Paper2Code archive

Paper archive page 44

Page 44 of 129. Links match the indexable papers sitemap inventory.

300 canonical paper links on this archive page.

VICBench: A Multi-Language Benchmark for Code Vulnerability Detection
arxiv-2608.12246 Sparse Blocked context only

Aug 12, 2026
Information Abundance Paradox: Long-Context Training Undermines Parametric Knowledge
arxiv-2608.12218 Sparse Blocked context only

Aug 12, 2026
Generation as Auxiliary Supervision: Enhancing Visual Understanding at Zero Inference Overhead via Decoupled Embedding Prediction
arxiv-2608.12209 Sparse Blocked context only

Aug 12, 2026
Who Thinks Best Depends on How Long You Let Them: Budget-Dependent Rankings in LLM Evaluation
arxiv-2608.12150 Sparse Blocked context only

Aug 12, 2026
Benchmarking Trustworthiness of SLMs: Pre-trained vs. Compressed
arxiv-2608.11981 Sparse Blocked context only

Aug 12, 2026
Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill
arxiv-2608.11924 Direct Blocked context only

Aug 12, 2026
Large Language Models Can Follow Instructions, But Not Many at Once: Phase Transitions in Compositional Constraint Satisfaction
arxiv-2608.12426 Sparse Blocked context only

Aug 12, 2026
Total Recall at What Cost? Benchmarking the Serving Cost of Agentic Memory Systems
arxiv-2608.11879 Sparse Blocked context only

Aug 12, 2026
ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM-based Agents
arxiv-2608.11878 Sparse Blocked context only

Aug 12, 2026
LookBack: Where and How to Score LVLM Responses via Visual Reference Usage
arxiv-2608.11847 Sparse Blocked context only

Aug 12, 2026
Quantifying the Relationship Between Clinical Safety and Environmental Impact in Therapeutic LLMs
arxiv-2608.11830 Sparse Blocked context only

Aug 12, 2026
Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling
arxiv-2608.11829 Sparse Blocked context only

Aug 12, 2026
How China-Origin Vision-Language Models Move from Refusal to Reframing in State Alignment
arxiv-2608.11816 Sparse Blocked context only

Aug 12, 2026
GRPO for Financial Advice Generation: Outperforming Commercial LLMs under CATE Evaluation
arxiv-2608.11787 Sparse Blocked context only

Aug 12, 2026
Language-Conditional Dequantization: Recovering What Quantization Steals from Non-English Languages
arxiv-2608.11786 Sparse Blocked context only

Aug 12, 2026
Diagnosis Before Recovery: Turning Agent Failures into Selective Self-Correction
arxiv-2608.11772 Sparse Blocked context only

Aug 12, 2026
LiveAnimate: Stable Long-Form Streaming Human Animation in Real-Time
arxiv-2608.11745 Sparse Blocked context only

Aug 12, 2026
Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Models
arxiv-2608.11742 Sparse Blocked context only

Aug 12, 2026
When the API Speaks the Wrong Language: Revisiting Post-Training for Multilingual Tool Use
arxiv-2608.11715 Sparse Blocked context only

Aug 12, 2026
Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing
arxiv-2608.11660 Sparse Blocked context only

Aug 12, 2026
Who Would You Vote For? Auditing Political Alignment in LLMs: An Italian Case-Study
arxiv-2608.11649 Sparse Blocked context only

Aug 12, 2026
Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs
arxiv-2608.11624 Sparse Blocked context only

Aug 12, 2026
MBA: Multimodal Benchmark and Agents for Real-World Business Ideation
arxiv-2608.11616 Sparse Blocked context only

Aug 12, 2026
VideoGAIA: A Benchmark for General AI Assistants on Agentic Video Understanding
arxiv-2608.14718 Sparse Blocked context only

Aug 12, 2026
Reinforcing Step-level Reasoning for Effective Self-Correction in LLMs
arxiv-2608.11573 Sparse Blocked context only

Aug 12, 2026
Beyond Single-Turn Confidence: Trajectory-Adapted Uncertainty Quantification for LLM Agents
arxiv-2608.11552 Sparse Blocked context only

Aug 12, 2026
Principal Trait Analysis: Towards Deriving "Skills" in Human-AI Collaboration
arxiv-2608.11460 Sparse Blocked context only

Aug 11, 2026
Benchmarking LLM Judges for Mobile Agent Evaluation
arxiv-2608.11434 Sparse Blocked context only

Aug 11, 2026
When Self-Consistency Backfires: Majority Vote Hurts the Majority of Hard Science Problems for Small LLMs
arxiv-2608.11403 Sparse Blocked context only

Aug 11, 2026
Self-Evolving Embodied Agents via Skill-Harness Evolution
arxiv-2608.11350 Sparse Blocked context only

Aug 11, 2026
ReRound: Reconstructive Rounding to Resolve Midpoint Ambiguity in Calibration-Free LLM Quantization
arxiv-2608.11045 Sparse Blocked context only

Aug 11, 2026
VibeLifeBench: Can Your Life Agent Be Proactive and Persistent in a Living World?
arxiv-2608.10875 Sparse Blocked context only

