Paper2Code archive

Paper archive page 50

Page 50 of 129. Links match the indexable papers sitemap inventory.

300 canonical paper links on this archive page.

Efficient Rationale-based Retrieval: On-policy Distillation from Generative Rerankers based on JEPA
arxiv-2604.23336 Sparse Blocked context only

Apr 25, 2026
Discovering Agentic Safety Specifications from 1-Bit Danger Signals
arxiv-2604.23210 Sparse Blocked context only

Apr 25, 2026
How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks
arxiv-2604.22750 Sparse Blocked context only

Apr 24, 2026
Aligning Dense Retrievers with LLM Utility via DistillationAligning Dense Retrievers with LLM Utility via Distillation
arxiv-2604.22722 Sparse Blocked context only

Apr 24, 2026
Thinking Without Words: Efficient Latent Reasoning with Abstract Chain-of-Thought
arxiv-2604.22709 Sparse Blocked context only

Apr 24, 2026
From Natural Language to Verified Code: Toward AI Assisted Problem-to-Code Generation with Dafny-Based Formal Verification
arxiv-2604.22601 Sparse Blocked context only

Apr 24, 2026
Learning Evidence Highlighting for Frozen LLMs
arxiv-2604.22565 Sparse Blocked context only

Apr 24, 2026
SOLAR-RL: Semi-Online Long-horizon Assignment Reinforcement Learning
arxiv-2604.22558 Sparse Blocked context only

Apr 24, 2026
Controllable Spoken Dialogue Generation: An LLM-Driven Grading System for K-12 Non-Native English Learners
arxiv-2604.22542 Sparse Blocked context only

Apr 24, 2026
RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment
arxiv-2604.22520 Sparse Blocked context only

Apr 24, 2026
Aggregate vs. Personalized Judges in Business Idea Evaluation: Evidence from Expert Disagreement
arxiv-2604.22517 Sparse Blocked context only

Apr 24, 2026
CGC: Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding
arxiv-2604.22498 Sparse Blocked context only

Apr 24, 2026
SSG: Logit-Balanced Vocabulary Partitioning for LLM Watermarking
arxiv-2604.22438 Sparse Blocked context only

Apr 24, 2026
AgentSearchBench: A Benchmark for AI Agent Search in the Wild
arxiv-2604.22436 Sparse Blocked context only

Apr 24, 2026
Introducing Background Temperature to Characterise Hidden Randomness in Large Language Models
arxiv-2604.22411 Sparse Blocked context only

Apr 24, 2026
Selective Contrastive Learning For Gloss Free Sign Language Translation
arxiv-2604.22374 Sparse Blocked context only

Apr 24, 2026
CNSL-bench: Benchmarking the Sign Language Understanding Capabilities of MLLMs on Chinese National Sign Language
arxiv-2604.22367 Sparse Blocked context only

Apr 24, 2026
Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization
arxiv-2604.22345 Sparse Blocked context only

Apr 24, 2026
Context-Fidelity Boosting: Enhancing Faithful Generation through Watermark-Inspired Decoding
arxiv-2604.22335 Sparse Blocked context only

Apr 24, 2026
ChangeQuery: Advancing Remote Sensing Change Analysis for Natural and Human-Induced Disasters from Visual Detection to Semantic Understanding
arxiv-2604.22333 Sparse Blocked context only

Apr 24, 2026
BLAST: Benchmarking LLMs with ASP-based Structured Testing
arxiv-2604.22306 Sparse Blocked context only

Apr 24, 2026
ReLeVAnT: Relevance Lexical Vectors for Accurate Legal Text Classification
arxiv-2604.22292 Sparse Blocked context only

Apr 24, 2026
Self-Correction as Feedback Control: Error Dynamics, Stability Thresholds, and Prompt Interventions in LLMs
arxiv-2604.22273 Sparse Blocked context only

Apr 24, 2026
Semantic Error Correction and Decoding for Short Block Channel Codes
arxiv-2604.22269 Sparse Blocked context only

Apr 24, 2026
Large Language Models Decide Early and Explain Later
arxiv-2604.22266 Sparse Blocked context only

Apr 24, 2026
Bridging the Long-Tail Gap: Robust Retrieval-Augmented Relation Completion via Multi-Stage Paraphrase Infusion
arxiv-2604.22261 Sparse Blocked context only

Apr 24, 2026
Towards Safe Mobility: A Unified Transportation Foundation Model enabled by Open-Ended Vision-Language Dataset
arxiv-2604.22260 Sparse Blocked context only

Apr 24, 2026
TTS-PRISM: A Perceptual Reasoning and Interpretable Speech Model for Fine-Grained Diagnosis
arxiv-2604.22225 Sparse Blocked context only

Apr 24, 2026
Verbal Confidence Saturation in 3-9B Open-Weight Instruction-Tuned LLMs: A Pre-Registered Psychometric Validity Screen
arxiv-2604.22215 Sparse Blocked context only

Apr 24, 2026
UniSonate: A Unified Model for Speech, Music, and Sound Effect Generation with Text Instructions
arxiv-2604.22209 Sparse Blocked context only

Apr 24, 2026
Behavioral Canaries: Auditing Private Retrieved Context Usage in RL Fine-Tuning
arxiv-2604.22191 Sparse Blocked context only

Apr 24, 2026
ResRank: Unifying Retrieval and Listwise Reranking via End-to-End Joint Training with Residual Passage Compression
arxiv-2604.22180 Sparse Blocked context only

