ML algorithms, training, and inference
![[2604.17188] Beyond Overlap Metrics: Rewarding Reasoning and Preferences for Faithful Multi-Role Dialogue Summarization](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
Abstract page for arXiv paper 2604.17188: Beyond Overlap Metrics: Rewarding Reasoning and Preferences for Faithful Multi-Role Dialogue Su...
Abstract page for arXiv paper 2603.09723: RbtAct: Rebuttal as Supervision for Actionable Review Feedback Generation
Abstract page for arXiv paper 2601.21225: MGSM-Pro: A Simple Strategy for Robust Multilingual Mathematical Reasoning Evaluation
Abstract page for arXiv paper 2501.07813: Talk to Right Specialists: Iterative Routing in Multi-agent Systems for Question Answering
Abstract page for arXiv paper 2408.11871: MegaFake: A Theory-Driven Dataset of Fake News Generated by Large Language Models
Abstract page for arXiv paper 2406.14194: VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model
Abstract page for arXiv paper 2604.01438: ClawSafety: "Safe" LLMs, Unsafe Agents
Abstract page for arXiv paper 2603.18633: An Onto-Relational-Sophic Framework for Governing Synthetic Minds
Abstract page for arXiv paper 2603.09127: Collective AI can amplify tiny perturbations into divergent decisions
Abstract page for arXiv paper 2602.07943: IV Co-Scientist: Multi-Agent LLM Framework for Causal Instrumental Variable Discovery
Abstract page for arXiv paper 2602.03151: Enhancing Foundation VLM Robustness to Missing Modality: Scalable Diffusion for Bi-directional ...
Abstract page for arXiv paper 2601.22776: TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization
Abstract page for arXiv paper 2601.21439: The Paradox of Robustness: Decoupling Rule-Based Logic from Affective Noise in High-Stakes Deci...
Abstract page for arXiv paper 2511.16383: An Agent-Based Framework for the Automatic Validation of Mathematical Optimization Models
Abstract page for arXiv paper 2601.05656: HAG: Hierarchical Demographic Tree-based Agent Generation for Topic-Adaptive Simulation
Abstract page for arXiv paper 2512.13168: Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows
Abstract page for arXiv paper 2511.14130: PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval
Abstract page for arXiv paper 2510.09901: Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics
Abstract page for arXiv paper 2508.02900: Seemingly Simple Planning Problems are Computationally Challenging: The Countdown Game
Abstract page for arXiv paper 2502.13388: Reflection of Episodes: Learning to Play Game from Expert and Self Experiences
Abstract page for arXiv paper 2411.06498: Barriers to Complexity-Theoretic Proofs that "AGI" Using Machine Learning is Impossible
Abstract page for arXiv paper 2604.04924: Your Pre-trained Diffusion Model Secretly Knows Restoration
Abstract page for arXiv paper 2604.04906: How AI Aggregation Affects Knowledge
Get the latest news, tools, and insights delivered to your inbox.
Daily or weekly digest • Unsubscribe anytime