Artificial Intelligence Paper Rankings

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

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

Advancing Mathematics Research with AI-Driven Formal Proof Search

Hallucination as Exploit: Evidence-Carrying Multimodal Agents

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

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

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

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

From Prompts to Protocols: An AI Agent for Laboratory Automation

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

Reasoning Can Be Restored by Correcting a Few Decision Tokens

Efficient Agentic Reasoning Through Self-Regulated Simulative Planning

Fully Open Meditron: An Auditable Pipeline for Clinical LLMs

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

State Contamination in Memory-Augmented LLM Agents

Imperfect World Models are Exploitable

Generative Recursive Reasoning

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

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

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

Echo: Learning from Experience Data via User-Driven Refinement

Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models

How Far Are We From True Auto-Research?

Beyond Mode Collapse: Distribution Matching for Diverse Reasoning

Forecasting Scientific Progress with Artificial Intelligence

From Static Risk to Dynamic Trajectories: Toward World-Model-Inspired Clinical Prediction

DeepWeb-Bench: A Deep Research Benchmark Demanding Massive Cross-Source Evidence and Long-Horizon Derivation

Formal Methods Meet LLMs: Auditing, Monitoring, and Intervention for Compliance of Advanced AI Systems

Not all uncertainty is alike: volatility, stochasticity, and exploration

SD-Search: On-Policy Hindsight Self-Distillation for Search-Augmented Reasoning

PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization

What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Models

Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matters Most

PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language Models

AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflows

Robotics-Inspired Guardrails for Foundation Models in Socially Sensitive Domains

Latent-space Attacks for Refusal Evasion in Language Models

SMDD-Bench: Can LLMs Solve Real-World Small Molecule Drug Design Tasks?

MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems

Look Before You Leap: Autonomous Exploration for LLM Agents

OpenComputer: Verifiable Software Worlds for Computer-Use Agents

PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents

TTE-Flash: Accelerating Reasoning-based Multimodal Representations via Think-Then-Embed Tokens

Reliability and Effectiveness of Autonomous AI Agents in Supply Chain Management

ADR: An Agentic Detection System for Enterprise Agentic AI Security

PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control

AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit Assignment

GeoX: Mastering Geospatial Reasoning Through Self-Play and Verifiable Rewards

AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration

Open-World Evaluations for Measuring Frontier AI Capabilities

Causal Evidence for Attention Head Imbalance in Modality Conflict Hallucination

Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents

GIM: Evaluating models via tasks that integrate multiple cognitive domains

Probing Embodied LLMs: When Higher Observation Fidelity Hurts Problem Solving

Memory-Guided Tree Search with Cross-Branch Knowledge Transfer for LLM Solver Synthesis

Conflict-Aware Additive Guidance for Flow Models under Compositional Rewards

Latent Action Reparameterization for Efficient Agent Inference

Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability

PRISMat: Policy-Driven, Permutation-Invariant Autoregressive Material Generation

Property-Guided LLM Program Synthesis for Planning

Harnessing LLM Agents with Skill Programs

Generative AI and the Productivity Divide: Human-AI Complementarities in Education

Library Drift: Diagnosing and Fixing a Silent Failure Mode in Self-Evolving LLM Skill Libraries

Interactive Evaluation Requires a Design Science

Ratchet: A Minimal Hygiene Recipe for Self-Evolving LLM Agents

Baba in Wonderland: Online Self-Supervised Dynamics Discovery for Executable World Models

ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling

Learning to Learn from Multimodal Experience

TOBench: A Task-Oriented Omni-Modal Benchmark for Real-World Tool-Using Agents

Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost

Not Every Rubric Teaches Equally: Policy-Aware Rubric Rewards for RLVR

Episodic-Semantic Memory Architecture for Long-Horizon Scientific Agents

MindLoom: Composing Thought Modes for Frontier-Level Reasoning Data Synthesis

Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents

Mind the Sim-to-Real Gap & Think Like a Scientist

Learning Quantifiable Visual Explanations Without Ground-Truth

CyberCorrect: A Cybernetic Framework for Closed-Loop Self-Correction in Large Language Models

Democratizing Large-Scale Re-Optimization with LLM-Guided Model Patches

How do Humans Process AI-generated Hallucination Contents: a Neuroimaging Study

Search-E1: Self-Distillation Drives Self-Evolution in Search-Augmented Reasoning

Position: The Turing-Completeness of Real-World Autoregressive Transformers Relies Heavily on Context Management