Aug 11, 2026
UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations
arxiv-2608.10835 Sparse Blocked context only

Aug 11, 2026
Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation
arxiv-2608.10812 Sparse Blocked context only

Aug 11, 2026
SPIEval: Evaluating Large Language Models as Mobile Assistants over Scattered Personal Information
arxiv-2608.10692 Direct Blocked context only

Aug 11, 2026
DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation
arxiv-2608.10636 Sparse Blocked context only

Aug 11, 2026
InSight-doc: Agentic Visual Perception for Long-Document Understanding
arxiv-2608.10628 Curated Related Blocked context only

Aug 11, 2026
Agent Safety Should Be a Runtime Contract
arxiv-2608.11274 Sparse Blocked context only

Aug 11, 2026
SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models
arxiv-2608.10538 Sparse Blocked context only

Aug 11, 2026
From Reasoning Depth to Reasoning Breadth: Evaluating Multi-Point Associative Reasoning in Large Language Models
arxiv-2608.10444 Sparse Blocked context only

Aug 11, 2026
Power law graph attention: exact generalization of scaled dot-product attention, empirical collapse at inference
arxiv-2608.10288 Sparse Blocked context only

Aug 10, 2026
Multimodal Model Diffing for Feature Discovery and Control
arxiv-2608.09928 Sparse Blocked context only

Aug 10, 2026
Decoding-Level Taboo: A Diagnostic Stress Test for LLM Robustness
arxiv-2608.09900 Sparse Blocked context only

Aug 10, 2026
Stealing Reasoning Traces from Proprietary LLM APIs
arxiv-2608.09867 Sparse Blocked context only

Aug 10, 2026
Parameter Exploration for RLVR via Variational Learning
arxiv-2608.09805 Sparse Blocked context only

Aug 10, 2026
Matryoshka Language Model Suites
arxiv-2608.09703 Sparse Blocked context only

Aug 10, 2026
TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability
arxiv-2608.09538 Sparse Blocked context only

Aug 10, 2026
Learning Preference Adaptation for Large Language Model Personalization via Verbal Reinforcement Learning
arxiv-2608.09507 Sparse Blocked context only

Aug 10, 2026
Intent Speaks Louder: Controllable User Simulation Beyond Response Imitation
arxiv-2608.09420 Sparse Blocked context only

Aug 10, 2026
DREAM Technical Report
arxiv-2608.09408 Sparse Blocked context only

Aug 10, 2026
Motif 3: Technical Report
arxiv-2608.09119 Sparse Blocked context only

Aug 10, 2026
Evo-Bench: Can Language Models Improve Agent Harness?
arxiv-2608.09096 Sparse Blocked context only

Aug 10, 2026
PolicyKG: An Agentic LLM Pipeline for Translating Institutional Policies into SHACL Knowledge Graphs
arxiv-2608.09028 Sparse Blocked context only

Aug 10, 2026
Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving
arxiv-2608.08910 Sparse Blocked context only

Aug 9, 2026
Full-bandwidth transformer
arxiv-2608.08888 Direct Blocked context only

Aug 9, 2026
SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic Verification
arxiv-2608.08786 Sparse Blocked context only

Aug 9, 2026
Can We Optimize the Performance-Carbon Emission Break-Even Point?: The Quest for Greener LLMs
arxiv-2608.08744 Sparse Blocked context only

Aug 9, 2026
UniSpace: Unified Visual Representation and Scalable Multimodal Modeling
arxiv-2608.08676 Sparse Blocked context only

Aug 9, 2026
CuteTTS: Efficient and High-Quality Speech Synthesis via Autoregressive Modeling of Continuous Latents
arxiv-2608.08638 Sparse Blocked context only

Aug 9, 2026
VectraYX-Vision-1B: A Sub-2B Spanish/LATAM Cybersecurity Vision-Language Model with Structured Visual Reasoning and Native Tool Use
arxiv-2608.08477 Sparse Blocked context only

Aug 9, 2026
Can LLM Agents Stick to the Script? A Benchmark for Long-Horizon Consistency in Interactive Narratives
arxiv-2608.08160 Sparse Blocked context only

Aug 8, 2026
NeuPAT: Neuron-aware Plasticity Allocation Tuning for Language-Preserving MLLMs
arxiv-2608.08107 Sparse Blocked context only

Aug 8, 2026
OasisKV: Scaling In-Decode KV Cache Beyond HBM with Lookahead Sparse Prefetching
arxiv-2608.08097 Sparse Blocked context only

Aug 8, 2026
Evidence-RL: Towards Evidence-intensive Visual Reasoning
arxiv-2608.08021 Sparse Blocked context only

Aug 8, 2026
ResidencyRL: Reinforcement Learning in Simulated Clinical Environments
arxiv-2608.07418 Sparse Blocked context only

Aug 7, 2026
Mendel Gödel Machine: Recursive Self-Improving Coding Agents via Comparative Evolution
arxiv-2608.07645 Sparse Blocked context only

