Matters more than Output for Distinguishing Humans from Machines

Attributing Emergence in Million-Agent Systems

PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments

Rollout Cards: A Reproducibility Standard for Agent Research

Alignment Imprint: Zero-Shot AI-Generated Text Detection via Provable Preference Discrepancy

Verifiable Process Rewards for Agentic Reasoning

Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents

Thinking in Text and Images: Interleaved Vision--Language Reasoning Traces for Long-Horizon Robot Manipulation

Orchard: An Open-Source Agentic Modeling Framework

State-Centric Decision Process

Read the Paper, Write the Code: Agentic Reproduction of Social-Science Results

Awakening the Sleeping Agent: Lean-Specific Agentic Data Reactivates General Tool Use in Goedel Prover

Distribution-Aware Algorithm Design with LLM Agents

Unlocking LLM Creativity in Science through Analogical Reasoning

What Really Improves Mathematical Reasoning: Structured Reasoning Signals Beyond Pure Code

Reason to Play: Behavioral and Brain Alignment Between Frontier LRMs and Human Game Learners

Geometric Metrics for MoE Specialization: From Fisher Information to Early Failure Detection

From Prompts to Protocols: An AI Agent for Laboratory Automation

Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs

Self-Correction as Feedback Control: Error Dynamics, Stability Thresholds, and Prompt Interventions in LLMs

AI Co-Mathematician: Accelerating Mathematicians with Agentic AI

SciCore-Mol: Augmenting Large Language Models with Pluggable Molecular Cognition Modules

To See the Unseen: on the Generalization Ability of Transformers in Symbolic Reasoning

D3-Gym: Constructing Real-World Verifiable Environments for Data-Driven Discovery

Reasoning Can Be Restored by Correcting a Few Decision Tokens

The Wittgensteinian Representation Hypothesis: Is Language the Attractor of Multimodal Convergence?

Policy-Invisible Violations in LLM-Based Agents

Seirênes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning

When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction

Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key

SGA-MCTS: Decoupling Planning from Execution via Training-Free Atomic Experience Retrieval

Efficient Agentic Reasoning Through Self-Regulated Simulative Planning

FormalScience: Scalable Human-in-the-Loop Autoformalisation of Science with Agentic Code Generation in Lean

Reasoning Fails Where Step Flow Breaks

Reasoning Structure Matters for Safety Alignment of Reasoning Models

SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning

History Anchors: How Prior Behavior Steers LLM Decisions Toward Unsafe Actions

To Whom Do Language Models Align? Measuring Principal Hierarchies Under High-Stakes Competing Demands

MIRROR: A Hierarchical Benchmark for Metacognitive Calibration in Large Language Models

PROMETHEUS: Automating Deep Causal Research Integrating Text, Data and Models

CT Open: An Open-Access, Uncontaminated, Live Platform for the Open Challenge of Clinical Trial Outcome Prediction

Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents

SAVE: A Generalizable Framework for Multi-Condition Single-Cell Generation with Gene Block Attention

Agentick: A Unified Benchmark for General Sequential Decision-Making Agents

Ulterior Motives: Detecting Misaligned Reasoning in Continuous Thought Models

The Evaluation Differential: When Frontier AI Models Recognise They Are Being Tested

Missingness-MDPs: Bridging the Theory of Missing Data and POMDPs

CLEF: EEG Foundation Model for Learning Clinical Semantics

A Foundation Model for Zero-Shot Logical Rule Induction

Seeing Through Experts Eyes A Foundational Vision Language Model Trained on Radiologists Gaze and Reasoning

TRIAGE: Evaluating Prospective Metacognitive Control in LLMs under Resource Constraints

Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack

Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists

FibQuant: Universal Vector Quantization for Random-Access KV-Cache Compression

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

Discovering Agentic Safety Specifications from 1-Bit Danger Signals

MCPHunt: An Evaluation Framework for Cross-Boundary Data Propagation in Multi-Server MCP Agents

Stability Implies Redundancy: Delta Attention Selective Halting for Efficient Long-Context Prefilling

Fully Open Meditron: An Auditable Pipeline for Clinical LLMs

Learning to Hand Off: Provably Convergent Workflow Learning under Interface Constraints

Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems

Poly-EPO: Training Exploratory Reasoning Models

Geometry over Density: Few-Shot Cross-Domain OOD Detection

SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions

Multi-Agent Orchestration for High-Throughput Materials Screening on a Leadership-Class System

Stable Agentic Control: Tool-Mediated LLM Architecture for Autonomous Cyber Defense

From Debate to Decision: Conformal Social Choice for Safe Multi-Agent Deliberation

When Can Human-AI Teams Outperform Individuals? Tight Bounds with Impossibility Guarantees

Do Agent Rules Shape or Distort? Guardrails Beat Guidance in Coding Agents

Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory

Can Large Language Models Reinvent Foundational Algorithms?

The Compliance Trap: How Structural Constraints Degrade Frontier AI Metacognition Under Adversarial Pressure

CoDaS: AI Co-Data-Scientist for Biomarker Discovery via Wearable Sensors

XDecomposer: Learning Prior-Free Set Decomposition for Multiphase X-ray Diffraction

AIBuildAI: An AI Agent for Automatically Building AI Models

State Contamination in Memory-Augmented LLM Agents

The Query Channel: Information-Theoretic Limits of Masking-Based Explanations

Imperfect World Models are Exploitable

IoT-Brain: Grounding LLMs for Semantic-Spatial Sensor Scheduling

Correct Is Not Enough: Training Reasoning Planners with Executor-Grounded Rewards

Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search Trajectories

Quantifying and Understanding Uncertainty in Large Reasoning Models

Generative Recursive Reasoning

Geometric Routing Enables Causal Expert Control in Mixture of Experts

Problem Reductions at Scale: Agentic Integration of Computationally Hard Problems

Self-Programmed Execution for Language-Model Agents

FVD: Inference-Time Alignment of Diffusion Models via Fleming-Viot Resampling

OptimusKG: Unifying biomedical knowledge in a modern multimodal graph

The Two Boundaries: Why Behavioral AI Governance Fails Structurally

From Holo Pockets to Electron Density: GPT-style Drug Design with Density

Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering Tasks with Generative Optimization

PopuLoRA: Co-Evolving LLM Populations for Reasoning Self-Play

Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation

On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment

$δ$-mem: Efficient Online Memory for Large Language Models

ECG-WM: A Physiology-Informed ECG World Model for Clinical Intervention Simulation

Von Neumann Networks

Ex Ante Evaluation of AI-Induced Idea Diversity Collapse

Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention

NeuroMAS: Multi-Agent Systems as Neural Networks with Joint Reinforcement Learning

Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction

Quantifying the human visual exposome with vision language models

Contextual Agentic Memory is a Memo, Not True Memory

Reinforcing VLAs in Task-Agnostic World Models

Breaking $\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning

MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGs

Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language Models