AllLLMRoboticsStartupsResearchEthicsBusinessHardwareAutonomousMedicineCreative
Topic

#LLM

Curated coverage on «LLM»: releases, research, benchmarks, open-source.

4868 articles-78% vs prev. week305 this week
Subscribe
RELATED:#Business#Hardware#Research#Creative#Startups#Ethics#Autonomous#Robotics#Medicine
STI-OPD: A Probabilistic Teacher Intervention for Multi-Step Agentic Tasks
LLM·arXiv cs.CL

STI-OPD: A Probabilistic Teacher Intervention for Multi-Step Agentic Tasks

Oct 9, 2026·2 min
MASA Reframes LLM Sparse Attention as Matrix Approximation
LLM

MASA Reframes LLM Sparse Attention as Matrix Approximation

Oct 9, 2026·2 min
Routed Sparse Autoencoders Separate Words From Intonation in Speech on WavLM and SPEAR
LLM

Routed Sparse Autoencoders Separate Words From Intonation in Speech on WavLM and SPEAR

Oct 9, 2026·2 min
Galahad-kv stores KV cache on NVMe and loads a block 2.8–4.3x faster than recomputing it
LLM

Galahad-kv stores KV cache on NVMe and loads a block 2.8–4.3x faster than recomputing it

Oct 9, 2026·2 min
Fine-Tuned 0.8B-Parameter Model Beats GPT-5.4 at Grammar Annotation
LLM·arXiv cs.CL

Fine-Tuned 0.8B-Parameter Model Beats GPT-5.4 at Grammar Annotation

A 0.8B Qwen3.5 fine-tuned on teacher-model labels beat GPT-5.4 and GPT-5.6 Sol on precision and recall, and cut inference costs roughly 16x.

Oct 9, 2026·2 min
Utterance Normalization Cuts the Cost of Analyzing Millions of Calls: A Pipeline Built Entirely on Small Models
LLM·arXiv cs.CL

Utterance Normalization Cuts the Cost of Analyzing Millions of Calls: A Pipeline Built Entirely on Small Models

An arXiv paper turns dialogues into short, attributed statements with tags. A shared preparation layer lets teams run call analytics on small models.

Oct 9, 2026·2 min
Text autoencoder compresses web text to 2.24 bits per byte without losing meaning
LLM·arXiv cs.CL

Text autoencoder compresses web text to 2.24 bits per byte without losing meaning

A new arXiv paper trains a neural network to compress text into a discrete latent: 2.24 bits per byte on web data, on par with lossless algorithms, with good…

Oct 9, 2026·2 min
Cognitive Thermometers: Neural Networks Proposed as a Way to Measure the Complexity of Meaning
LLM·arXiv cs.CL

Cognitive Thermometers: Neural Networks Proposed as a Way to Measure the Complexity of Meaning

A survey on arXiv proposes using machine learning models as "cognitive thermometers" to measure which meanings languages choose most often, and why.

Oct 9, 2026·2 min
Top themes
01LLMs Draft Road-Work Plans for WisDOT: 14B Barely Beats 7BOct 9, 2026·2 min02Wieszcz-XIX: A 3.1-Billion-Word Polish Corpus From Before 1918 Trains Models From ScratchOct 9, 2026·2 min03Diffu-LoRA Lets the Adapter Decide Which Stable Diffusion Layers Need RankOct 9, 2026·2 min04GenUI-Harness Lifts a 4B Model From 9.33% to 58% Pass@3, Beating Claude Opus 5Oct 9, 2026·2 min05OpenProblemBench: GPT-6-Astra Solves 14% of Open Math and Physics ProblemsOct 9, 2026·2 min
AgentHorizon: Best Judge GPT-5.5 Scores Only 80.9% on Long Agent Tasks
LLM·arXiv cs.AI

AgentHorizon: Best Judge GPT-5.5 Scores Only 80.9% on Long Agent Tasks

Oct 9, 2026·2 min
Two Distillation Schemes Make AI Students Reveal Their Teachers' Hidden Behavior
LLM·arXiv cs.AI

Two Distillation Schemes Make AI Students Reveal Their Teachers' Hidden Behavior

Oct 9, 2026·2 min
Researchers prove that bloating AGENTS.md is harmful: the file has a size limit
LLM·arXiv cs.AI