Apr 24, 2026
dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model
arxiv-2604.22152 Sparse Blocked context only

Apr 24, 2026
Voice Under Revision: Large Language Models and the Normalization of Personal Narrative
arxiv-2604.22142 Curated Related Blocked context only

Apr 24, 2026
Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework
arxiv-2604.22119 Sparse Blocked context only

Apr 23, 2026
Memanto: Typed Semantic Memory with Information-Theoretic Retrieval for Long-Horizon Agents
arxiv-2604.22085 Direct Blocked context only

Apr 23, 2026
Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning
arxiv-2604.22074 Sparse Blocked context only

Apr 23, 2026
Reliability Auditing for Downstream LLM tasks in Psychiatry: LLM-Generated Hospitalization Risk Scores
arxiv-2604.22063 Sparse Blocked context only

Apr 23, 2026
Incentivizing Neuro-symbolic Language-based Reasoning in VLMs via Reinforcement Learning
arxiv-2604.22062 Sparse Blocked context only

Apr 23, 2026
Lightweight Retrieval-Augmented Generation and Large Language Model-Based Modeling for Scalable Patient-Trial Matching
arxiv-2604.22061 Sparse Blocked context only

Apr 23, 2026
Context Unrolling in Omni Models
arxiv-2604.21921 Sparse Blocked context only

Apr 23, 2026
When Prompts Override Vision: Prompt-Induced Hallucinations in LVLMs
arxiv-2604.21911 Sparse Blocked context only

Apr 23, 2026
Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems
arxiv-2604.21794 Sparse Blocked context only

Apr 23, 2026
StructMem: Structured Memory for Long-Horizon Behavior in LLMs
arxiv-2604.21748 Sparse Blocked context only

Apr 23, 2026
Encoder-Free Human Motion Understanding via Structured Motion Descriptions
arxiv-2604.21668 Curated Related Blocked context only

Apr 23, 2026
Process Supervision via Verbal Critique Improves Reasoning in Large Language Models
arxiv-2604.21611 Sparse Blocked context only

Apr 23, 2026
Generalizing Numerical Reasoning in Table Data through Operation Sketches and Self-Supervised Learning
arxiv-2604.21495 Sparse Blocked context only

Apr 23, 2026
Efficient Agent Evaluation via Diversity-Guided User Simulation
arxiv-2604.21480 Sparse Blocked context only

Apr 23, 2026
CARE: Counselor-Aligned Response Engine for Online Mental-Health Support
arxiv-2604.21352 Sparse Blocked context only

Apr 23, 2026
Beyond Single Plots: A Benchmark for Question Answering on Multi-Charts
arxiv-2604.21344 Sparse Blocked context only

Apr 23, 2026
Ideological Bias in LLMs' Economic Causal Reasoning
arxiv-2604.21334 Sparse Blocked context only

Apr 23, 2026
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning
arxiv-2604.21327 Sparse Blocked context only

Apr 23, 2026
CAP: Controllable Alignment Prompting for Unlearning in LLMs
arxiv-2604.21251 Sparse Blocked context only

Apr 23, 2026
Learning Dynamic Representations and Policies from Multimodal Clinical Time-Series with Informative Missingness
arxiv-2604.21235 Sparse Blocked context only

Apr 23, 2026
Trust but Verify: Introducing DAVinCI -- A Framework for Dual Attribution and Verification in Claim Inference for Language Models
arxiv-2604.21193 Sparse Blocked context only

Apr 23, 2026
Breaking MCP with Function Hijacking Attacks: Novel Threats for Function Calling and Agentic Models
arxiv-2604.20994 Sparse Blocked context only

Apr 22, 2026
Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Tasks
arxiv-2604.20987 Sparse Blocked context only

Apr 22, 2026
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
arxiv-2604.20796 Curated Related Blocked context only

Apr 22, 2026
Working Memory Constraints Scaffold Learning in Transformers under Data Scarcity
arxiv-2604.20789 Sparse Blocked context only

Apr 22, 2026
Anchor-and-Resume Concession Under Dynamic Pricing for LLM-Augmented Freight Negotiation
arxiv-2604.20732 Sparse Blocked context only

Apr 22, 2026
COMPASS: COntinual Multilingual PEFT with Adaptive Semantic Sampling
arxiv-2604.20720 Sparse Blocked context only

Apr 22, 2026
The Expense of Seeing: Attaining Trustworthy Multimodal Reasoning Within the Monolithic Paradigm
arxiv-2604.20665 Sparse Blocked context only

Apr 22, 2026
Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science Workflows
arxiv-2604.20658 Sparse Blocked context only

Apr 22, 2026
Self-Aware Vector Embeddings for Retrieval-Augmented Generation: A Neuroscience-Inspired Framework for Temporal, Confidence-Weighted, and Relational Knowledge
arxiv-2604.20598 Sparse Blocked context only

Apr 22, 2026
Exploring Spatial Intelligence from a Generative Perspective
arxiv-2604.20570 Sparse Blocked context only

Apr 22, 2026
CHASM: Unveiling Covert Advertisements on Chinese Social Media
arxiv-2604.20511 Sparse Blocked context only

Apr 22, 2026
HaS: Accelerating RAG through Homology-Aware Speculative Retrieval
arxiv-2604.20452 Sparse Blocked context only