Aug 7, 2026
$A^2E$ : An End-to-End Agent Auditing Engine
arxiv-2608.07346 Sparse Blocked context only

Aug 7, 2026
An AI4AI Framework for Visual Token Pruning
arxiv-2608.07193 Sparse Blocked context only

Aug 7, 2026
Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory
arxiv-2608.07169 Sparse Blocked context only

Aug 7, 2026
Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection
arxiv-2608.06865 Sparse Blocked context only

Aug 7, 2026
Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence
arxiv-2608.06756 Sparse Blocked context only

Aug 7, 2026
AtlasVLA: Persistent World-Ego State Modeling for Vision-Language-Action Models
arxiv-2608.06729 Sparse Blocked context only

Aug 7, 2026
Characterizing the Quality Profile of AI-Generated C++ in Production
arxiv-2608.06640 Sparse Blocked context only

Aug 6, 2026
Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After Life Events
arxiv-2608.06485 Sparse Blocked context only

Aug 6, 2026
DyPES-VLA: Learning Shared Dynamics Priors and Embodiment-Specific Control for Cross-Embodiment Manipulation
arxiv-2608.06374 Sparse Blocked context only

Aug 6, 2026
On-Policy Self-Distillation without Any Supervision
arxiv-2608.06296 Sparse Blocked context only

Aug 6, 2026
MASS: Multiplayer World Models with Authoritative Shared State
arxiv-2608.06257 Sparse Blocked context only

Aug 6, 2026
EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
arxiv-2608.06197 Sparse Blocked context only

Aug 6, 2026
PaDoc: Layout-Grounded Parallel Decoding for Document Parsing
arxiv-2608.06146 Sparse Blocked context only

Aug 6, 2026
Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval
arxiv-2608.06060 Sparse Blocked context only

Aug 6, 2026
OneEmo: A Unified Multimodal Reasoning Model for Emotion Perception, Understanding, and Interaction
arxiv-2608.06013 Curated Related Blocked context only

Aug 6, 2026
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning
arxiv-2608.05987 Direct Blocked context only

Aug 6, 2026
Energy-Guided Flow Matching
arxiv-2608.05811 Sparse Blocked context only

Aug 6, 2026
On-Policy Delta Distillation for Multilingual Math Reasoning
arxiv-2608.05802 Sparse Blocked context only

Aug 6, 2026
KVAE: Family of Tokenizers for Multimodal Generative Models
arxiv-2608.05798 Sparse Blocked context only

Aug 6, 2026
Activity Frames: Deterministic Screen-Activity Compilation for Agent Memory and Replay
arxiv-2608.05784 Direct Blocked context only

Aug 6, 2026
ChronoVision: Temporal Reasoning via Latent State Reconstruction
arxiv-2608.05631 Sparse Blocked context only

Aug 6, 2026
SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries
arxiv-2608.05604 Sparse Blocked context only

Aug 6, 2026
EffectLearner: World-Aware Object-Effect Reasoning for Real-World Video Object Removal
arxiv-2608.05565 Sparse Blocked context only

Aug 6, 2026
Recursive Synthesis for Long-Horizon Terminal Tasks
arxiv-2608.05466 Sparse Blocked context only

Aug 5, 2026
EvoHarness-RL: Learning Runtime Harness Coordination for Self-Evolving Agents
arxiv-2608.05446 Sparse Blocked context only

Aug 5, 2026
World-to-Wrist: Task-Conditioned Future Wrist Modeling for Fine-Grained Robot Manipulation
arxiv-2608.05369 Sparse Blocked context only

Aug 5, 2026
SmartMage: Dynamic Modality Orchestration for 3D Scene Understanding
arxiv-2608.05137 Sparse Blocked context only

Aug 5, 2026
OPD-V: Visual On-Policy Self-Distillation with Modality Balance
arxiv-2608.05131 Sparse Blocked context only

Aug 5, 2026
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming
arxiv-2608.05108 Sparse Blocked context only

Aug 5, 2026
ABSeeker: Training Long-Horizon Search Agents via Answer-Backtracked Credit Assignment
arxiv-2608.05102 Sparse Blocked context only

Aug 5, 2026
WorldClaw: Agentic 3D Open-World Generation at Scale
arxiv-2608.05248 Direct Blocked context only

Aug 5, 2026
Poly-OPD: Heterogeneous Multi-Teacher On-Policy Distillation for Capability-Selectable Flow Models
arxiv-2608.04349 Sparse Blocked context only

Aug 5, 2026
CLIP-CC-Bench: Evaluating Paragraph-Level Video Descriptions in Video-Language Models
arxiv-2608.04302 Sparse Blocked context only

Aug 5, 2026
SIGNPOST-Bench: Benchmarking Text-Vision Conflict Resolution in Multimodal Large Language Models
arxiv-2608.04244 Sparse Blocked context only

Aug 4, 2026
MatrAIx: Simulating the World with 8.3 Billion Persona Agents
arxiv-2608.04205 Direct Blocked context only

Aug 4, 2026
TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning
arxiv-2608.04007 Sparse Blocked context only

