Great deep dive into how we're doing Harness Engineering to improve Deep Agents at the frontier of coding!
AGENTS
-
Experiential Reinforcement Learning: Teaching LLMs Self-Reflection
By
–
Making LLMs truly learn from its experience "Experiential Reinforcement Learning (ERL)" ERL makes an agent attempt -> get sparse feedback -> write a self-reflection -> retry All by distilling the improved retry back into the base policy so the correction sticks without needing
-
LangSmith Insights: Group Traces and Schedule Recurring Jobs
By
–
🔎 Use LangSmith Insights to group traces and find emergent usage patterns of your agents
— LangChain (@LangChain) 17 février 2026
Now with the ability to set a schedule and run recurring jobs!
Docs 👉 https://t.co/IjrWYOCsri pic.twitter.com/8hgZFJ7qNlUse LangSmith Insights to group traces and find emergent usage patterns of your agents Now with the ability to set a schedule and run recurring jobs! Docs https://
docs.langchain.com/langsmith/insi
ghts
… -
xAI Grok 4.20 features four parallel expert agents
By
–
BREAKING: xAI just dropped Grok 4.20 and it’s a team of 4 university professor–level agents This is not a normal model release. It’s four specialized agents running in parallel, reasoning together before you ever see the answer. Not one brain guessing.
Four experts -
Creating Superintelligent Agents: Beyond Clever Programming
By
–
How to Create a Superintelligent Agent? Today’s AI systems, however impressive, are still the result of clever programming and smart technology. https://
deananthonygratton.com/post/how-to-cr
eate-a-superintelligent-agent
… by @grattonboy #AI #MWC26 @grattongirl -
LangChain at IncentroCon Agentic ’26: Agent Engineering Best Practices
By
–
Join Marco Perini (LangChain) and Tim Ruiterkamp (Incentro) at IncentroCon Agentic '26 in Hilversum, Netherlands. Marco and Tim will guide you through agent engineering best practices with LangSmith RSVP for free here: https://
eventbrite.nl/e/tickets-ince
ntrocon-agentic-26-1437153176839?aff=LangChain
… -
Lossless Context Management Advances Agent Language Models
By
–
A paper worth paying close attention to. It presents Lossless Context Management (LCM), which reframes how agents handle long contexts. It outperforms Claude Code on long-context tasks. Recursive Language Models give the model full autonomy to write its own memory scripts. LCM
-
Eight Essential AI Agents for HR Leaders in 2026
By
–
8 AI Agents Every HR Leader Needs to Know in 2026 AI agents are becoming essential in HR — here are eight that HR leaders should understand and consider by 2026. Read more https://
bernardmarr.com/8-ai-agents-ev
ery-hr-leader-needs-to-know-in-2026/
… #AI #HRTech #FutureOfWork #BernardMarr -
Agent World Model: Synthetic Environments for RL Agent Training
By
–
Training tool-use agents with RL requires diverse, executable environments. But these environments barely exist. This new research introduces Agent World Model (AWM), a fully synthetic pipeline that generates executable agentic environments at scale. Starting from high-level
-
Voice-to-action agents to reduce input friction
By
–
Voice-to-action is where the agent layer is heading.
— God of Prompt (@godofprompt) 17 février 2026
Most people underestimate how much productivity leaks through input friction. Typing, tab switching, copy pasting between apps. None of that is actual work. It's overhead.
The teams solving that friction layer will own the… https://t.co/wfiLPZctOOVoice-to-action is where the agent layer is heading. Most people underestimate how much productivity leaks through input friction. Typing, tab switching, copy pasting between apps. None of that is actual work. It's overhead. The teams solving that friction layer will own the