Apr 22, 2026
WebGen-R1: Incentivizing Large Language Models to Generate Functional and Aesthetic Websites with Reinforcement Learning
arxiv-2604.20398 Sparse Blocked context only

Apr 22, 2026
Hybrid Policy Distillation for LLMs
arxiv-2604.20244 Sparse Blocked context only

Apr 22, 2026
Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows
arxiv-2604.20200 Sparse Blocked context only

Apr 22, 2026
Simplified Sparse Attention via Gist Tokens
arxiv-2604.20920 Sparse Blocked context only

Apr 22, 2026
Temporally Extended Mixture-of-Experts Models
arxiv-2604.20156 Sparse Blocked context only

Apr 22, 2026
EvoAgent: An Evolvable Agent Framework with Skill Learning and Multi-Agent Delegation
arxiv-2604.20133 Sparse Blocked context only

Apr 22, 2026
SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks
arxiv-2604.20087 Sparse Blocked context only

Apr 22, 2026
Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text
arxiv-2604.20051 Sparse Blocked context only

Apr 21, 2026
Visual Reasoning through Tool-supervised Reinforcement Learning
arxiv-2604.19945 Sparse Blocked context only

Apr 21, 2026
CreativeGame:Toward Mechanic-Aware Creative Game Generation
arxiv-2604.19926 Sparse Blocked context only

Apr 21, 2026
MMCORE: MultiModal COnnection with Representation Aligned Latent Embeddings
arxiv-2604.19902 Sparse Blocked context only

Apr 21, 2026
AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model
arxiv-2604.19747 Direct Blocked context only

Apr 21, 2026
PlayCoder: Making LLM-Generated GUI Code Playable
arxiv-2604.19742 Sparse Blocked context only

Apr 21, 2026
DR-Venus: Towards Frontier Edge-Scale Deep Research Agents with Only 10K Open Data
arxiv-2604.19859 Sparse Blocked context only

Apr 21, 2026
Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language
arxiv-2604.19667 Sparse Blocked context only

Apr 21, 2026
Pause or Fabricate? Training Language Models for Grounded Reasoning
arxiv-2604.19656 Sparse Blocked context only

Apr 21, 2026
CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation
arxiv-2604.19636 Curated Related Blocked context only

Apr 21, 2026
SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing
arxiv-2604.19587 Sparse Blocked context only

Apr 21, 2026
A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression
arxiv-2604.19572 Direct Blocked context only

Apr 21, 2026
LePREC: Reasoning as Classification over Structured Factors for Assessing Relevance of Legal Issues
arxiv-2604.19464 Sparse Blocked context only

Apr 21, 2026
What Makes an LLM a Good Optimizer? A Trajectory Analysis of LLM-Guided Evolutionary Search
arxiv-2604.19440 Sparse Blocked context only

Apr 21, 2026
HP-Edit: A Human-Preference Post-Training Framework for Image Editing
arxiv-2604.19406 Sparse Blocked context only

Apr 21, 2026
DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing
arxiv-2604.19351 Curated Related Blocked context only

Apr 21, 2026
Evaluating LLM-Driven Summarisation of Parliamentary Debates with Computational Argumentation
arxiv-2604.19331 Sparse Blocked context only

Apr 21, 2026
RDP LoRA: Geometry-Driven Identification for Parameter-Efficient Adaptation in Large Language Models
arxiv-2604.19321 Sparse Blocked context only

Apr 21, 2026
IndiaFinBench: An Evaluation Benchmark for Large Language Model Performance on Indian Financial Regulatory Text
arxiv-2604.19298 Sparse Blocked context only

Apr 21, 2026
Detoxification for LLM: From Dataset Itself
arxiv-2604.19124 Curated Related Blocked context only

Apr 21, 2026
Expert Upcycling: Shifting the Compute-Efficient Frontier of Mixture-of-Experts
arxiv-2604.19835 Sparse Blocked context only

Apr 21, 2026
SAVOIR: Learning Social Savoir-Faire via Shapley-based Reward Attribution
arxiv-2604.18982 Sparse Blocked context only

Apr 21, 2026
AI scientists produce results without reasoning scientifically
arxiv-2604.18805 Sparse Blocked context only

Apr 20, 2026
Remask, Don't Replace: Token-to-Mask Refinement in Diffusion Large Language Models
arxiv-2604.18738 Sparse Blocked context only

Apr 20, 2026
MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval
arxiv-2604.18584 Sparse Blocked context only

Apr 20, 2026
Sessa: Selective State Space Attention
arxiv-2604.18580 Sparse Blocked context only

Apr 20, 2026
When Can LLMs Learn to Reason with Weak Supervision?
arxiv-2604.18574 Sparse Blocked context only

Apr 20, 2026
MultiWorld: Scalable Multi-Agent Multi-View Video World Models
arxiv-2604.18564 Direct Blocked context only

Apr 20, 2026
ClawEnvKit: Automatic Environment Generation for Claw-Like Agents
arxiv-2604.18543 Direct Blocked context only

Apr 20, 2026
StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning
arxiv-2604.18401 Sparse Blocked context only

Apr 20, 2026
River-LLM: Large Language Model Seamless Exit Based on KV Share
arxiv-2604.18396 Sparse Blocked context only

Apr 20, 2026
OpenGame: Open Agentic Coding for Games
arxiv-2604.18394 Sparse Blocked context only

Apr 20, 2026
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
arxiv-2604.18292 Sparse Blocked context only

