pull down to refresh

Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RLarxiv.org/abs/2508.07976
183 sats \ 0 comments \ @optimism 13 Aug AI
related
[Help Wanted] Tell us about your searches to help SN improve
2299 sats \ 60 comments \ @SimpleStacker 29 Mar meta
Beyond the Sum: Unlocking AI Agents Potential Through Market Forcesgithub.com/Fewsats/beyond_the_sum
2406 sats \ 1 comment \ @Rsync25 26 Dec 2024 lightning
AI: Accelerated Incompetencewww.slater.dev/accelerated-incompetence/
1830 sats \ 7 comments \ @co574 29 May devs
The Hater's Guide To The AI Bubble (Ed Zitron)www.wheresyoured.at/the-haters-gui/
1301 sats \ 2 comments \ @StillStackinAfterAllTheseYears 23 Jul AI
AgentFly: Fine-tuning LLM Agents without Fine-tuning LLMsarxiv.org/abs/2508.16153
152 sats \ 0 comments \ @optimism 25 Aug AI
Agentic Reinforced Policy Optimizationarxiv.org/abs/2507.19849
141 sats \ 0 comments \ @optimism 29 Jul AI
Is AI hitting a wall?www.ft.com/content/d01290c9-cc92-4c1f-bd70-ac332cd40f94
343 sats \ 2 comments \ @Coinsreporter 16 Aug AI
Search-capable AI agents may cheat on benchmark testswww.theregister.com/2025/08/23/searchcapable_ai_agents_may_cheat
237 sats \ 2 comments \ @Coinsreporter 23 Aug AI
Combinatorial Node Selection & Resource Allocation in LN via Attention RLarxiv.org/html/2411.17353v1
221 sats \ 0 comments \ @Rsync25 27 Nov 2024 lightning
Content Independence Day: no AI crawl without compensation!blog.cloudflare.com/content-independence-day-no-ai-crawl-without-compensation/
392 sats \ 3 comments \ @0xbitcoiner 1 Jul AI
Game Theory Can Make AI More Correct and Efficient | Quanta Magazinewww.quantamagazine.org/game-theory-can-make-ai-more-correct-and-efficient-20240509/
13.2k sats \ 2 comments \ @nout 12 May 2024 science
Don’t Build Multi-Agentscognition.ai/blog/dont-build-multi-agents
180 sats \ 0 comments \ @carter 2 Sep AI
DeepPHY: Benchmarking Agentic VLMs on Physical Reasoningarxiv.org/abs/2508.05405
182 sats \ 0 comments \ @optimism 10 Aug AI
MCP-Bench: Benchmarking Tool-Using LLM Agentsarxiv.org/abs/2508.20453
239 sats \ 0 comments \ @optimism 30 Aug AI
Hybrid pathfinding optimization for the LN with Reinforcement Learningwww.sciencedirect.com/science/article/abs/pii/S0952197625002258
212 sats \ 0 comments \ @jakoyoh629 14 Feb lightning
Context Rot: How Increasing Input Tokens Impacts LLM Performanceresearch.trychroma.com/context-rot
304 sats \ 2 comments \ @Scoresby 14 Jul AI
Google just updated its algorithm. The Internet will never be the samewww.bbc.com/future/article/20240524-how-googles-new-algorithm-will-shape-your-internet
458 sats \ 13 comments \ @ch0k1 25 May 2024 news
Tesla’s Robotaxi Platform Could Drive Long-Term AI Dominancesubstack.com/@drrobertcastellano/p-162494731
1302 sats \ 6 comments \ @Car 23 Jun AI
Reflective Prompt Evolution Can Outperform Reinforcement Learningarxiviq.substack.com/p/gepa-reflective-prompt-evolution
110 sats \ 0 comments \ @carter 31 Jul AI
How have you incorporated ChatGPT (& other ai) into your daily workflow?
120 sats \ 6 comments \ @birdeye21 20 Jul 2023 tech
Gemini: Google's most capable AI model yetblog.google/technology/ai/google-gemini-ai/
606 sats \ 1 comment \ @hn 6 Dec 2023 tech