NGM: A Plug-and-Play Training-Free Memory Module for LLMs

EXG: Self-Evolving Agents with Experience Graphs

ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding

POLAR-Bench: A Diagnostic Benchmark for Privacy-Utility Trade-offs in LLM Agents

Active Evidence-Seeking and Diagnostic Reasoning in Large Language Models for Clinical Decision Support

Learning Bilevel Policies over Symbolic World Models for Long-Horizon Planning

Can AI Make Conflicts Worse? An Alignment Failure in LLM Deployment Across Conflict Contexts

AMEL: Accumulated Message Effects on LLM Judgments

CLORE: Content-Level Optimization for Reasoning Efficiency

Is VLA Reasoning Faithful? Probing Safety of Chain-of-Causation

What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents

A2RBench: An Automatic Paradigm for Formally Verifiable Abstract Reasoning Benchmark Generation

CatalyticMLLM: A Graph-Text Multimodal Large Language Model for Catalytic Materials

Beyond Rational Illusion: Behaviorally Realistic Strategic Classification

AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignment

Reasoning Before Diagnosis: Physician-Inspired Structured Thinking for ECG Classification

Actionable World Representation

LinAlg-Bench: A Forensic Benchmark Revealing Structural Failure Modes in LLM Mathematical Reasoning

Probabilistic Tiny Recursive Model

Explainable Wastewater Digital Twins: Adaptive Context-Conditioned Structured Simulators with Self-Falsifying Decision Support

SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects

Responsible Agentic AI Requires Explicit Provenance

Visualizing the Invisible: Generative Visual Grounding Empowers Universal EEG Understanding in MLLMs

Embedding by Elicitation: Dynamic Representations for Bayesian Optimization of System Prompts

Implicit Safety Alignment from Crowd Preferences

PALS: Power-Aware LLM Serving for Mixture-of-Experts Models

Latent Heuristic Search: Continuous Optimization for Automated Algorithm Design

Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?

Reconciling Contradictory Views on the Effectiveness of SFT in LLMs: An Interaction Perspective

What Counts as AI Sycophancy? A Taxonomy and Expert Survey of a Fragmented Construct

DocOS: Towards Proactive Document-Guided Actions in GUI Agents

Skill Weaving: Efficient LLM Improvement via Modular Skillpacks

Conflict-Resilient Multi-Agent Reasoning via Signed Graph Modeling

LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems

ArborKV: Structure-Aware KV Cache Management for Scaling Tree-based LLM Reasoning

Deterministic Event-Graph Substrates as World Models for Counterfactual Reasoning

Minimax Optimal Variance-Aware Regret Bounds for Multinomial Logistic MDPs

FLUID: From Ephemeral IDs to Multimodal Semantic Codes for Industrial-Scale Livestreaming Recommendation

Whispers in the Noise: Surrogate-Guided Concept Awakening via a Multi-Agent Framework

IdleSpec: Exploiting Idle Time via Speculative Planning for LLM Agents

Pseudocode-Guided Structured Reasoning for Automating Reliable Inference in Vision-Language Models

DecisionBench: A Benchmark for Emergent Delegation in Long-Horizon Agentic Workflows

Evidence-Grounded Frontier Mapping and Agentic Hypothesis Generation in Nanomedicine

\ECUAS{n}: A family of metrics for principled evaluation of uncertainty-augmented systems

Dynamics of collective creativity in AI art competitions

ShopGym: An Integrated Framework for Realistic Simulation and Scalable Benchmarking of E-Commerce Web Agents

Prediction of Challenging Behaviors Associated with Profound Autism in a Classroom Setting Using Wearable Sensors

Cross-domain benchmarks reveal when coordinated AI agents improve scientific inference from partial evidence

AnchorDiff: Topology-Aware Masked Diffusion with Confidence-based Rewriting for Radiology Report Generation

Neurosymbolic Learning for Inference-Time Argumentation

Harnessing AI for Inverse Partial Differential Equation Problems: Past, Present, and Prospects

GraphMind: From Operational Traces to Self-Evolving Workflow Automation

AI for Auto-Research: Roadmap & User Guide

Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDP

Scalable Environments Drive Generalizable Agents

SCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational Science

QQJ: Quantifying Qualitative Judgment for Scalable and Human-Aligned Evaluation of Generative AI

Skim: Speculative Execution for Fast and Efficient Web Agents

Meta-Soft: Leveraging Composable Meta-Tokens for Context-Preserving KV Cache Compression

DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEG

OCCAM: Open-set Causal Concept explAnation and Ontology induction for black-box vision Models

Causal Intervention-Based Memory Selection for Long-Horizon LLM Agents

SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents

Self-supervised Hierarchical Visual Reasoning with World Model

Trace2Skill: Verifier-Guided Skill Evolution for Long-Context EDA Agents

Unlocking Proactivity in Task-Oriented Dialogue

Memory-Augmented Reinforcement Learning Agent for CAD Generation

ST-SimDiff: Balancing Spatiotemporal Similarity and Difference for Efficient Video Understanding with MLLMs

The Impact of AI Usage and Informativeness on Skill Development in Logical Reasoning

MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization

Divergence-Suppressing Couplings for Rectified Flow

Interaction Locality in Hierarchical Recursive Reasoning

Spreadsheet-RL: Advancing Large Language Model Agents on Realistic Spreadsheet Tasks via Reinforcement Learning

ScreenSearch: Uncertainty-Aware OS Exploration

TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning

Attention-Guided Reward for Reinforcement Learning-based Jailbreak against Large Reasoning Models

Interference-Aware Multi-Task Unlearning

AtelierEval: Agentic Evaluation of Humans & LLMs as Text-to-Image Prompters

Progressive Autonomy as Preference Learning: A Formalization of Trust Calibration for Agentic Tool Use

PRISM: A Benchmark for Programmatic Spatial-Temporal Reasoning

AutoRPA: Efficient GUI Automation through LLM-Driven Code Synthesis from Interactions

Prior Knowledge or Search? A Study of LLM Agents in Hardware-Aware Code Optimization

TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks

Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical Planning

CAM-Bench: A Benchmark for Computational and Applied Mathematics in Lean

MetaCogAgent: A Metacognitive Multi-Agent LLM Framework with Self-Aware Task Delegation

Learn-by-Wire Training Control Governance: Bounded Autonomous Training Under Stress for Stability and Efficiency

The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems

A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM Agents

STRIDE: A Self-Reflective Agent Framework for Reliable Automatic Equation Discovery

RAG-based EEG-to-Text Translation Using Deep Learning and LLMs

Evaluating Deep Research Agents on Expert Consulting Work: A Benchmark with Verifiers, Rubrics, and Cognitive Traps

SimGym: A Framework for A/B Test Simulation in E-Commerce with Traffic-Grounded VLM Agents

Position: A Three-Layer Probabilistic Assume-Guarantee Architecture Is Structurally Required for Safe LLM Agent Deployment

SGR-Bench: Benchmarking Search Agents on State-Gated Retrieval

Generative Auto-Bidding with Unified Modeling and Exploration

Generalization or Memorization? Brittleness Testing for Chess-Trained Language Models

Beyond the Cartesian Illusion: Testing Two-Stage Multi-Modal Theory of Mind under Perceptual Bottlenecks

Planning in the LLM Era: Building for Reliability and Efficiency

AOP-Wiki EMOD 3.0: Data Model Expansions and Content Evaluation Framework for Using Agentic AI to Improve Integration between AOPs and New Approach Methodologies (NAMs)

SAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative Recommendation

Toward AI VIS Co-Scientists: A General and End-to-End Agent Harness for Solving Complex Data Visualization Tasks

Reasoners or Translators? Contamination-aware Evaluation and Neuro-Symbolic Robustness in Tax Law

FORGE: Self-Evolving Agent Memory With No Weight Updates via Population Broadcast

Can Large Language Models Revolutionize Survey Research? Experiments with Disaster Preparedness Responses

LACO: Adaptive Latent Communication for Collaborative Driving

CBT-Audio: Evaluating Audio Language Models for Patient-Side Distress Intensity Estimation in CBT Session Recordings

EngiAI: A Multi-Agent Framework and Benchmark Suite for LLM-Driven Engineering Design

ScenePilot: Controllable Boundary-Driven Critical Scenario Generation for Autonomous Driving

Scaling Observation-aware Planning in Uncertain Domains

Evaluating the Utility of Personal Health Records in Personalized Health AI

Pairwise Preference Reward and Group-Based Diversity Enhancement for Superior Open-Ended Generation

AgentAtlas: Beyond Outcome Leaderboards for LLM Agents

Confirming Correct, Missing the Rest: LLM Tutoring Agents Struggle Where Feedback Matters Most