Apr 20, 2026
Beyond Pattern Matching: Seven Cross-Domain Techniques for Prompt Injection Detection
arxiv-2604.18248 Sparse Blocked context only

Apr 20, 2026
AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware Evaluation
arxiv-2604.18240 Sparse Blocked context only

Apr 20, 2026
WebCompass: Towards Multimodal Web Coding Evaluation for Code Language Models
arxiv-2604.18224 Sparse Blocked context only

Apr 20, 2026
Multiplication in Multimodal LLMs: Computation with Text, Image, and Audio Inputs
arxiv-2604.18203 Sparse Blocked context only

Apr 20, 2026
MM-JudgeBias: A Benchmark for Evaluating Compositional Biases in MLLM-as-a-Judge
arxiv-2604.18164 Sparse Blocked context only

Apr 20, 2026
Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration
arxiv-2604.18131 Sparse Blocked context only

Apr 20, 2026
Employing General-Purpose and Biomedical Large Language Models with Advanced Prompt Engineering for Pharmacoepidemiologic Study Design
arxiv-2604.17988 Sparse Blocked context only

Apr 20, 2026
Modeling Multiple Support Strategies within a Single Turn for Emotional Support Conversations
arxiv-2604.17972 Sparse Blocked context only

Apr 20, 2026
Unlocking the Edge deployment and ondevice acceleration of multi-LoRA enabled one-for-all foundational LLM
arxiv-2604.18655 Sparse Blocked context only

Apr 20, 2026
On the Reliability of Computer Use Agents
arxiv-2604.17849 Sparse Blocked context only

Apr 20, 2026
Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Model
arxiv-2604.17739 Sparse Blocked context only

Apr 20, 2026
Screen Before You Interpret: A Portable Validity Protocol for Benchmark-Based LLM Confidence Signals
arxiv-2604.17714 Sparse Blocked context only

Apr 20, 2026
The Geometric Canary: Predicting Steerability and Detecting Drift via Representational Stability
arxiv-2604.17698 Sparse Blocked context only

Apr 20, 2026
Stratagem: Learning Transferable Reasoning via Trajectory-Modulated Game Self-Play
arxiv-2604.17696 Sparse Blocked context only

Apr 20, 2026
MoE-nD: Per-Layer Mixture-of-Experts Routing for Multi-Axis KV Cache Compression
arxiv-2604.17695 Sparse Blocked context only

Apr 20, 2026
Agents Explore but Agents Ignore: LLMs Lack Environmental Curiosity
arxiv-2604.17609 Sparse Blocked context only

Apr 19, 2026
Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories
arxiv-2604.17596 Sparse Blocked context only

Apr 19, 2026
UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models
arxiv-2604.17565 Sparse Blocked context only

Apr 19, 2026
HSG: Hyperbolic Scene Graph
arxiv-2604.17454 Sparse Blocked context only

Apr 19, 2026
Jupiter-N Technical Report
arxiv-2604.17429 Sparse Blocked context only

Apr 19, 2026
EvoMaster: A Foundational Agent Framework for Building Evolving Autonomous Scientific Agents at Scale
arxiv-2604.17406 Sparse Blocked context only

Apr 19, 2026
Speculative Decoding for Autoregressive Video Generation
arxiv-2604.17397 Sparse Blocked context only

Apr 19, 2026
Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?
arxiv-2604.17338 Sparse Blocked context only

Apr 19, 2026
When Background Matters: Breaking Medical Vision Language Models by Transferable Attack
arxiv-2604.17318 Sparse Blocked context only

Apr 19, 2026
Cat-DPO: Category-Adaptive Safety Alignment
arxiv-2604.17299 Sparse Blocked context only

Apr 19, 2026
LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics
arxiv-2604.17295 Sparse Blocked context only

Apr 19, 2026
GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)
arxiv-2604.17091 Sparse Blocked context only

Apr 18, 2026
Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL
arxiv-2604.17073 Sparse Blocked context only

Apr 18, 2026
MNAFT: modality neuron-aware fine-tuning of multimodal large language models for image translation
arxiv-2604.16943 Sparse Blocked context only

Apr 18, 2026
EasyVideoR1: Easier RL for Video Understanding
arxiv-2604.16893 Sparse Blocked context only

Apr 18, 2026
FlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills
arxiv-2607.21596 Sparse Blocked context only

Apr 18, 2026
The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation
arxiv-2604.16830 Sparse Blocked context only

Apr 18, 2026
Repurposing 3D Generative Model for Autoregressive Layout Generation
arxiv-2604.16299 Sparse Blocked context only

Apr 17, 2026
VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects
arxiv-2604.16272 Sparse Blocked context only

Apr 17, 2026
AtManRL: Towards Faithful Reasoning via Differentiable Attention Saliency
arxiv-2604.16158 Sparse Blocked context only

Apr 17, 2026
Mind's Eye: A Benchmark of Visual Abstraction, Transformation and Composition for Multimodal LLMs
arxiv-2604.16054 Sparse Blocked context only

Apr 17, 2026
On the Robustness of LLM-Based Dense Retrievers: A Systematic Analysis of Generalizability and Stability
arxiv-2604.16576 Sparse Blocked context only

Apr 17, 2026
Neurosymbolic Repo-level Code Localization
arxiv-2604.16021 Sparse Blocked context only

