Artificial Intelligence Paper Rankings

AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation

Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure

Why LLMs Fail at Causal Discovery and How Interventional Agents Escape

Entropy Distribution as a Fingerprint for Hallucinations in Generative Models

Calibrating Conservatism for Scalable Oversight

Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases

Formalizing Mathematics at Scale

When Context Flips, Safety Breaks: Diagnosing Brittle Safety in Aligned Language Models

RULER: Representation-Level Verification of Machine Unlearning

DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes

SIA: Self Improving AI with Harness & Weight Updates

Detecting Is Not Resolving: The Monitoring Control Gap in Retrieval Augmented LLMs

CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents

What Makes Chain-of-Thought Work at Probe Time? Local Co-occurrence Rather Than Global Derivation

Learning to Search and Searching to Learn for Generalization in Planning

LLM-Evolved Domain-Independent Heuristics for Symbolic AI Planning

The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure

The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Retrieved Context

Your Agents Are Aging Too: Agent Lifespan Engineering for Deployed Systems

GRASP: Gated Regression-Aware Skill Proposer for Self-Improving LLM Agents

Human-like in-group bias in instruction-tuned language model agents

Is Agent Memory a Database? Rethinking Data Foundations for Long-Term AI Agent Memory

The Curse of Helpfulness: Inverse Scaling Law in Robustness to Distractor Instructions via DistractionIF

Mind-Omni: A Unified Multi-Task Framework for Brain-Vision-Language Modeling via Discrete Diffusion

The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence

Voluntary Collusion with Secret Tools in Competing LLM Agents

PassNet: Scaling Large Language Models for Graph Compiler Pass Generation

CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning

AIBuildAI-2: A Knowledge-Enhanced Agent for Automatically Building AI Models

Credit Assignment with Resets in Language Model Reasoning

LACUNA: Safe Agents as Recursive Program Holes

When and How Human Curation Backfires: Preference Alignment under Multi-Model Self-Consuming Loop

Quantifying and Optimizing Simplicity via Polynomial Representations

Battery-Sim-Agent: Leveraging LLM-Agent for Inverse Battery Parameter Estimation

PolyFusionAgent: A Multimodal Foundation Model and Autonomous AI Assistant for Polymer Property Prediction and Inverse Design

UnityMAS-O: A General RL Optimization Framework for LLM-Based Multi-Agent Systems

Better Accuracies, Worse Reasoning: A Step-Level Audit of Medical Chain-of-Thought Distillation

Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training

Plant, Persist, Trigger: Sleeper Attack on Large Language Model Agents

Robust and Efficient Guardrails with Latent Reasoning

CaMBRAIN: Real-time, Continuous EEG Inference with Causal State Space Models

OpenURMA: A Clean-Room Open Implementation of the Unified Bus Protocol

MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models

Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems

LaneRoPE: Positional Encoding for Collaborative Parallel Reasoning and Generation

AI Cartography: Mapping the Latent Landscape of AI Benchmark Ecosystems

Demystifying Data Organization for Enhanced LLM Training

Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents

Composition Collapse: Stable Factual Knowledge Does Not Imply Compositional Reasoning

Orthogonal Concept Erasure for Diffusion Models

DeepTool: Scaling Interleaved Deliberation in Tool-Integrated Reasoning via Process-Supervised Reinforcement Learning

Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning

Behavioural Analysis of Alignment Faking

Thinking as Compression: Your Reasoning Model is Secretly a Context Compressor

LiveBrowseComp: Are Search Agents Searching, or Just Verifying What They Already Know?

CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists

From Static Context to Calibrated Interactive RL: Mitigating Distribution Shift in Multi-turn Dialogue with Aligned Simulator

Harness-Bench: Measuring Harness Effects across Models in Realistic Agent Workflows

Bridging the Detection-to-Abstention Gap in Reasoning Models under Insufficient Information

Beyond a Single Direction: Chain-of-Thought Disrupts Simple Steering of Refusal

Compass: Navigating Global Marine Lead Data Integration through Expert-Guided LLM Agent

ReasonOps: Operator Segmentation for LLM Reasoning Traces

SafeMed-R1: Clinician-Audited Safety and Ethics Alignment for Medical Large Language Models

A Unified Framework for the Evaluation of LLM Agentic Capabilities

MemCog: From Memory-as-Tool to Memory-as-Cognition in Conversational Agents

Mechanistically Interpreting the Role of Sample Difficulty in RLVR for LLMs

StructBreak: Structural Cognitive Overload-Induced Safety Failures in MLLMs

Provably Secure Agent Guardrail

MUSE: Benchmarking Manufacturable, Functional, and Assemblable Text-to-CAD Generation

Advancing Creative Physical Intelligence in Large Multimodal Models

ZipRL: Adaptive Multi-Turn Context Compression with Hindsight Response Replay

On the Origin of Synthetic Information by Means of Steganographic Inheritance

Continual Model Routing in Evolving Model Hubs

PRO-CUA: Process-Reward Optimization for Computer Use Agents

Position: AI Safety Requires Effective Controllability

Which Changes Matter? Towards Trustworthy Legal AI via Relevance-Sensitive Evaluation and Solver-Grounded Reasoning

MolLingo: Molecule-Native Representations for LLM-Powered Scientific Agents

Can LLMs Introspect? A Reality Check

Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy

Do Clinical Models Change Treatment Decisions?