Aug 4, 2026
OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents
arxiv-2608.05013 Sparse Blocked context only

Aug 4, 2026
Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent
arxiv-2608.03979 Direct Blocked context only

Aug 4, 2026
JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion
arxiv-2608.03974 Direct Blocked context only

Aug 4, 2026
ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct Reasoning
arxiv-2608.03972 Sparse Blocked context only

Aug 4, 2026
UniWorld-Design: From Pixel Generation to Layer-Native Design
arxiv-2608.03971 Sparse Blocked context only

Aug 4, 2026
Omega-S: A Functional Resilience Index for LLM Fine-Tuning
arxiv-2608.03887 Sparse Blocked context only

Aug 4, 2026
ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?
arxiv-2608.03874 Sparse Blocked context only

Aug 4, 2026
OmniPack: Unified Token Compression for Efficient Omni-modal Large Language Models
arxiv-2608.03812 Sparse Blocked context only

Aug 4, 2026
Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss
arxiv-2608.03796 Sparse Blocked context only

Aug 4, 2026
GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks
arxiv-2608.03764 Sparse Blocked context only

Aug 4, 2026
Agents Catching Agents: Shortcut Cascades and Benchmark Gaming in Clinical Multi-Agent Systems
arxiv-2608.03744 Sparse Blocked context only

Aug 4, 2026
When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation
arxiv-2608.03632 Sparse Blocked context only

Aug 4, 2026
SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs
arxiv-2608.03573 Sparse Blocked context only

Aug 4, 2026
LLaDA MoE v2: Scaling Mixture-of-Experts Diffusion Language Models
arxiv-2608.03457 Curated Related Blocked context only

Aug 4, 2026
DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces
arxiv-2608.03451 Sparse Blocked context only

Aug 4, 2026
Self-Evolving Coding Agents
arxiv-2608.03392 Sparse Blocked context only

Aug 4, 2026
iFAN: Inference-Aware Learning for Plain Mask Transformers
arxiv-2608.03216 Sparse Blocked context only

Aug 4, 2026
CURV: Enhancing Chart Understanding Through Curriculum Visual Grounded Reasoning
arxiv-2608.02833 Sparse Blocked context only

Aug 3, 2026
Better, Stronger, Faster, and Broader: Structured All-Mask Prediction for MLLM-Based Segmentation
arxiv-2608.02791 Sparse Blocked context only

Aug 3, 2026
WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity
arxiv-2608.02603 Sparse Blocked context only

Aug 3, 2026
AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling
arxiv-2608.02602 Sparse Blocked context only

Aug 3, 2026
Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing
arxiv-2608.02711 Direct Blocked context only

Aug 3, 2026
GradCuit: Credit-Assigned Gradient Flow Enables Robust and Interpretable Test-Time Latent Reasoning
arxiv-2608.02585 Sparse Blocked context only

Aug 3, 2026
What to Edit Next: Visually Aligned Image-Editing Follow-Up Suggestions in Conversational Systems
arxiv-2608.07565 Sparse Blocked context only

Aug 3, 2026
RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States
arxiv-2608.02508 Sparse Blocked context only

Aug 3, 2026
Shared Prefixes, Better Credit: Adaptive Routing for Multi-Agent Reasoning
arxiv-2608.02291 Sparse Blocked context only

Aug 3, 2026
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks
arxiv-2608.01964 Direct Blocked context only

Aug 3, 2026
PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning
arxiv-2608.01837 Sparse Blocked context only

Aug 3, 2026
DeepVoyager-VL: Incentivizing Vision-in-the-Loop Search for Long-Horizon Multimodal Agents
arxiv-2608.01827 Sparse Blocked context only

Aug 3, 2026
Interpretable MEG Decoding of Perceived Speech: Cortical Sources and the Stimulus Features That Drive Retrieval
arxiv-2608.01481 Sparse Blocked context only

Aug 2, 2026
FATE: Frame-Level Audio-Visual Temporal Embedding
arxiv-2608.01310 Sparse Blocked context only

Aug 2, 2026
3DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering
arxiv-2608.01185 Sparse Blocked context only

Aug 2, 2026
MiniWorld: Democratizing the Training of Video World Models from Scratch
arxiv-2608.01127 Sparse Blocked context only

Aug 2, 2026
FactorJEPA: Factorizing Monolithic Futures into Layout-Agent-Interaction Channels for Crowded and Chaotic Global South Urban Worlds
arxiv-2608.01049 Direct Blocked context only

Aug 2, 2026
Gaokerena: A Small Persian Medical Language Model Family
arxiv-2608.00932 Sparse Blocked context only

Aug 2, 2026
Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance
arxiv-2608.00782 Sparse Blocked context only

Aug 1, 2026
OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution
arxiv-2608.00677 Direct Blocked context only

Aug 1, 2026
Relax Within, Balance Across: Geometry-Guided Load Balancing for Vision-Language Mixture-of-Experts
arxiv-2608.00574 Sparse Blocked context only

Aug 1, 2026
Decoding Children's Gait Behavior
arxiv-2608.00371 Sparse Blocked context only