Researchers prove that bloating AGENTS.md is harmful: the file has a size limit

Oct 9, 2026·2 min
GUISE Shows Narrative Wrappers Break Qwen3-1.7B in 89–96% of Cases
LLM·arXiv cs.AI

GUISE Shows Narrative Wrappers Break Qwen3-1.7B in 89–96% of Cases

Oct 9, 2026·2 min
An LLM Teaches a Planner to Get by With Polynomial Memory and Solves 1709 of 1890 Tasks
LLM·arXiv cs.AI

An LLM Teaches a Planner to Get by With Polynomial Memory and Solves 1709 of 1890 Tasks

Researchers replaced storage of millions of states with a learned policy with registers. Search runs in polynomial memory and solves 1709 of 1890 IPC 2023 test…

Oct 9, 2026·2 min
StoreBench: LLM Agents Run an Online Store and Lose to a Script — 49% vs. 97%
LLM·arXiv cs.AI

StoreBench: LLM Agents Run an Online Store and Lose to a Script — 49% vs. 97%

The StoreBench benchmark put seven top LLMs in charge of a clothing store. The best, DeepSeek-V4-Pro, passes 49% of tasks; a simple heuristic passes 97%; humans…

Oct 9, 2026·3 min
LLM Agents Don't Learn Community Norms From Interaction, Study Finds
LLM·arXiv cs.AI

LLM Agents Don't Learn Community Norms From Interaction, Study Finds

An arXiv preprint introduces the notion of LLM normative competence. In debates with synthetic norms, baseline agents failed to infer the rules, even when doing so would have raised their accuracy.

Oct 9, 2026·2 min
Qwen3.6-27B and Qwen3-4B Agents Blow Their Time Budgets Without Harness Hints
LLM·arXiv cs.AI

Qwen3.6-27B and Qwen3-4B Agents Blow Their Time Budgets Without Harness Hints

Oct 9, 2026·2 min
Plan-and-Patch: Diffusion LLM Repairs Agent Plans Twice as Often as Qwen3-8B
LLM·arXiv cs.AI

Plan-and-Patch: Diffusion LLM Repairs Agent Plans Twice as Often as Qwen3-8B

Oct 9, 2026·2 min
arXiv authors call for replacing a single annotation "truth" with a space of interpretations
LLM·arXiv cs.AI

arXiv authors call for replacing a single annotation "truth" with a space of interpretations

Oct 9, 2026·2 min
TGIT Translates Short Drone Commands and Lifts Navigation Success from 11% to 33%
LLM·arXiv cs.AI

TGIT Translates Short Drone Commands and Lifts Navigation Success from 11% to 33%

Oct 9, 2026·2 min
Agent strikes out its own old tool outputs and cuts input tokens by half
LLM·arXiv cs.AI

Agent strikes out its own old tool outputs and cuts input tokens by half

Oct 9, 2026·2 min
Credit AI Agent Can Only Change Its Harness: Gate Admitted 144 of 7,449 Edits
LLM

Credit AI Agent Can Only Change Its Harness: Gate Admitted 144 of 7,449 Edits

Oct 9, 2026·3 min
arXiv Authors Bound Agent Self-Improvement by Verification Class
LLM

arXiv Authors Bound Agent Self-Improvement by Verification Class

Oct 9, 2026·2 min
Western open-weight models pitch businesses an alternative to Chinese and closed AI
LLM

Western open-weight models pitch businesses an alternative to Chinese and closed AI

Oct 9, 2026·2 min
Vitalik Buterin Backs "Bunker Mode" for Crypto Over AI Progress in Math
LLM·Hacker News AI

Vitalik Buterin Backs "Bunker Mode" for Crypto Over AI Progress in Math

Justin Drake urged the crypto industry to go into "bunker mode": he estimates AI could undermine wallet security within months. Vitalik Buterin backed him.

Oct 9, 2026·2 min
Simon Willison releases ttok 0.4: the token counter gets --list-models
LLM·Simon Willison

Simon Willison releases ttok 0.4: the token counter gets --list-models

The first update to the ttok CLI tool in about two years fixes a Click warning, refreshes CI, and adds a --list-models command that lists available models.

Oct 9, 2026·2 min
Related topics
Business 1166Research 520Robotics 178Hardware 108Autonomous 39Ethics 10Startups 9Medicine 8