Localizing Input Uncertainty Quantification for Large Language Models via Shapley Values

From Fact Overwriting to Knowledge Evolution: Causal Editing via On-Policy Self-Distillation

EvoMD-LLM: Learning the Language of Species Evolution in Reactive Molecular Dynamics

Croissant Tasks: A Metadata Format for Reproducible Machine Learning Evaluations

Planning with the Views via Scene Self-Exploration

SchGen: PCB Schematic Generation with Semantic-Grounded Code Representations

Geometry of Human Perceptual Domains Emerges Transiently in LLM Representations

From Accounting to Coordination: A Virtual Water-Aware Electricity-Computation-Water Nexus Framework for Data Center Dispatch

MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research

Aligned but Fragile: Enhancing LLM Safety Robustness via Zeroth-Order Optimization

Conformal Certification of Reasoning Trace Prefixes

AGORA: Adapter-Grounded Observation-Action Retention for Inference-Free Prompt Compression in LLM Agents

Beyond Consensus: Trace-Level Synthesis in Mixture of Agents

Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation Learning

PEAM: Parametric Embodied Agent Memory through Contrastive Internalization of Experience in Minecraft

Reasoning Matters: Mitigate Hallucination in Multimodal Large Reasoning Models via Reasoning-Conditioned Preference Optimization

Learning When to Optimize: Verified Optimization Skills from Expert GPU-Kernel Lineages

Locally Coherent, Globally Incoherent: Bounding Compositional Incoherence in Multi-Component LLM Agents

TRACER: Turn-level Regret Matching with Inner Reinforcement Credit for Cooperative Multi-LLM Reasoning

JobBench: Aligning Agent Work With Human Will

CODESKILL: Learning Self-Evolving Skills for Coding Agents

Insuring Every Action: An Authority Frontier Framework for Runtime Actuarial Control of Autonomous AI Agents

Double-Edged Sword or Sharp Tool? Designing and Evaluating Triadic LLM-Teacher Collaboration for K-12 Writing at Scale

Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation

KairosAgent: Agentic Time Series Forecasting with Fused Semantic Reasoning

Verifiable Benchmarking of Long-Horizon Spatial Biology

Look on Demand: A Cognitive Scheduling Framework for Visual Evidence Acquisition in Multimodal Reasoning

NaRA: Noise-Aware LoRA for Parameter-Efficient Fine-Tuning of Diffusion LLMs

Anchor: Mitigating Artifact Drift in Agent Benchmark Generation

Prompt Codebooks: Discrete Compositional Optimization for Language Model Instruction Refinement

Certified Policy Optimisation for Nested Causal Bandits via PAC-Bayes Risk

Personalizing Embodied Multimodal Large Language Model Agents over Long-term User Interactions

Retrying vs Resampling in AI Control

A Policy-Driven Runtime Layer for Agentic LLM Serving

Harmonizing Real-Time Constraints and Long-Horizon Reasoning: An Asynchronous Agentic Framework for Dynamic Scheduling

Plan Before Search: Search Agents Need Plan

Measuring Progress Toward AGI: A Cognitive Framework

From Model Scaling to System Scaling: Scaling the Harness in Agentic AI

Beyond Attack Success Rate: Temporal Logit Observability for LLM Safety Failures

OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories

MEMENTO: Leveraging Web as a Learning Signal for Low-Data Domains

ParaTool: Shifting Tool Representations from Context to Parameters

Multi-Adapter Representation Interventions via Energy Calibration

Accelerating Constrained Decoding with Token Space Compression

Confidence-Orchestrated Self-Evolution against Uncertain LLM Feedback

Automatic Layer Selection for Hallucination Detection

Can Broad Biomedical Knowledge be Contextualized into Scenario-Grounded Propositions?

