Daily Papers of 2025-09-02

1. PVPO: Pre-Estimated Value-Based Policy Optimization for Agentic Reasoning 29 upvotes, #1 of 2025-09-02
2. T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables 21 upvotes, #2 of 2025-09-02
3. How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench 15 upvotes, #3 of 2025-09-02
4. No Label Left Behind: A Unified Surface Defect Detection Model for all Supervision Regimes 8 upvotes, #4 of 2025-09-02
5. From reactive to cognitive: brain-inspired spatial intelligence for embodied agents 7 upvotes, #5 of 2025-09-02
6. UI-Level Evaluation of ALLaM 34B: Measuring an Arabic-Centric LLM via HUMAIN Chat 6 upvotes, #6 of 2025-09-02
7. Democracy-in-Silico: Institutional Design as Alignment in AI-Governed Polities 2 upvotes, #7 of 2025-09-02

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.