Apr 17, 2026
Hierarchical Codec Diffusion for Video-to-Speech Generation
arxiv-2604.15923 Sparse Blocked context only

Apr 17, 2026
CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution
arxiv-2604.15840 Sparse Blocked context only

Apr 17, 2026
Qwen3.5-Omni Technical Report
arxiv-2604.15804 Sparse Blocked context only

Apr 17, 2026
MemEvoBench: Benchmarking Safety Risks from Memory Misevolution in LLM Agents
arxiv-2604.15774 Sparse Blocked context only

Apr 17, 2026
KWBench: Measuring Unprompted Problem Recognition in Knowledge Work
arxiv-2604.15760 Sparse Blocked context only

Apr 17, 2026
GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows
arxiv-2604.15715 Sparse Blocked context only

Apr 17, 2026
Faster LLM Inference via Sequential Monte Carlo
arxiv-2604.15672 Curated Related Blocked context only

Apr 17, 2026
Stargazer: A Scalable Model-Fitting Benchmark Environment for AI Agents under Astrophysical Constraints
arxiv-2604.15664 Sparse Blocked context only

Apr 17, 2026
Why Fine-Tuning Encourages Hallucinations and How to Fix It
arxiv-2604.15574 Sparse Blocked context only

Apr 16, 2026
MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation
arxiv-2604.15309 Sparse Blocked context only

Apr 16, 2026
RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework
arxiv-2604.15308 Direct Blocked context only

Apr 16, 2026
Generalization in LLM Problem Solving: The Case of the Shortest Path
arxiv-2604.15306 Sparse Blocked context only

Apr 16, 2026
Why Do Vision Language Models Struggle To Recognize Human Emotions?
arxiv-2604.15280 Sparse Blocked context only

Apr 16, 2026
Scaling Test-Time Compute for Agentic Coding
arxiv-2604.16529 Sparse Blocked context only

Apr 16, 2026
From Tokens to Steps: Verification-Aware Speculative Decoding for Efficient Multi-Step Reasoning
arxiv-2604.15244 Sparse Blocked context only

Apr 16, 2026
MADE: A Living Benchmark for Multi-Label Text Classification with Uncertainty Quantification of Medical Device Adverse Events
arxiv-2604.15203 Sparse Blocked context only

Apr 16, 2026
Scepsy: Serving Agentic Workflows Using Aggregate LLM Pipelines
arxiv-2604.15186 Sparse Blocked context only

Apr 16, 2026
Compressing Sequences in the Latent Embedding Space: $K$-Token Merging for Large Language Models
arxiv-2604.15153 Sparse Blocked context only

Apr 16, 2026
QuantCode-Bench: A Benchmark for Evaluating the Ability of Large Language Models to Generate Executable Algorithmic Trading Strategies
arxiv-2604.15151 Sparse Blocked context only

Apr 16, 2026
LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking
arxiv-2604.15149 Sparse Blocked context only

Apr 16, 2026
IG-Search: Step-Level Information Gain Rewards for Search-Augmented Reasoning
arxiv-2604.15148 Sparse Blocked context only

Apr 16, 2026
Blinded Multi-Rater Comparative Evaluation of a Large Language Model and Clinician-Authored Responses in CGM-Informed Diabetes Counseling
arxiv-2604.15124 Sparse Blocked context only

Apr 16, 2026
OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis
arxiv-2604.15093 Sparse Blocked context only

Apr 16, 2026
Autonomous Evolution of EDA Tools: Multi-Agent Self-Evolved ABC
arxiv-2604.15082 Sparse Blocked context only

Apr 16, 2026
Towards Faster Language Model Inference Using Mixture-of-Experts Flow Matching
arxiv-2604.15009 Sparse Blocked context only

Apr 16, 2026
UniDoc-RL: Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards
arxiv-2604.14967 Sparse Blocked context only

Apr 16, 2026
RaTA-Tool: Retrieval-based Tool Selection with Multimodal Large Language Models
arxiv-2604.14951 Sparse Blocked context only

Apr 16, 2026
LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning
arxiv-2604.14922 Sparse Blocked context only

Apr 16, 2026
RACER: Retrieval-Augmented Contextual Rapid Speculative Decoding
arxiv-2604.14885 Sparse Blocked context only

Apr 16, 2026
Modeling LLM Unlearning as an Asymmetric Two-Task Learning Problem
arxiv-2604.14808 Sparse Blocked context only

Apr 16, 2026
Is This Edit Correct? A Multi-Dimensional Benchmark for Reasoning-Aware Image Editing
arxiv-2606.05172 Sparse Blocked context only

Apr 16, 2026
DR$^{3}$-Eval: Towards Realistic and Reproducible Deep Research Evaluation
arxiv-2604.14683 Sparse Blocked context only

Apr 16, 2026
StoryCoder: Narrative Reformulation for Structured Reasoning in LLM Code Generation
arxiv-2604.14631 Sparse Blocked context only

Apr 16, 2026
Mechanistic Decoding of Cognitive Constructs in Large Language Models
arxiv-2604.14593 Sparse Blocked context only

Apr 16, 2026
Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG
arxiv-2604.14572 Sparse Blocked context only

Apr 16, 2026
TRACER: Trace-Based Adaptive Cost-Efficient Routing for LLM Classification
arxiv-2604.14531 Direct Blocked context only

