Daily Papers of 2026-08-20

  1. SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation 157 upvotes, #1 of 2026-08-20
  2. Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence 147 upvotes, #2 of 2026-08-20
  3. SemaPLC: A Project-Grounded, Verification-Gated Agent Harness for PLC Code Generation 116 upvotes, #3 of 2026-08-20
  4. Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL 94 upvotes, #4 of 2026-08-20
  5. SPADE: Self-Play in Adaptive Synthetic Executable Environments 51 upvotes, #5 of 2026-08-20
  6. Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis 33 upvotes, #6 of 2026-08-20
  7. FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents 20 upvotes, #7 of 2026-08-20
  8. Training Leaves Traces: Centered Residual Signatures for Language Model Lineage Verification 18 upvotes, #8 of 2026-08-20
  9. The More Popular, The Harder to Forget: Adaptive Popularity for LLM Unlearning 17 upvotes, #9 of 2026-08-20
  10. Looped Language Models Improve Compositional Tool Calling 17 upvotes, #9 of 2026-08-20
  11. Decision-Metric Alignment in Latent World Models: Diagnostics and Action-Conditioned Objectives for MPC Planning 17 upvotes, #9 of 2026-08-20
  12. Scaling Creative Writing Beyond Story-Centric Data with Attribute-Guided Genre Expansion 14 upvotes, #12 of 2026-08-20
  13. SoftVTBench: A Deformation-Aware Visuo-Tactile Dataset and Benchmark for Deformable-Object Manipulation 13 upvotes, #13 of 2026-08-20
  14. VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation 11 upvotes, #14 of 2026-08-20
  15. SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents 7 upvotes, #15 of 2026-08-20
  16. LLMs Get Smarter from Targeted Synthetic Multilingual Data 5 upvotes, #16 of 2026-08-20
  17. Bounded Agents: Delegation Security for Multi-Agent AI Systems 4 upvotes, #17 of 2026-08-20
  18. Evaluating Music Context Preservation: A Multi-facet Framework for Music Editing Systems 3 upvotes, #18 of 2026-08-20
  19. Towards Real-Time and Adaptable LiDAR Scene Completion 3 upvotes, #18 of 2026-08-20
  20. Temporal Multi-Signal Fusion for Token-Level Hallucination Detection 3 upvotes, #18 of 2026-08-20
  21. SPK: Eliciting Structured Prior Knowledge for Interpretable Out-of-Distribution Detection in Real-Time Object Detection 2 upvotes, #21 of 2026-08-20

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.