Aug 1, 2026
Verifier-Induced Support Reshaping in On-Policy Optimization
arxiv-2608.00220 Sparse Blocked context only

Jul 31, 2026
ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction
arxiv-2607.29677 Direct Blocked context only

Jul 31, 2026
AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?
arxiv-2608.00155 Sparse Blocked context only

Jul 31, 2026
DiffusionGemma Technical Report
arxiv-2608.00146 Sparse Blocked context only

Jul 31, 2026
Zero-Mem: Zero-Token Memory Operations for LLM Agents
arxiv-2607.29377 Sparse Blocked context only

Jul 31, 2026
Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning
arxiv-2607.29211 Sparse Blocked context only

Jul 31, 2026
DarwinX: Evolving Agent Harnesses Through Natural Selection
arxiv-2608.07545 Sparse Blocked context only

Jul 31, 2026
Evaluation-Verification Reward for Consistent Multi-Reference Image Editing
arxiv-2607.29025 Sparse Blocked context only

Jul 31, 2026
MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations
arxiv-2607.28956 Sparse Blocked context only

Jul 31, 2026
To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing
arxiv-2607.28887 Sparse Blocked context only

Jul 30, 2026
OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models
arxiv-2607.28609 Sparse Blocked context only

Jul 30, 2026
Beacon: Knowing When and How to Perform Agentic Visual Reasoning
arxiv-2607.28595 Sparse Blocked context only

Jul 30, 2026
$β$-OPSD: Deriving with Policy Optimization, Training with Self-Distillation
arxiv-2607.28582 Sparse Blocked context only

Jul 30, 2026
Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering
arxiv-2607.28568 Direct Blocked context only

Jul 30, 2026
ORCA-bench: How Ready Are Language Model Agents for Oncall?
arxiv-2607.28545 Sparse Blocked context only

Jul 30, 2026
Would You Walk to the Car Wash? Revealing the Salience Bias of Large Language Models in Commonsense Reasoning
arxiv-2607.28478 Sparse Blocked context only

Jul 30, 2026
Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations
arxiv-2607.28319 Sparse Blocked context only

Jul 30, 2026
Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents
arxiv-2607.28227 Direct Blocked context only

Jul 30, 2026
SKILL-KD: Contrastive Skill Distillation for LLM Agents
arxiv-2607.28048 Sparse Blocked context only

Jul 30, 2026
Flux-OPD: On-Policy Distillation with Evolving Contexts
arxiv-2607.28022 Sparse Blocked context only

Jul 30, 2026
$Σ$-Mem: An Online Reliability Memory for LLM-based Multi-Agent Systems
arxiv-2607.27958 Sparse Blocked context only

Jul 30, 2026
ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow
arxiv-2607.27924 Sparse Blocked context only

Jul 30, 2026
Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory
arxiv-2607.27919 Curated Related Blocked context only

Jul 30, 2026
Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation
arxiv-2607.27816 Sparse Blocked context only

Jul 30, 2026
Harness-G: A Graph-Structured Harness for Search Agents
arxiv-2607.27652 Sparse Blocked context only

Jul 30, 2026
MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models
arxiv-2607.27637 Sparse Blocked context only

Jul 30, 2026
TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM
arxiv-2607.27205 Direct Blocked context only

Jul 29, 2026
Can AI agents conduct open-ended AI research? Early evidence from two case studies
arxiv-2607.27191 Sparse Blocked context only

Jul 29, 2026
OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding
arxiv-2607.27155 Sparse Blocked context only

Jul 29, 2026
SecRespond: Benchmarking AI Agents for Real-World Post-Compromise Incident Response
arxiv-2607.26791 Direct Blocked context only

Jul 29, 2026
SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution
arxiv-2607.26784 Direct Blocked context only

Jul 29, 2026
See2Think: Do Multimodal Models Really Use Intermediate Visual States?
arxiv-2607.26769 Sparse Blocked context only

Jul 29, 2026
Metis: Memory Foundation Model
arxiv-2607.26760 Direct Blocked context only

Jul 29, 2026
Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control
arxiv-2607.26657 Sparse Blocked context only

Jul 29, 2026
BM25 Wins at Scale: A Scaling Study of Retrieval-Augmented Generation Paradigms
arxiv-2607.26497 Sparse Blocked context only

Jul 29, 2026
ExplainBench: Evaluating Code Explanations from Agents
arxiv-2607.26451 Sparse Blocked context only

Jul 29, 2026
Seeing or Knowing? Visual Context Sensitivity in Multimodal Large Language Models
arxiv-2607.26326 Sparse Blocked context only

Jul 28, 2026
StealthBench: Measuring Operational Stealth in Autonomous Offensive-Security Agents
arxiv-2607.26314 Sparse Blocked context only

Jul 28, 2026
INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models
arxiv-2607.26056 Direct Blocked context only

Jul 28, 2026
Wonder: Video World Model Done Better
arxiv-2607.26037 Sparse Blocked context only