Apr 16, 2026
EuropeMedQA Study Protocol: A Multilingual, Multimodal Medical Examination Dataset for Language Model Evaluation
arxiv-2604.14306 Sparse Blocked context only

Apr 15, 2026
ROSE: Retrieval-Oriented Segmentation Enhancement
arxiv-2604.14147 Sparse Blocked context only

Apr 15, 2026
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
arxiv-2604.14268 Direct Blocked context only

Apr 15, 2026
From $P(y|x)$ to $P(y)$: Investigating Reinforcement Learning in Pre-train Space
arxiv-2604.14142 Sparse Blocked context only

Apr 15, 2026
HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation System
arxiv-2604.14125 Sparse Blocked context only

Apr 15, 2026
TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration
arxiv-2604.14116 Curated Related Blocked context only

Apr 15, 2026
TIP: Token Importance in On-Policy Distillation
arxiv-2604.14084 Sparse Blocked context only

Apr 15, 2026
Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective
arxiv-2604.14025 Sparse Blocked context only

Apr 15, 2026
Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents
arxiv-2604.14004 Sparse Blocked context only

Apr 15, 2026
CollabCoder: Plan-Code Co-Evolution via Collaborative Decision-Making for Efficient Code Generation
arxiv-2604.13946 Sparse Blocked context only

Apr 15, 2026
DiPO: Disentangled Perplexity Policy Optimization for Fine-grained Exploration-Exploitation Trade-Off
arxiv-2604.13902 Sparse Blocked context only

Apr 15, 2026
SparseBalance: Load-Balanced Long Context Training with Dynamic Sparse Attention
arxiv-2604.13847 Sparse Blocked context only

Apr 15, 2026
UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization
arxiv-2604.13822 Sparse Blocked context only

Apr 15, 2026
Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA
arxiv-2604.13731 Sparse Blocked context only

Apr 15, 2026
An Empirical Investigation of Practical LLM-as-a-Judge Improvement Techniques on RewardBench 2
arxiv-2604.13717 Sparse Blocked context only

Apr 15, 2026
IndicDB -- Benchmarking Multilingual Text-to-SQL Capabilities in Indian Languages
arxiv-2604.13686 Sparse Blocked context only

Apr 15, 2026
Time series causal discovery with variable lags
arxiv-2605.04081 Sparse Blocked context only

Apr 15, 2026
Calibrated Speculative Decoding: Frequency-Guided Candidate Selection for Efficient Inference
arxiv-2604.13634 Sparse Blocked context only

Apr 15, 2026
Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges
arxiv-2604.13602 Sparse Blocked context only

Apr 15, 2026
ToolSpec: Accelerating Tool Calling via Schema-Aware and Retrieval-Augmented Speculative Decoding
arxiv-2604.13519 Sparse Blocked context only

Apr 15, 2026
Representation over Routing: Overcoming Surrogate Hacking in Multi-Timescale PPO
arxiv-2604.13517 Sparse Blocked context only

Apr 15, 2026
MERRIN: A Benchmark for Multimodal Evidence Retrieval and Reasoning in Noisy Web Environments
arxiv-2604.13418 Sparse Blocked context only

Apr 15, 2026
Peer-Predictive Self-Training for Language Model Reasoning
arxiv-2604.13356 Sparse Blocked context only

Apr 14, 2026
AgentSPEX: An Agent SPecification and EXecution Language
arxiv-2604.13346 Sparse Blocked context only

Apr 14, 2026
WebXSkill: Skill Learning for Autonomous Web Agents
arxiv-2604.13318 Sparse Blocked context only

Apr 14, 2026
KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs
arxiv-2604.13226 Sparse Blocked context only

Apr 14, 2026
InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis
arxiv-2604.13201 Sparse Blocked context only

Apr 14, 2026
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
arxiv-2604.14228 Direct Blocked context only

Apr 14, 2026
Toward Autonomous Long-Horizon Engineering for ML Research
arxiv-2604.13018 Sparse Blocked context only

Apr 14, 2026
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
arxiv-2604.13016 Direct Blocked context only

Apr 14, 2026
Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation
arxiv-2604.13010 Sparse Blocked context only

Apr 14, 2026
One Token Away from Collapse: The Fragility of Instruction-Tuned Helpfulness
arxiv-2604.13006 Sparse Blocked context only

Apr 14, 2026
Boosting Visual Instruction Tuning with Self-Supervised Guidance
arxiv-2604.12966 Sparse Blocked context only

Apr 14, 2026
Towards Long-horizon Agentic Multimodal Search
arxiv-2604.12890 Sparse Blocked context only

Apr 14, 2026
KnowRL: Boosting LLM Reasoning via Reinforcement Learning with Minimal-Sufficient Knowledge Guidance
arxiv-2604.12627 Sparse Blocked context only

Apr 14, 2026
Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO
arxiv-2605.04077 Sparse Blocked context only

Apr 14, 2026
Latent-Condensed Transformer for Efficient Long Context Modeling
arxiv-2604.12452 Sparse Blocked context only

Apr 14, 2026
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
arxiv-2604.12374 Curated Related Blocked context only

Apr 14, 2026
Self-Adversarial One Step Generation via Condition Shifting
arxiv-2604.12322 Sparse Blocked context only

Apr 14, 2026
Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision
arxiv-2604.12002 Sparse Blocked context only

Apr 13, 2026
ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents
arxiv-2604.11784 Direct Blocked context only

