Topics
Results for “llm agents”
49 results
- MiniMax M3.1 Flash — Hacker News · Seen · 462 points
- Hybrid Reasoning Agents: 35–55% fewer tokens and up to 2.6× faster inference — 2 sources · Seen · 506 points
- stepfun-ai/Step-5-Preview — Hugging Face Models · Seen
- nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB — Hugging Face Models · Seen
- reflection/Beam-1.0-501B-A23B — Hugging Face Models · Seen
- BizBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business — Hugging Face Papers · Seen · 269 points
- Harness^2: Recursive Agent Harnessing for an Open World — Hugging Face Papers · Seen · 112 points
- COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation — Hugging Face Papers · Seen · 131 points
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills — Hugging Face Papers · Seen · 268 points
- AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications — Hugging Face Papers · Seen · 71 points
- Prime Agent: A Self-Improving RLM Harness — Hugging Face Papers · Seen · 57 points
- ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration — Hugging Face Papers · Seen · 155 points
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory — Hugging Face Papers · Seen · 74 points
- TradingAgents: Multi-Agents LLM Financial Trading Framework — Hugging Face Papers · Seen · 153 points
- headroomlabs-ai/headroom — GitHub Trending · Seen
- ant-intl/BizAgentBench — Hugging Face Datasets · Seen
- Qwen/BlenderWorld — Hugging Face Datasets · Seen
- Structured outputs for Anthropic Claude models on Amazon Bedrock — AWS Machine Learning Blog · Seen
- I Built a Cozy 60 FPS AI Agent Bakery Game to Teach RAG, Guardrails, Context Caching & Multi-Agent Orchestration — DEV Community · Seen
- Building Better Agents through End-to-End Evals — DEV Community · Seen
- What requirements don't you have? — Lobsters · Seen · 23 points
- Testing the Planning Claims of LLM-Based Agents against Formal Semantics — arXiv AI Papers · Seen
- PRIME: Towards Verifiable Evidence-Grounded Reasoning in LLM Agents — arXiv AI Papers · Seen
- When is a large language model a good calibration agent? Physics-labeled prompting for budgeted engineering simulator calibration — arXiv AI Papers · Seen
- Structured Authority Injection: Persistent Human Control for LLM Agents via Typed MCP Overrides — arXiv AI Papers · Seen
- AI Needs a Test That Fights Back — DEV Community · Seen
- REMORY: Learning Residual Memory for Context Compaction — Hugging Face Papers · Seen · 164 points
- If You Never Do Anything Else to Fix Your Prompts, Do This One Thing — DEV Community · Seen
- Scale Agentic Coding Workflows with Meta’s Muse Spark Open on NVIDIA GB300 NVL72 — NVIDIA Developer Blog · Seen
- NVIDIA Nemotron 3.5 Super VL Powers Specialized Agents with Multimodal Reasoning — NVIDIA Developer Blog · Seen
- Muse Spark Open — Hacker News · Seen · 914 points
- affaan-m/ECC — GitHub Trending · Seen
- What LLMs 'Know' That You Don't Know They Know: Stop Inventing Prompt DSLs and Ride 50 Years of Unix Pre-Training Gravity — DEV Community · Seen
- Mara Chain: Rethinking Failure as a Stepping Stone for AI System Auto-Evolution — Hugging Face Papers · Seen · 10 points
- obra/superpowers — GitHub Trending · Seen
- What agents mean for Rust (and vice versa) — 2 sources · Seen · 10 points
- Run fast, private agents on-device with LFM2.5-24B-A2B — Hugging Face Blog · Seen
- Gemini 4 Argon: Built to solve your hardest problems — Google AI Blog · Seen
- Build long-horizon agents with Grok 4.7 on Amazon Bedrock — AWS Machine Learning Blog · Seen
- FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution — Hugging Face Papers · Seen · 113 points
- Show HN: Jevcrawl – A web crawler for AI agents with no LLM in the crawl loop — Hacker News · Seen · 12 points
- How to engineer an AI harness for game development — Hacker News · Seen · 151 points
- Gemini 4 Argon — Hacker News · Seen · 1,317 points
- IDRs as Records of Intent — Hacker News · Seen · 20 points
- Jev handed our LLM the wrong page a tenth as often as our embeddings — Hacker News · Seen · 8 points
- The gap in shared understanding of LLM capability is widening — Hacker News · Seen · 715 points
- gaia-benchmark/GAIA — Hugging Face Datasets · Seen
- 2026 in LLMs (so far) — Lobsters · Seen · 2 points
- Recursive self-improvement through collective intelligence — Hacker News · Seen · 135 points