Jul 28, 2026
MODUS: Decoder-Only Any-to-Any Modeling of Diverse Modalities
arxiv-2607.25948 Sparse Blocked context only

Jul 28, 2026
MemSFT: Mitigating Alignment Tax with an External Parametric Memory
arxiv-2607.25614 Sparse Blocked context only

Jul 28, 2026
CodeNib: A Multi-View Data System for Serving Repository Context to Coding Agents
arxiv-2607.25431 Direct Blocked context only

Jul 28, 2026
CAST: Game Solvers as Turn-Level Teachers for LLM Agents
arxiv-2607.25308 Sparse Blocked context only

Jul 28, 2026
VisualPatchWorld: Code World Models as Latent Structured Representations for Planning
arxiv-2607.25236 Sparse Blocked context only

Jul 28, 2026
Towards Robust Reinforcement Learning for Small-Scale Language Model Agents
arxiv-2607.25091 Sparse Blocked context only

Jul 27, 2026
ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding
arxiv-2607.24743 Sparse Blocked context only

Jul 27, 2026
The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation
arxiv-2607.24720 Sparse Blocked context only

Jul 27, 2026
Kimi K3: Open Frontier Intelligence
arxiv-2607.24653 Curated Related Blocked context only

Jul 27, 2026
Evidence Attribution in Visual Document Understanding without Coordinates or Region Labels
arxiv-2607.24651 Curated Related Blocked context only

Jul 27, 2026
LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding
arxiv-2607.24555 Sparse Blocked context only

Jul 27, 2026
From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search
arxiv-2607.24280 Sparse Blocked context only

Jul 27, 2026
FilmBench: A Film-Grade Benchmark for Cinematic Video Generation
arxiv-2607.24241 Sparse Blocked context only

Jul 27, 2026
Agent Retrieval Bench: Evaluating Repository Context Retrieval for Coding Agents
arxiv-2607.24882 Sparse Blocked context only

Jul 27, 2026
WorldDiT: A Unified Diffusion Architecture for World and Action Modeling
arxiv-2607.23909 Curated Related Blocked context only

Jul 27, 2026
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement
arxiv-2607.23802 Sparse Blocked context only

Jul 26, 2026
ZenGen: Social Mind for LLMs
arxiv-2607.23740 Curated Related Blocked context only

Jul 26, 2026
JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents
arxiv-2607.23588 Direct Blocked context only

Jul 26, 2026
UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models
arxiv-2607.23373 Sparse Blocked context only

Jul 25, 2026
Toward Automated Detection of Documentation Inconsistencies in Electronic Health Records
arxiv-2607.22954 Sparse Blocked context only

Jul 24, 2026
Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills
arxiv-2607.22529 Sparse Blocked context only

Jul 24, 2026
IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation
arxiv-2607.22375 Sparse Blocked context only

Jul 24, 2026
StateAct: Program State, before Pixels, for Long-Horizon Computer-Use Agents
arxiv-2607.22798 Sparse Blocked context only

Jul 24, 2026
Scaling Native Multimodal Pre-Training From Scratch
arxiv-2607.22043 Sparse Blocked context only

Jul 24, 2026
Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers
arxiv-2607.21594 Sparse Blocked context only

Jul 23, 2026
OpenForgeRL: Train Harness-native Agents in Any Environment
arxiv-2607.21557 Sparse Blocked context only

Jul 23, 2026
Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems
arxiv-2607.21503 Sparse Blocked context only

Jul 23, 2026
ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders
arxiv-2607.21217 Sparse Blocked context only

Jul 23, 2026
Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text
arxiv-2607.21072 Sparse Blocked context only

Jul 23, 2026
Sample-Efficient Learning from Agent Experience
arxiv-2607.21051 Sparse Blocked context only

Jul 23, 2026
Robostral Navigate
arxiv-2607.20785 Sparse Blocked context only

Jul 22, 2026
NVIDIA-labs OO Agents: Native Python Object-Oriented Agents
arxiv-2607.20709 Sparse Blocked context only

Jul 22, 2026
Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning
arxiv-2607.21653 Direct Blocked context only

Jul 22, 2026
SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPOD
arxiv-2607.20145 Sparse Blocked context only

Jul 22, 2026
G-MAD: A Game-Based Data Generation Framework for Multi-View RGB-T Aerial Object Detection
arxiv-2607.19942 Sparse Blocked context only

Jul 22, 2026
Are the Financial Reasoning from LLMs Credible? A Real World Test over Long-Horizon Statements
arxiv-2607.28661 Sparse Blocked context only

Jul 22, 2026
Multi-Head Attention Residuals
arxiv-2607.27230 Sparse Blocked context only

Jul 22, 2026
Trace: A Taxonomy-Guided Environment for Multidomain Visual Reasoning
arxiv-2607.19790 Sparse Blocked context only

Jul 22, 2026
Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking
arxiv-2607.19747 Sparse Blocked context only

Jul 22, 2026
SLPO: Scaling Latent Reasoning via a Surrogate Policy
arxiv-2607.19691 Sparse Blocked context only