MemFail: Stress-Testing Failure Modes of LLM Memory Systems

Tree of Thoughts as a Classical Heuristic Search Problem: Formal Foundations and Design Patterns

VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions

Deconstructing Spatial Complexity: Hierarchical Decomposition for LLM Spatial Reasoning

Back to Parsimonious Latents: Learning Task-Centric World Models from Visual Foundations

Towards Faithful Agentic XAI: A Verification Method and an Open-World Benchmark for Better Model Faithfulness

The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion Models

MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs

Where Rollouts Begin: Low-Load, High-Leverage First-Token Diversification for RLVR

SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search

GTA: Generating Long-Horizon Tasks for Web Agents at Scale

EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents

Do Agents Think Deeper? A Mechanistic Investigation of Layer-Wise Dynamics in Sequential Planning

MuCRASP: Multimodal Chain-of-thought Reasoning aware Structured Pruning

Satisfiability Solving with LLMs: A Matched-Pair Evaluation of Reasoning Capability

Mind the Tool Failures: Achieving Synergistic Tool Gains for Medical Agents

ProjectionBench: Evaluating Scientific Hypothesis Generation in LLMs Under Progressive Information Disclosure

On the Geometry of Games and their Solvers

BenchTrace: A Benchmark for Testing Reflection Ability and Controlled Evolution in LLM Agents

Revealing Algorithmic Deductive Circuits for Logical Reasoning

Uncertainty Reasoning with Large Language Models for Explainable Disease Diagnosis

HRBench: Benchmarking and Understanding Thinking-Mode Switch Strategies in Hybrid-Reasoning LLMs

OmniMatBench: A Human-Calibrated Multimodal Reasoning Benchmark Across 19 Materials Science Subfields

Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training Traces

A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks

Harnessing non-adversarial robustness in large language models

MedGuideX: Internalizing Decision Logic from Executable Guidelines into Large Language Models for Clinical Reasoning

Relevant Is Not Warranted: Evidence-Force Calibration for Cited RAG

Scaling, Benchmarking, and Reasoning of Vision-Language Agents for Mobile GUI Navigation

Asking Is Not Enough: Protocol Sensitivity in LLM Confidence Calibration

Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations

When Should Models Change Their Minds? Contextual Belief Management in Large Language Models

Indexing the Unreadable: LLM-Native Recursive Construction and Search of Service Taxonomies

Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Question Answering

DREAM-R: Multimodal Speculative Reasoning with RL-Based Refined Drafting, Precise Verification, and Fully Parallel Execution

Reliable Reasoning with Large Language Models via Preference-Based Maximum Satisfiability

From Knowing to Doing: A Memory-Controlled Benchmark for LLM Trading Agents on Stock Markets

Bandwidth-Efficient and Privacy-Preserving Edge-Cloud Many-to-Many Speech Translation

Teaching Values to Machines: Simulating Human-Like Behavior in LLMs

LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs

RAISE: RAG Design as an Architecture Search Problem

VeriTrip: A Verifiable Benchmark for Travel Planning Agents over Unstructured Web Corpora

You Live More Than Once: Towards Hierarchical Skill Meta-Evolving

Behind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network

Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments

Towards end-to-end LLM-based censoring-aware survival analysis

OmniToM: Benchmarking Theory of Mind in LLMs via Explicit Belief Modeling

$D^2$-Monitor: Dynamic Safety Monitoring for Diffusion LLMs via Hesitation-Aware Routing

Generating Robust Portfolios of Optimization Models using Large Language Models

Whose Alignment? Comparing LLM Process Alignment Across Diverse Organizational Decision Contexts

From XXLTraffic to EvoXXLTraffic: Scaling Traffic Forecasting to Sensor-Evolving Networks

VitalAgent: A Tool-Augmented Agent for Reactive and Proactive Physiological Monitoring over Wearable Health Data

Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World

A Fixed-Budget, Cluster-Aware Standard for LLM-as-a-Judge Evaluation: A Multi-Hop RAG Stress Test

BlazeEdit: Generalist Image Editing on Mobile Devices with Image-to-Image Diffusion Models

Intelligence as Managed Autonomy: Failure, Escalation, and Governance for Agentic AI Systems

Moment-KV: Momentum-Based Decode-Time KV Cache Compression for Long Generation

Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models

AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions

Natural Language Query to Configuration for Retrieval Agents

AlphaTransit: Learning to Design City-scale Transit Routes

CIVIC: End-to-End Sequence Compactness for Efficient Vision-Language Models

StepOPSD: Step-Aware Online Preference Distillation for Agent Reinforcement Learning

Xetrieval: Mechanistically Explaining Dense Retrieval

Why Specialist Models Still Matter: A Heterogeneous Multi-Agent Paradigm for Medical Artificial Intelligence

SkillGrad: Optimizing Agent Skills Like Gradient Descent

ProvMind: Provenance-grounded reasoning for materials synthesis

Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection

BatteryMFormer: Multi-level Learning for Battery Degradation Trajectory Forecasting

VeriTrace: Evolving Mental Models for Deep Research Agents