Apr 13, 2026
Towards Autonomous Mechanistic Reasoning in Virtual Cells
arxiv-2604.11661 Sparse Blocked context only

Apr 13, 2026
Self-Evolving LLM Memory Extraction Across Heterogeneous Tasks
arxiv-2604.11610 Curated Related Blocked context only

Apr 13, 2026
A Triadic Suffix Tokenization Scheme for Numerical Reasoning
arxiv-2604.11582 Sparse Blocked context only

Apr 13, 2026
Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarking
arxiv-2604.11581 Sparse Blocked context only

Apr 13, 2026
Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
arxiv-2604.11554 Direct Blocked context only

Apr 13, 2026
Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory
arxiv-2604.11544 Sparse Blocked context only

Apr 13, 2026
METER: Evaluating Multi-Level Contextual Causal Reasoning in Large Language Models
arxiv-2604.11502 Sparse Blocked context only

Apr 13, 2026
Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of Inference
arxiv-2604.11496 Sparse Blocked context only

Apr 13, 2026
Anthropogenic Regional Adaptation in Multimodal Vision-Language Model
arxiv-2604.11490 Sparse Blocked context only

Apr 13, 2026
METRO: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialogues
arxiv-2604.11427 Sparse Blocked context only

Apr 13, 2026
OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video
arxiv-2604.11102 Sparse Blocked context only

Apr 13, 2026
Guardrails Beat Guidance: A Large-Scale Study of Rules, Skills, and Persistent Configuration for Coding Agents
arxiv-2604.11088 Direct Blocked context only

Apr 13, 2026
You Only Judge Once: Multi-response Reward Modeling in a Single Forward Pass
arxiv-2604.10966 Sparse Blocked context only

Apr 13, 2026
OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models
arxiv-2604.10866 Sparse Blocked context only

Apr 13, 2026
Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing
arxiv-2604.10708 Direct Blocked context only

Apr 12, 2026
Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models
arxiv-2604.10681 Sparse Blocked context only

Apr 12, 2026
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents
arxiv-2604.10577 Sparse Blocked context only

Apr 12, 2026
IceCache: Memory-efficient KV-cache Management for Long-Sequence LLMs
arxiv-2604.10539 Sparse Blocked context only

Apr 12, 2026
Thinking Fast, Thinking Wrong: Intuitiveness Modulates LLM Counterfactual Reasoning in Policy Evaluation
arxiv-2604.10511 Sparse Blocked context only

Apr 12, 2026
The Amazing Agent Race: Strong Tool Users, Weak Navigators
arxiv-2604.10261 Sparse Blocked context only

Apr 11, 2026
A Temporally Augmented Graph Attention Network for Affordance Classification
arxiv-2604.10149 Sparse Blocked context only

Apr 11, 2026
Think in Sentences: Explicit Sentence Boundaries Enhance Language Model's Capabilities
arxiv-2604.10135 Sparse Blocked context only

Apr 11, 2026
From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models
arxiv-2604.09459 Sparse Blocked context only

Apr 10, 2026
Many-Tier Instruction Hierarchy in LLM Agents
arxiv-2604.09443 Sparse Blocked context only

Apr 10, 2026
Do AI Coding Agents Log Like Humans? An Empirical Study
arxiv-2604.09409 Sparse Blocked context only

Apr 10, 2026
HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?
arxiv-2604.09408 Sparse Blocked context only

Apr 10, 2026
CONSCIENTIA: Can LLM Agents Learn to Strategize? Emergent Deception and Trust in a Multi-Agent NYC Simulation
arxiv-2604.09746 Sparse Blocked context only

Apr 10, 2026
MAB-DQA: Addressing Query Aspect Importance in Document Question Answering with Multi-Armed Bandits
arxiv-2604.08952 Sparse Blocked context only

Apr 10, 2026
SPPO: Sequence-Level PPO for Long-Horizon Reasoning Tasks
arxiv-2604.08865 Sparse Blocked context only

Apr 10, 2026
Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts
arxiv-2604.08541 Sparse Blocked context only

Apr 9, 2026
OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks
arxiv-2604.08539 Sparse Blocked context only

Apr 9, 2026
AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation
arxiv-2604.08540 Sparse Blocked context only

Apr 9, 2026
RewardFlow: Generate Images by Optimizing What You Reward
arxiv-2604.08536 Sparse Blocked context only

Apr 9, 2026
Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language Models
arxiv-2604.08527 Sparse Blocked context only

Apr 9, 2026
Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest
arxiv-2604.08525 Sparse Blocked context only

Apr 9, 2026
What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal
arxiv-2604.08524 Sparse Blocked context only

Apr 9, 2026
What do Language Models Learn and When? The Implicit Curriculum Hypothesis
arxiv-2604.08510 Sparse Blocked context only

Apr 9, 2026
Quantifying Explanation Consistency: The C-Score Metric for CAM-Based Explainability in Medical Image Classification
arxiv-2604.08502 Sparse Blocked context only

Apr 9, 2026
SUPERNOVA: Eliciting General Reasoning in LLMs with Reinforcement Learning on Natural Instructions
arxiv-2604.08477 Sparse Blocked context only

Apr 9, 2026
Faithful GRPO: Improving Visual Spatial Reasoning in Multimodal Language Models via Constrained Policy Optimization
arxiv-2604.08476 Sparse Blocked context only

