#agenticsystems — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #agenticsystems, aggregated by home.social.
-
Agent token cost grows quadratically in turns without caching, roughly linearly with caching. A new post fits those curves to SWE-bench traces on three models. Cross-model finding shows something interesting: Gemini 3 Flash takes 2× as many turns as GPT-5.2 or Opus 4.6, so its leaner per-turn verbosity (~300 tokens vs ~1,000) still burns more total tokens.
-
The Inference Shift: Ben Thompson splits "inference" into two workloads. Answer inference (human waiting) stays on premium GPUs; agentic inference (no human waiting) migrates to commodity memory hierarchy. Familiar shape: the 70s batch-off-mainframes migration may rerun on today's GPU clusters.
https://benjaminhan.net/posts/20260511-the-inference-shift/?utm_source=mastodon&utm_medium=social
-
Whoa, hold onto your propeller hats, folks! 🤓 We've got a #GitHub project that's apparently a self-modifying, open-sourced "agentic system" (whatever that means) living in consumer hardware. Because clearly what we all need is more inscrutable tech jargon disguised as innovation! 🤖🔧
https://github.com/ninjahawk/hollow-agentOS #Innovation #SelfModifyingTech #AgenticSystems #ConsumerHardware #TechJargon #HackerNews #ngated -
Supervising Ralph Wiggum: pairing a design agent with a separate metacognitive critic beats a plain retry loop AND a self-monitoring agent on battery-pack design.
Metacognitive prompts alone don't help; moving them to a different agent does. Converges with ReMA's math-reasoning result: a separately parameterized head for meta-level work outperforms one model doing both.
-
Position paper: today's self-improving agents lean on extrinsic metacognition — fixed human-designed loops about what to monitor, when to switch strategies. Genuine self-improvement needs the agent itself to decide those.
The intrinsic/extrinsic axis is the right lens for recent agent work. STaR, DSPy, MASS, MetaSPO all extrinsic by this definition. Optimistic bet: current LLMs already carry partial ingredients.
-
ReMA trains a two-agent RL setup: a meta-thinker plans reasoning, an executor carries it out. Trained jointly with multi-agent RL, beats R1-style single-agent baselines on math.
The split-agent pattern keeps showing up. Supervising Ralph Wiggum (engineering design, prompted) runs the same architecture a year later and lands the same direction of result. Open question: does decoupling survive a FLOPs-matched comparison?
https://benjaminhan.net/posts/20260430-rema-meta-think/?utm_source=mastodon&utm_medium=social
-
MASS optimizes multi-agent LLM systems by interleaving prompt and topology search: block-level prompts, topology rejection sampling, then workflow-level prompts.
Topology gets quietly demoted. Ablation on Gemini 1.5 Pro: ~6% gain from block prompts, 3% from topology, 2% from workflow prompts. Prompt tuning dominates — contradicts the topology-first thesis of ADAS and AFlow.
-
🔍 What if your AI could discover tools like a developer and reason like a strategist?
From tool selection to runtime planning—MCP lets LLMs think beyond the prompt.
Explore the autonomy blueprint for next-gen AI agents 🚀
👇
https://medium.com/@rogt.x1997/how-dynamic-tool-discovery-with-mcp-is-rewriting-the-rules-of-autonomy-5cce7475d6e2
#AI #LLMAgents #AutonomousAI #ModelContext #OpenAI #GenAI #AgenticSystems
https://medium.com/@rogt.x1997/how-dynamic-tool-discovery-with-mcp-is-rewriting-the-rules-of-autonomy-5cce7475d6e2