"Meta-Harness: End-to-End Optimization of Model Harnesses" A big portion of agentic LLM performance relies on human-designed harness around the model, not just the weights. On top of that, how well a harness is designed could impact a model's performance heavily. So this paper
AGENTS
-
Open Source Maintainer Struggles with AI Agent Adoption Gap
By
–
You don’t realize how hard this is. I have over 40 maintainers now and still ship over 70% of commits. Gap with agentic use is very high.
-
Multi-Agent Architecture: CC Hands Off Tasks to Codex
By
–
they are both still used in their own harnesses, that’s the whole reason why this is effective. CC can hand off an issue to codex to work on in its own harness!
-
Microsoft Copilot Frontier Model Council Compares AI Responses Side by Side
By
–
🚨Microsoft just dropped Copilot Cowork in Frontier; and the new Model Council feature is wild
— Futurepedia – Learn to Leverage AI (@futurepedia_io) 31 mars 2026
Inside Researcher, you can now compare responses from multiple AI models side by side:
→ See where they agree
→ See where they diverge
→ Get what each uniquely brings
Like having… pic.twitter.com/E7ZYvzOphMMicrosoft just dropped Copilot Cowork in Frontier; and the new Model Council feature is wild Inside Researcher, you can now compare responses from multiple AI models side by side:
→ See where they agree
→ See where they diverge
→ Get what each uniquely brings Like having -
Best Platforms for AI Agents
By
–
Best Platforms for #AIAgents
by @Python_Dv #AI #LLM #ArtificialIntelligence #MachineLearning #ML -
FinQA Open-Sourced: RL Environment for Financial Reasoning Agents
By
–
We just open-sourced FinQA — an #RL environment for financial reasoning agents. Real SEC 10-K data, multi-step reasoning + tool use, constrained SQL, binary rewards. The whole 9 yards! The kicker: a 4B model fine-tuned with FinQA outperformed a 235B model from the same family on finance reasoning: 58x smaller!
→ View original post on X — @snorkelai, 2026-03-31 00:19 UTC
-
5 Tips for Onboarding AI Agents Effectively
By
–
Stop dumping 10 folders of context on your AI agent and wondering why it’s confused.
— This Week in Startups (@twistartups) 31 mars 2026
Instead, on board your agent like you would a new hire. Tell it who you are, what the job is, and point it to the right links.
Always be SPECIFIC about what you want, and let the agent figure… pic.twitter.com/iWekuort5MStop dumping 10 folders of context on your AI agent and wondering why it’s confused. Instead, on board your agent like you would a new hire. Tell it who you are, what the job is, and point it to the right links. Always be SPECIFIC about what you want, and let the agent figure out the rest for itself. More of Google AI PM @Saboo_Shubham_’s ultimate OpenClaw starter guide on today’s new TWiST… plus demos of @AgentMail and @MoltworldIO. Chapters : 0:00 Intro 1:24 Plaud: If your work depends on conversations — interviews, meetings, calls — you need a Plaud NotePin. You can check it out at Plaud.ai/twist and use code TWIST for 10% off! 3:05 We're Claw-pilled once again; it's an all AI Agent showcase 6:15 Google AI PM Shubham Saboo's Top 5 OpenClaw tips 10:14 Quo (formerly OpenPhone) gives you a clean, modern way to handle every customer call, text, and thread all in one place. Try it free at quo.com/TWiST. 13:26 Tip #1 — Onboard your agent like a new hire 17:31 Tip #2 — Talk to your agents constantly 19:02 Tip #3 — Put your agents on a schedule 19:51 LinkedIn Jobs – Hire right, the first time. Post your first job and get $100 off towards your job post at LinkedIn.com/twist. 23:41 Tip #4 — Add cross-agent memory 29:33 Tip #5 — Let your agents self-improve 29:51 Iru unifies identity, endpoint security, and compliance into one platform. TWiST listeners get 20% off when they book a demo at iru.com/twist! 34:03 Why Jason says founders should avoid journalists (cc: @Jason, @Lons, @Haakamaujla) 🎥 Watch the full episode here 👇
→ View original post on X — @saboo_shubham_, 2026-03-31 00:11 UTC
-
Snorkel AI Sponsors First ACM Agentic AI Systems Conference
By
–
The first @TheOfficialACM conference on agentic AI systems just got a boost. @SnorkelAI is joining as a sponsor of @CAISconf this May in San Jose. Stanford AI Lab roots, production AI focus, and a shared belief that this community needs a rigorous home. caisconf.org
→ View original post on X — @snorkelai, 2026-03-31 00:09 UTC
-
Must-Read AI Research of the Week: LLM Agents and Optimization
By
–
Must-read AI research of the week: ▪️ Learning to Commit: Generating Organic Pull Requests via Online Repository Memory ▪️ Effective Strategies for Asynchronous Software Engineering Agents ▪️ Composer 2 ▪️ From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents ▪️ Scalable Prompt Routing via Fine-Grained Latent Task Discovery ▪️ MSFT: Addressing Dataset Mixtures Overfitting Heterogeneously in Multi-task SFT ▪️ On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation ▪️ Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs ▪️ Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs? ▪️ RL for Distributional Reasoning in LMs ▪️ Rethinking Token-Level Policy Optimization for Multimodal Chain-of-Thought ▪️ EVA: Efficient Reinforcement Learning for End-to-End Agent Find the full list and the main AI news here: turingpost.com/p/fod146
→ View original post on X — @debashis_dutta, 2026-03-30 23:41 UTC
-
4B Model Outperforms 235B Through Tool Discipline in FinQA
By
–
In the FinQA env, a 4B model was fine-tuned to outperform a 235B model from the same family on our Finance Reasoning benchmark. What did we teach the 4B model? Tool discipline. Learn more: snorkel.ai/blog/building-fin…
→ View original post on X — @snorkelai, 2026-03-30 22:51 UTC