📄 Paper Explainer

Recent Papers from arXiv

• arXiv:2606.03988
  Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models
  Mahtab Bigverdi, Lindsey Li, Weikai Huang, et al.
  Artificial Intelligence (cs.AI)
• arXiv:2606.03937
  Entropy Is Not Enough: Unlocking Effective Reinforcement Learning for Visual Reasoning via Vision-Anchored Token Selection
  Senjie Jin, Peixin Wang, Boyang Liu, et al.
  Artificial Intelligence (cs.AI)
• arXiv:2606.03918
  Hedge-Bench: Benchmarking Agents on Hard, Realistic Tasks Pertaining to Financial Reasoning
  Eric Cho, Shawn Huang, Alice Lu, et al.
  Artificial Intelligence (cs.AI)
• arXiv:2606.03906
  scTranslation: A Comprehensive Benchmark for Single-Cell Multi-Omics Modality Translation
  Jiabei Cheng, Jingbo Zhou, Jun Xia, et al.
  Artificial Intelligence (cs.AI)
• arXiv:2606.03883
  Reasoning Structure of Large Language Models
  Frédéric Berdoz, Luca A. Lanzendörfer, Fabian Farestam, et al.
  Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
• arXiv:2606.03858
  PyraMathBench: Evaluating and Improving Mathematical Capability in Large Language Models
  Zetian Ouyang, Linlin Wang, Gerard de Melo, et al.
  Artificial Intelligence (cs.AI)
• arXiv:2606.03841
  EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management
  Zherui Yang, Fan Liu, Yansong Ning, et al.
  Artificial Intelligence (cs.AI)
• arXiv:2606.03829
  BigFinanceBench: A Workflow-Grounded Benchmark for Financial-Research Agents
  Alex Wang, Georg Meinhardt, Jacob Katz, et al.
  Artificial Intelligence (cs.AI)
• arXiv:2606.03823
  Calibrating Urban Traffic Simulation from Sparse Road Observations via Genetic Optimization
  Hunter Sawyer, Jesse Roberts, Simon Matei
  Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Neural and Evolutionary Computing (cs.NE)
• arXiv:2606.03814
  Leveraging BART to Assess CS1 C++ Programming Assignments using Rubric-based Criteria
  Kelsey Rainey, Jesse Roberts
  Artificial Intelligence (cs.AI)
• arXiv:2606.03812
  Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis
  Sanjay Das, Ran Elgedawy, Ethan Seefried, et al.
  Artificial Intelligence (cs.AI)
• arXiv:2606.03777
  From Control Boundary to Insurance Claim: Reconstructing AI-Mediated Losses Through the CER Framework
  Alex Leung, Rex Zhang, Kentaroh Toyoda, et al.
  Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Risk Management (q-fin.RM)
• arXiv:2606.03755
  LAP: An Agent-to-Instrument Protocol for Autonomous Science
  Linwu Zhu, Liqiang Gao, Yan Chen, et al.
  Artificial Intelligence (cs.AI)
• arXiv:2606.03743
  Proof-Refactor: Refactoring Generated Formal Proofs into Modular Artifacts
  Yiming Fu, Peixuan Liu, Zichen Wang, et al.
  Artificial Intelligence (cs.AI)
• arXiv:2606.03741
  When to Re-Plan: Subgoal Persistence in Hierarchical Latent Reasoning
  Ayushi Chadha
  Artificial Intelligence (cs.AI)
• arXiv:2606.03719
  Unveiling the Structure of Do-Calculus Reasoning via Derivation Graphs
  Clément Yvernes, Emilie Devijver, Marianne Clausel, et al.
  Artificial Intelligence (cs.AI)
• arXiv:2606.03705
  Code-on-Graph: Iterative Programmatic Reasoning via Large Language Models on Knowledge Graphs
  Weiwei Ding, Zixuan Li, Long Bai, et al.
  Artificial Intelligence (cs.AI)
• arXiv:2606.03704
  Dynamic Objective Selection with Safeguards and LLM Oversight for Financial Decision-Making
  Keigo Sakurai, Takahiro Ogawa, Miki Haseyama, et al.
  Artificial Intelligence (cs.AI); Computational Engineering, Finance, and Science (cs.CE); Computers and Society (cs.CY)
• arXiv:2606.03692
  SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents
  Yuan Xiong, Ziqi Miao, Qian Chen, et al.
  Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
• arXiv:2606.03686
  The DeepSpeak-Agentic Dataset
  Sarah Barrington, Maty Bohacek, Hany Farid
  Artificial Intelligence (cs.AI)
• arXiv:2606.03678
  EvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agents
  Tong Nie, Yuewen Mei, Yihong Tang, et al.
  Artificial Intelligence (cs.AI)
• arXiv:2606.03660
  From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models
  Hongyu Guo, Hao Li, He Cao, et al.
  Artificial Intelligence (cs.AI)
• arXiv:2606.03657
  Diagnosing Knowledge Gaps in LLM Tool Use: An Agentic Benchmark for Novel API Acquisition
  Jinnuo Liu, Yue Peng, Jinhan Niu, et al.
  Artificial Intelligence (cs.AI)
• arXiv:2606.03655
  Towards Non-Monotonic Entailment in Propositional Defeasible Standpoint Logic
  Nicholas Leisegang, Thomas Meyer, Ivan Varzniczak
  Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO)
• arXiv:2606.03641
  Gender-Dependent Diagnostic Substitution in LLM Medical Triage: Same Symptoms, Unequal Urgency
  Qi Han Wong
  Artificial Intelligence (cs.AI); Computers and Society (cs.CY)