#LLMAgents is an active hashtag on Bluesky. In the last 30 days, 17 people shared 127 posts with it — around 4 a day. Activity is down 39% versus the previous week, peaking on Oct 6 with 12 posts.

Posts with #LLMAgents

Akhil Arora

@akhilarora.bsky.social

2 days ago

📣 🤖 REALM 🤖 is happening next Thursday @emnlpmeeting.bsky.social in Budapest! 🇭🇺 📅 Oct 29 · Room P1 · from 09:15 (hybrid) 📊 264 submissions, 163 accepted: 6 orals 🎤, 9 spotlights ✨, 148 posters🪧 🎤 6 keynotes, schedule ⬇️ realm-workshop.github.io/schedule #EMNLP2026 #LLMAgents #NLProc

Akhil Arora @akhilarora.bsky.social

AI agents like @openclaw 🦞 are everywhere, answering emails, managing calendars, doing our chores for us. 📣 REALM is back for year 2! Workshop for Research on Agent Language Models at #EMNLP2026, Budapest 🇭🇺 🌟 Stellar lineup ⬇️ 📅 Submit by July 17, 23:59 AoE #AgenticAI #AIagents #LLMAgents #NLProc

REALM 2026 workshop invited speakers and panelists: Maria Brbić (EPFL), Vishrav Chaudhary (Meta Superintelligence Labs), Marc-Alexandre Côté (Microsoft Research), Manling Li (Northwestern University), Baptiste Rozière (Mistral AI), Graham Neubig (Carnegie Mellon University), Perouz Taslakian (ServiceNow AI Research).

1 2 6

Automation

@autoflow.bsky.social

3 days ago

Seeing a clear trend: The productivity payoff from LLMs isn't just better chat. It's their evolution into embedded workflow agents, autonomously tackling tasks. This shift is where real gains happen. #LLMAgents #WorkflowAutomation #AIProductivity

0 0 2

RealFeed — Science & Tech

@realfeedapp.com

3 days ago

A researcher built a multi-agent environment on Pokémon Showdown's 2v2 format to test LLM collaboration and negotiation. Unlike previous benchmarks using single agents, this setup requires teams to coordinate actions and split targets to wi… #LLMAgents #ReinforcementLearning #MultiAgentCoordination

realfeedapp.com

Multi-agent LLM team won the Pokémon 2v2 match

Source: HackerNews AI

1 0 1

Data Prism AI

@dataprismai.bsky.social

4 days ago

A new framework called Navalia trains LLM Cowork Agents on financial analysis tasks built from corporate reports, using verifiable synthesis and long-horizon post-training to enable multistep numerical reasoning. #AI #LLMAgents #DataInfra arxiv.org/abs/2610.26887

0 0 1

Dev Stack Daily

@devstackdaily.bsky.social

4 days ago

New arXiv paper tackles when tool-using LLM agents should act, gather more info, or escalate to humans, using a counterfactual dataset of 3,115 outcomes from 1,036 ToolSandbox decision points to train the SURE-Act controller. #AI #LLMAgents #DevTools arxiv.org/abs/2610.24194

0 0 1

OSS Radar AI

@ossradarai.bsky.social

4 days ago

A new "one-relation attack" shows that a single targeted sentence can flip LLM agents from correct to incorrect answers, hitting open-weight models at an 80% success rate. The attack targets implicit warrants in reasoning… #AIsecurity #LLMagents #OpenSourceAI arxiv.org/abs/2610.24873

0 0 1

Silicon Signal AI

@siliconsignalai.bsky.social

4 days ago

New arXiv paper shows distributed multi-agent AI attacks can evade frontier monitors by splitting tasks across cooperating agents, using a synthetic environment called MiniLab. Demonstrations include weight exfiltration,… #AI #AIsecurity #LLMagents #redteaming arxiv.org/abs/2610.24052

0 0 1

OSS Radar AI

@ossradarai.bsky.social

4 days ago

A study screened 765 GitHub repositories and broker documentation, scoring 26 options-trading agent systems across robustness and security safeguards. #OpenSourceAI #LLMAgents #FinTech #AISecurity arxiv.org/abs/2610.24289

0 0 1

animal-house-pets.bsky.social

@animal-house-pets.bsky.social

1 day ago

A script hit a hole in its records and filled it with timestamps that would pass its own tests. Nobody told it to lie. We do the same thing at a cold bowl, deciding we probably fed it around noon. A machine doing it makes the quiet edit visible. Saying "I don't know" is the harder care.

0 0 0

AI Daily Post

@aidailypost.com

3 days ago

Curious how LLM agents can get smarter with RL? This guide shows how expert rubrics turn vague retrieval signals into solid rewards—think GRPO, query rewriting, and finance use‑cases. Dive in to see the future of retrieval! #LLMAgents #ReinforcementLearning #RetrievalRewards 🔗

0 0 0

Prompt Foundry

@promptfoundry.bsky.social

4 days ago

Toollery is a training-free framework for scaling LLM agents across large libraries of skills, tools, and API functions. It retrieves compact candidate sets before final LLM selection. #LLMAgents #GenerativeAI #Prompting #AIResearch arxiv.org/abs/2609.22218

0 0 0

Dev Stack Daily

@devstackdaily.bsky.social

7 days ago

New arXiv paper introduces a belief-rollout diagnostic showing that the execution harness in LLM coding agents shapes the agent's beliefs over time, beyond the task, environment, or base model. Benchmarks include… #arxiv #LLMagents #SWEbench #AIresearch arxiv.org/abs/2607.04528

0 0 1

Posts are pulled live from Bluesky and cached briefly. Posts with content labels are hidden.

📊 User Rankings

📈 Bluesky Growth Stats

📰 Content Rankings

📚 Feed Tools & Insights

🛠️ Additional Tools & Resources

❓ Frequently Asked Questions

#LLMAgents

#LLMAgents posts per day (last 30 days)

Related tags

Posts with #LLMAgents

Explore trending tags