Jul 22, 2026
Scaling Laws for Hypernetwork-Based Knowledge Injection in Large Language Models
arxiv-2607.19604 Sparse Blocked context only

Jul 21, 2026
Appearance Pointers -- Multimodal Region Control of Diffusion Transformers
arxiv-2607.19344 Curated Related Blocked context only

Jul 21, 2026
ISO: An RLVR-Native Optimization Stack
arxiv-2607.19331 Curated Related Blocked context only

Jul 21, 2026
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU
arxiv-2607.19191 Direct Blocked context only

Jul 21, 2026
Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers
arxiv-2607.19139 Sparse Blocked context only

Jul 21, 2026
Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing
arxiv-2607.19064 Sparse Blocked context only

Jul 21, 2026
Where Should Optimizer State Live? Tiered State Allocation for Memory-Efficient Mixture-of-Experts Training
arxiv-2607.19058 Sparse Blocked context only

Jul 21, 2026
H$^2$SD: Hybrid Hindsight Self-Distillation
arxiv-2607.18955 Sparse Blocked context only

Jul 21, 2026
AI Tour Meeting: Group Travel Planning by LLM Agents
arxiv-2607.18806 Sparse Blocked context only

Jul 21, 2026
AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents
arxiv-2607.18754 Direct Blocked context only

Jul 21, 2026
EduPanel: A Three-Agent LLM Judge for Teaching Videos -- Reliability, Complementarity, and Human Trust Calibration
arxiv-2607.18529 Sparse Blocked context only

Jul 20, 2026
SWE-Pruner Pro: The Coder LLM Already Knows What to Prune
arxiv-2607.18213 Sparse Blocked context only

Jul 20, 2026
AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report
arxiv-2607.18367 Direct Blocked context only

Jul 20, 2026
LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks
arxiv-2607.18110 Sparse Blocked context only

Jul 20, 2026
SciForma: Structure-Faithful Generation of Scientific Diagrams
arxiv-2607.18091 Sparse Blocked context only

Jul 20, 2026
WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting
arxiv-2607.18084 Direct Blocked context only

Jul 20, 2026
Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?
arxiv-2607.17986 Sparse Blocked context only

Jul 20, 2026
DiFA: Inference-Time Forward-Process Alignment for Diffusion Models
arxiv-2607.17972 Sparse Blocked context only

Jul 20, 2026
ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning
arxiv-2607.17599 Sparse Blocked context only

Jul 20, 2026
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs
arxiv-2607.17423 Curated Related Blocked context only

Jul 19, 2026
Distilled Reinforcement Learning for LLM Post-training
arxiv-2607.17247 Sparse Blocked context only

Jul 19, 2026
Poor Man's Agentic Modeling: Simulating Large LLM-Agent Societies on a Laptop
arxiv-2608.11215 Sparse Blocked context only

Jul 19, 2026
Environment-free Synthetic Data Generation for API-Calling Agents
arxiv-2607.16900 Sparse Blocked context only

Jul 18, 2026
Dataset Distillation by Influence Matching
arxiv-2607.16859 Sparse Blocked context only

Jul 18, 2026
Group Entropy-Controlled Policy Optimization
arxiv-2607.16850 Sparse Blocked context only

Jul 18, 2026
DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines
arxiv-2607.16617 Direct Blocked context only

Jul 18, 2026
Can Multimodal Large Language Models Understand OCT?
arxiv-2607.16609 Sparse Blocked context only

Jul 18, 2026
An Exam for Active Observers
arxiv-2607.16165 Sparse Blocked context only

Jul 17, 2026
Audio-Visual Flamingo: Open Audio-Visual Intelligence for Long and Complex Videos
arxiv-2607.16107 Curated Related Blocked context only

Jul 17, 2026
Understanding Reasoning from Pretraining to Post-Training
arxiv-2607.16097 Sparse Blocked context only

Jul 17, 2026
AVE-Compass: Towards Holistic Evaluation for Audio-Video Editing Abilities
arxiv-2607.24821 Sparse Blocked context only

Jul 17, 2026
DSWorld: A Data Science World Model for Efficient Autonomous Agents
arxiv-2607.15901 Sparse Blocked context only

Jul 17, 2026
S1-Omni: A Unified Multimodal Reasoning Model for Scientific Understanding, Prediction, and Generation
arxiv-2607.15686 Sparse Blocked context only

Jul 17, 2026
RecGPT-V3 Technical Report
arxiv-2607.15591 Sparse Blocked context only

Jul 17, 2026
SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction
arxiv-2607.15550 Sparse Blocked context only

Jul 17, 2026
Hierarchical Denoising For Multi-Step Visual Reasoning
arxiv-2607.15278 Sparse Blocked context only

Jul 16, 2026
Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents
arxiv-2607.15263 Sparse Blocked context only

Jul 16, 2026
SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration
arxiv-2607.15257 Sparse Blocked context only

Jul 16, 2026
On-Policy Delta Distillation
arxiv-2607.15161 Sparse Blocked context only

Jul 16, 2026
Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories
arxiv-2607.15330 Curated Related Blocked context only

