Daily Papers of 2026-11-12

  1. Scaling Mathematical Proof Supervision from Structured Textbooks 39 upvotes, #1 of 2026-11-12
  2. SteerDistill: Quantizing LLM Agents via Closed-Loop Teacher Steering 31 upvotes, #2 of 2026-11-12
  3. Incentivizing Self-Learning in Large Language Models via Reinforcement Learning 27 upvotes, #3 of 2026-11-12
  4. Read Less, Solve More: Token-Efficient Sparse Reading of External Content for AI Agents 18 upvotes, #4 of 2026-11-12
  5. Ensemble Routing for Prompt-Adaptive Cost-Aware LLM Inference 14 upvotes, #5 of 2026-11-12
  6. Interactive Visual Gym: Evaluating Visual Interaction Models with Simulated Users in Interactive Worlds 13 upvotes, #6 of 2026-11-12
  7. GTAGym: Real AAA Game Tasks Environment for Evaluation and Reinforcement Learning 12 upvotes, #7 of 2026-11-12
  8. Evolving Infra: Agent-Adaptive LLM Serving at Scale 10 upvotes, #8 of 2026-11-12
  9. Where Does Alignment Emerge and What Does It Mean? A Closer Look at the Platonic Representation Hypothesis 6 upvotes, #9 of 2026-11-12
  10. CogBattery: Human-Referenced Evaluation of Cognitive Task Behavior and Structure in Language Models 4 upvotes, #10 of 2026-11-12
  11. FAME-QP: A GPU-Accelerated Quadratic-Programming Solver for Real-Time Model Predictive Control 4 upvotes, #10 of 2026-11-12
  12. Precision on Demand: Escalating Weight Bits at Uncertain Decoding Steps in a Small Local Model 4 upvotes, #10 of 2026-11-12
  13. WMIP: A Working-Memory-Inspired Programmable Probe of Cumulative State Tracking in Large Language Models 3 upvotes, #13 of 2026-11-12
  14. CARTBench: Rubric-Based Evaluation of Shopping Advice for Complex and Ambiguous Requests with Timelines 3 upvotes, #13 of 2026-11-12
  15. Module-Aware Optimization for Graph Neural Networks 3 upvotes, #13 of 2026-11-12
  16. Mixed Signals: Weight-Space Programming for EEG and ECG 3 upvotes, #13 of 2026-11-12
  17. ScrapeBench: Evaluating Legal Compliance of AI Agents in Website Scraping 2 upvotes, #17 of 2026-11-12
  18. PolyRoute: A Twelve-Language and Code-Mixed Benchmark for Typed-Decision Routing, with Baselines and a Leaderboard 2 upvotes, #17 of 2026-11-12
  19. Bits or permutations? Spending a fixed inference budget on weight precision or on option-order averaging in small local language models 2 upvotes, #17 of 2026-11-12
  20. Subliminal Learning in Vision-Language Models 0 upvotes, #20 of 2026-11-12
  21. Probing Transformer Representations Layer by Layer, Module by Module 0 upvotes, #20 of 2026-11-12

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.