Apr 9, 2026
From Safety Risk to Design Principle: Peer-Preservation in Multi-Agent LLM Systems and Its Implications for Orchestrated Democratic Discourse Analysis
arxiv-2604.08465 Sparse Blocked context only

Apr 9, 2026
OVS-DINO: Open-Vocabulary Segmentation via Structure-Aligned SAM-DINO with Language Guidance
arxiv-2604.08461 Sparse Blocked context only

Apr 9, 2026
Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models
arxiv-2604.08456 Sparse Blocked context only

Apr 9, 2026
KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation
arxiv-2604.08455 Direct Blocked context only

Apr 9, 2026
Learning Who Disagrees: Demographic Importance Weighting for Modeling Annotator Distributions with DiADEM
arxiv-2604.08425 Sparse Blocked context only

Apr 9, 2026
Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing
arxiv-2604.08401 Sparse Blocked context only

Apr 9, 2026
Phantasia: Context-Adaptive Backdoors in Vision Language Models
arxiv-2604.08395 Sparse Blocked context only

Apr 9, 2026
Awakening the Sleeping Agent: Lean-Specific Agentic Data Reactivates General Tool Use in Goedel Prover
arxiv-2604.08388 Sparse Blocked context only

Apr 9, 2026
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
arxiv-2604.08377 Direct Blocked context only

Apr 9, 2026
Don't Overthink It: Inter-Rollout Action Agreement as a Free Adaptive-Compute Signal for LLM Agents
arxiv-2604.08369 Sparse Blocked context only

Apr 9, 2026
ASPECT:Analogical Semantic Policy Execution via Language Conditioned Transfer
arxiv-2604.08355 Sparse Blocked context only

Apr 9, 2026
PokeGym: A Visually-Driven Long-Horizon Benchmark for Vision-Language Models
arxiv-2604.08340 Sparse Blocked context only

Apr 9, 2026
InstAP: Instance-Aware Vision-Language Pre-Train for Spatial-Temporal Understanding
arxiv-2604.08337 Sparse Blocked context only

Apr 9, 2026
Dead Weights, Live Signals: Feedforward Graphs of Frozen Language Models
arxiv-2604.08335 Sparse Blocked context only

Apr 9, 2026
Lost in the Hype: Revealing and Dissecting the Performance Degradation of Medical Multimodal Large Language Models in Image Classification
arxiv-2604.08333 Sparse Blocked context only

Apr 9, 2026
ProMedical: Hierarchical Fine-Grained Criteria Modeling for Medical LLM Alignment via Explicit Injection
arxiv-2604.08326 Sparse Blocked context only

Apr 9, 2026
Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions
arxiv-2604.08304 Sparse Blocked context only

Apr 9, 2026
DMax: Aggressive Parallel Decoding for dLLMs
arxiv-2604.08302 Sparse Blocked context only

Apr 9, 2026
Distributed Multi-Layer Editing for Rule-Level Knowledge in Large Language Models
arxiv-2604.08284 Sparse Blocked context only

Apr 9, 2026
When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning
arxiv-2604.08281 Sparse Blocked context only

Apr 9, 2026
DBMF: A Dual-Branch Multimodal Framework for Out-of-Distribution Detection
arxiv-2604.08261 Sparse Blocked context only

Apr 9, 2026
Self-Debias: Self-correcting for Debiasing Large Language Models
arxiv-2604.08243 Sparse Blocked context only

Apr 9, 2026
EditCaption: Human-Aligned Instruction Synthesis for Image Editing via Supervised Fine-Tuning and Direct Preference Optimization
arxiv-2604.08213 Sparse Blocked context only

Apr 9, 2026
Aligning Agents via Planning: A Benchmark for Trajectory-Level Reward Modeling
arxiv-2604.08178 Sparse Blocked context only

Apr 9, 2026
Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference
arxiv-2604.08133 Sparse Blocked context only

Apr 9, 2026
Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator
arxiv-2604.08121 Sparse Blocked context only

Apr 9, 2026
Small Vision-Language Models are Smart Compressors for Long Video Understanding
arxiv-2604.08120 Curated Related Blocked context only

Apr 9, 2026
Dual-Pool Token-Budget Routing for Cost-Efficient and Reliable LLM Serving
arxiv-2604.08075 Sparse Blocked context only

Apr 9, 2026
Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation
arxiv-2604.08046 Sparse Blocked context only

Apr 9, 2026
Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs
arxiv-2604.08003 Sparse Blocked context only

Apr 9, 2026
PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory
arxiv-2604.08000 Sparse Blocked context only

Apr 9, 2026
A Decomposition Perspective to Long-context Reasoning for LLMs
arxiv-2604.07981 Sparse Blocked context only

Apr 9, 2026
TOOLCAD: Exploring Tool-Using Large Language Models in Text-to-CAD Generation with Reinforcement Learning
arxiv-2604.07960 Sparse Blocked context only

Apr 9, 2026
Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning
arxiv-2604.07941 Sparse Blocked context only

Apr 9, 2026
TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation
arxiv-2604.07894 Sparse Blocked context only

Apr 9, 2026
Data Selection for Multi-turn Dialogue Instruction Tuning
arxiv-2604.07892 Sparse Blocked context only

Apr 9, 2026
Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection
arxiv-2604.07831 Sparse Blocked context only

Apr 9, 2026
TEMPER: Testing Emotional Perturbation in Quantitative Reasoning
arxiv-2604.07801 Sparse Blocked context only

Apr 9, 2026

All archive pages