Jul 16, 2026
SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment
arxiv-2607.15058 Sparse Blocked context only

Jul 16, 2026
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
arxiv-2607.14777 Direct Blocked context only

Jul 16, 2026
WanSong v1.0 Technical Report
arxiv-2607.14749 Sparse Blocked context only

Jul 16, 2026
VIABench: A Comprehensive Video Benchmark Collected from Blind Individuals for Visual Impairment Assistance
arxiv-2607.14660 Sparse Blocked context only

Jul 16, 2026
Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization
arxiv-2607.14614 Sparse Blocked context only

Jul 16, 2026
xHC: Expanded Hyper-Connections
arxiv-2607.14530 Sparse Blocked context only

Jul 16, 2026
Cura 1T: Specialized Model for Agentic Healthcare
arxiv-2607.15314 Sparse Blocked context only

Jul 15, 2026
Multi-Head Latent Control: A Unified Interface for LLM Agent Decision Making
arxiv-2607.14277 Sparse Blocked context only

Jul 15, 2026
VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders
arxiv-2607.14088 Sparse Blocked context only

Jul 15, 2026
MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation
arxiv-2607.14189 Sparse Blocked context only

Jul 15, 2026
GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch
arxiv-2607.13960 Direct Blocked context only

Jul 15, 2026
RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination
arxiv-2607.14187 Sparse Blocked context only

Jul 15, 2026
NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs
arxiv-2607.14186 Sparse Blocked context only

Jul 15, 2026
AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities
arxiv-2607.13705 Sparse Blocked context only

Jul 15, 2026
OvisOCR2 Technical Report
arxiv-2607.13639 Direct Blocked context only

Jul 15, 2026
DeepLoop: Depth Scaling for Looped Transformers
arxiv-2607.13491 Sparse Blocked context only

Jul 15, 2026
Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations
arxiv-2607.13399 Sparse Blocked context only

Jul 15, 2026
DiffGI: Differentiable Geometry Images for High-Fidelity Thin-Shell 3D Generation
arxiv-2607.13365 Sparse Blocked context only

Jul 15, 2026
Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable
arxiv-2607.13285 Direct Blocked context only

Jul 14, 2026
From Human-Centric to Agentic Code Review: The Impact of Different Generations of Generative AI Technology on Review Quality
arxiv-2607.13196 Sparse Blocked context only

Jul 14, 2026
Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes
arxiv-2607.13188 Sparse Blocked context only

Jul 14, 2026
PalmClaw: A Native On-Device Agent Framework for Mobile Phones
arxiv-2607.13027 Direct Blocked context only

Jul 14, 2026
Boogu-Image-0.1: Boosting Open-Source Unified Multimodal Understanding and Generation
arxiv-2607.13125 Direct Blocked context only

Jul 14, 2026
VisCo: Leveraging Large Language Models as Intrinsic Encoders for Visual Token Compression
arxiv-2607.12756 Sparse Blocked context only

Jul 14, 2026
Hallo4D: Multi-Modal Hallucination Mitigation for Consistent Spatio-Temporal Generation
arxiv-2607.12752 Sparse Blocked context only

Jul 14, 2026
KnowAct-GUIClaw: Know Deeply, Act Perfectly, Personal GUI Assistant with Self-Evolving Memory and Skill
arxiv-2607.12625 Direct Blocked context only

Jul 14, 2026
Self in Space: Benchmarking Self-Awareness and Spatial Cognition in UAV Embodied Intelligence
arxiv-2607.12477 Sparse Blocked context only

Jul 14, 2026
Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning
arxiv-2607.12395 Sparse Blocked context only

Jul 14, 2026
Rethinking the Evaluation of Harness Evolution for Agents
arxiv-2607.12227 Direct Blocked context only

Jul 14, 2026
Token Reduction Is Not Cost Reduction
arxiv-2607.12161 Direct Blocked context only

Jul 13, 2026
Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation
arxiv-2607.11886 Sparse Blocked context only

Jul 13, 2026
Evidence-Backed Video Question Answering
arxiv-2607.11862 Sparse Blocked context only

Jul 13, 2026
AdvancedMathBench: A Benchmark Suite for Advanced Mathematical Proof Generation and Verification
arxiv-2607.11849 Sparse Blocked context only

Jul 13, 2026
MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning
arxiv-2607.11736 Sparse Blocked context only

Jul 13, 2026
Qwen-Music Technical Report
arxiv-2607.11699 Sparse Blocked context only

Jul 13, 2026
RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM
arxiv-2607.11683 Direct Blocked context only

Jul 13, 2026
Xiaomi-Robotics-U0: Unified Embodied Synthesis with World Foundation Model
arxiv-2607.11643 Sparse Blocked context only

Jul 13, 2026
MAGIC: Transition-Aware Generation of Navigable Multi-Scene Game Worlds with Large Language Models
arxiv-2607.11594 Sparse Blocked context only

Jul 13, 2026
MonkeyOCRv2: A Visual-Text Foundation Model for Document AI
arxiv-2607.11562 Direct Blocked context only

Jul 13, 2026

All archive pages