Today's standouts across cs.AI, cs.CL and cs.LG, picked by Jev from every new submission.
291 read → 74 shortlisted → 39 worth opening · 2026-11-06 · $0.0115
- · {\tau}-bench-LILT: Evaluating Conversational Agents on Realistic Multilingual Tool-Use Tasks
- · MCPHallu: Benchmarking Reasoning, Execution, and Memory Hallucinations in MCP Agents
- · TCSExam: Evaluating Frontier LLMs on the Full Range of TCS Research
OpenRSS
Tool-using and web-browsing LLM agents, from every new cs.AI, cs.CL, cs.LG and cs.MA submission.
287 read → 14 shortlisted → 3 worth opening · 2026-11-06 · $0.0109
- · Who Should Know What? Empirical Information Design for Multi-Agent LLM Economies
- · CORE: Coarse-to-Fine Search with Context Management for Deep Research
- · SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization
OpenRSS
Machine learning evaluated on patients, from new PubMed records — not preprints.
293 read → 19 shortlisted → 14 worth opening · 2026-11-06 · $0.0125
- · A parsimonious machine-learning model using routine laboratory data to differentiate nontuberculous mycobacterial disease from tuberculosis: Development and independent external validation.
- · Miscarriage Risk Prediction for Women With Polycystic Ovary Syndrome Who Achieve Clinical Pregnancy After Fresh Embryo Transfer: Multicenter Development, Geographic External Validation, and Prospective Temporal Validation Study.
- · Development and Validation of an Interpretable Machine-Learning Model for Predicting Suboptimal Clinical Response After Sleeve Gastrectomy: A Multicenter Study.
OpenRSS
Making inference faster, smaller or cheaper — across cs.LG, cs.DC and cs.AR.
166 read → 11 shortlisted → 7 worth opening · 2026-11-06 · $0.0064
- · TriAttention: Unified Sparse Mixed-Precision Attention for Long-Context LLM Inference
- · LowRAM: Low-Rank Keys and Amortised Values for Composable KV Cache Compression at Test-Time
- · TileQuant: Tile as the Precision-Allocation Unit for LLM Mixed-Precision Post-Training Quantization
OpenRSS
New bioRxiv neuroscience preprints, filtered for computational and systems work.
48 read → 0 shortlisted → 0 worth opening · 2026-11-06 · $0.0019
OpenRSS
Learned control and manipulation, from every new cs.RO submission.
68 read → 4 shortlisted → 0 worth opening · 2026-11-06 · $0.0026
OpenRSS
Tech news with the retellings removed: first-party announcements, measured numbers, and things you can use today.
208 read → 22 shortlisted → 15 worth opening · 2026-11-06 · $0.0077
- · DeepSeek-V4.1-Flash-1017 on one RTX 3090: Big updates to the Delta Inference Engine v0.93. Same 41 tok/s at 192GB/IQ2 at better quality, usable from 64 GB RAM, first token ~40% sooner, new Unsloth quants at full speed, EXL3, basic multi-GPU, public CI and more
- · Introducing Inkling 2 Small
- · [Paper] FireFlash : An Open Recipe for Long-Horizon Agentic RL Achieving the Performance-Cost Pareto Frontier
OpenRSS