TACO: Tool-Augmented Credit Optimization for Agentic Tool Use
Agentic multimodal models perform diverse operations on an image via code and reason over the returned view, an effective paradigm for fine-grained visual question answering. However,…
Full feed
Feed 27,506 posts
Every story across every category, newest first. Each card links to the original publisher; daily-brief posts open as editorial pages.
ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models
The emergence of Large Reasoning Models has introduced exceptionally long Chain-of-Thought traces, creating a transparency burden where critical logic is often buried under massive procedural text.…
Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent
We introduce Agents-A1, a 35B Mixture-of-Experts Agentic Model that reaches trillion-parameter-level performance by scaling the agent horizon. We investigate agent-horizon scaling from two perspectives: scaling long-horizon…
PolicyGuard: A Dialogue-Grounded Sub-Agent Verifier for Policy Adherence in LLM Agents
LLM agents handle user requests on behalf of organizations through tool calls and must follow the company policies stated in their system prompts. Prior work approaches…
Focusing on What Matters: Saliency-Harnessing Accurate Routing for Diffusion MoE
Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling diffusion models in visual generation. Recent advancements have focused on adaptively allocating computational resources across…
How Good Can Linear Models Be for Time-Series Forecasting?
Time-series forecasting research has been moving steadily toward larger architectures, from specialized transformers to general-purpose foundation models, on the assumption that capacity is what unlocks accuracy.…
They are such liars!
They are such liars!Wilfred Reilly: The original frame for the US-AID debate was: "Evil space Nazi Elon Musk killed 14,000,000 people!!!"*I and others pointed out that…
GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots
Data, as the fundamental substrate of modern intelligence, has greatly driven the development of current foundation models. Naturally, researchers aim to extend this paradigm to the…
Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction
Predicting human item difficulty is central to educational assessment, where reliable estimates support fairness and effective test construction. Existing methods often depend on costly human calibration…
Bridging VideoQA and Video-Guided Agentic Tasks via Generalized Keyframe Extraction
Video understanding is a fundamental capability for multimodal intelligence, and recent Multimodal Large Language Models (MLLMs) have achieved remarkable performance on Video Question Answering (VideoQA) benchmarks.…
MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation
Normalizing Flows (NFs) are powerful generative models capable of exact density estimation and sampling. However, their strict invertibility often forces the model to exhaust its capacity…
Bingo
BingoAesthetica: Why would anyone use prediction models when we can use real mortality data? Answer: Because you can't make bodies appear out of thin air, but…
Loko Scheme 0.13.0
Article URL: https://weinholt.se/articles/loko-scheme-0-13-0/ Comments URL: https://news.ycombinator.com/item?id=48727953 Points: 11 # Comments: 1
Exactly
ExactlyJohn LeFevre: This is a classic meme.But it's not the entire picture:1) Most of the grift and graft happens at the NGO level with overpaid liberal…
Try it out
Try it outtetsuo: X just launched hosted MCP servers so AI tools can connect directly to the platform.Connect Grok Build, Cursor, Claude, VS Code, or any…
RT Gad Saad: Happy birthday to a truly legendary intellectual!
RT Gad SaadHappy birthday to a truly legendary intellectual!Sowell Economics: Happy birthday Dr. Thomas Sowell!
RT The Bulwark: "Every one of these children had a name. They had dreams, loves, and futures. Their lives were as valuable and special as your child’…
RT The Bulwark"Every one of these children had a name. They had dreams, loves, and futures. Their lives were as valuable and special as your child’s…
RT thebes: "Assistant! My dividend is half the size it should be!" .oO ( Thinking… ) You are correct, User. Your dividend of the Beyond was $25,514,…
RT thebes"Assistant! My dividend is half the size it should be!".oO ( Thinking... ) You are correct, User. Your dividend of the Beyond was $25,514,376.30. Using…
Vibe coding platform Base44 launches own model as AI startups seek defensibility
Wix-owned vibe coding platform Base44 has started rolling out its own AI model — with hopes that it will eventually outperform frontier models.
AsyncOPD: How Stale Can On-Policy Distillation Be?
On-policy distillation (OPD) trains a student on its own rollouts guided by teacher feedback and is becoming increasingly important for large language model (LLM) post-training. Like…
RT Sawyer Merritt: Ford CEO Jim Farley in new interview on Chinese EV competition: "There's no real competition from Tesla, GM or Ford with what we've…
RT Sawyer MerrittFord CEO Jim Farley in new interview on Chinese EV competition:"There's no real competition from Tesla, GM or Ford with what we've seen from…
How I’m using local models from real-world coding
Just want to share since after many attempts over the past year, I finally have a setup I kinda like and does useful work for me.…
Why Won't Europe Build AI Data Centers in Iceland?
Article URL: https://mrkt30.com/why-wont-europe-build-ai-data-centers-in-iceland/ Comments URL: https://news.ycombinator.com/item?id=48727538 Points: 4 # Comments: 0
RT Alex Volkov @ AI Engineer: A candid hallway track interview with the man himself – @swyx Mini Podcast if you will, he's told me about a huge milest…
RT Alex Volkov @ AI EngineerA candid hallway track interview with the man himself - @swyx Mini Podcast if you will, he's told me about a…