Agentic AI

Changes since langchain-openai==1.7.1 release(openai): 1.7.2 ( #41245 ) fix(openai): keep Responses stream items on one block when output_index drifts ( #41121 )

• Read the full item at LangChain Releases.

arXiv:2610.20780v1 Announce Type: new Abstract: In LLM-based multi-agent systems (MAS), a local mistake can propagate as other agents build on it, turning a correctable error into a failed task. Diagnosing completed runs or repeatedly re-executing them to search for corrections does not provide a learned policy for intervening while execution is still in progress.

• Read the full item at arXiv cs.AI.

arXiv:2610.20809v1 Announce Type: new Abstract: A self-improving agent has to decide which new skills to keep, and in practice it keeps whatever earns a high reward, convinces a judge model, or compresses its library, even when the skill is wrong. That is fine until the answers have to be exactly right: over a table of transactions, a total is either right or wrong.

• Read the full item at arXiv cs.AI.

arXiv:2610.20960v1 Announce Type: new Abstract: Safety in agentic systems is inherently sequential: whether an action is safe depends on prior actions, tool outputs, information disclosures, and interactions among agents. Recent work has shifted agent safety guardrails from post-hoc trajectory-level assessment toward step-level action diagnosis and proactive risk prediction, yet existing training…

• Read the full item at arXiv cs.AI.