Agents
-
Agents
VS Code Agent Merge turns PR blockers into a continuous agent loop
VS Code 1.136 lets agents repeatedly fix PR reviews, CI failures and conflicts, raising a new need for independent merge controls.
-
Research
DRACO turns agent-evaluation evidence into step-level training credit
IBM's DRACO redistributes rubric-based reward across agent steps, with open code and a source discrepancy that highlights the need for reproducible evaluation.
-
Research
PatchBench shows why a stopped crash is not a verified AI security fix
PatchBench finds that single-PoC checks can overstate AI vulnerability-patching success and argues for independent security and semantic validation.
-
Research
Context privilege escalation turns agent memory into a security boundary
A study across 12 agent harnesses shows how context can gain authority across roles and scopes, making provenance-aware non-escalation controls a runtime requirement.
-
Research
CordisBench shows where agent harnesses should replace reasoning with verification
CordisBench finds that models struggle with growing harness lifecycle interactions even when software can compute the tested state consequences exactly.
-
New Models
GPT-6 Astra launches with critical cyber capability and staged access
OpenAI launches GPT-6 Astra with staged access, Critical cyber classification and runtime safeguards that can interrupt agent tasks.
-
Agents
Zoho Catalyst 3.0 gives coding agents controlled access to cloud infrastructure
Catalyst 3.0 connects coding agents to cloud infrastructure through MCP, with scoped permissions, audit logs and reversible changes.
-
Agents
GitHub lets Copilot approvals count toward merge requirements
Copilot code review can now count as a required pull-request approval, with enterprise, repository and path controls around where AI approval applies.
-
Agents
GitHub extends Copilot content exclusions to app and CLI, but gaps remain
Copilot app and CLI now respect content exclusions, while GitHub still documents gaps in IDE agent modes, symlinks and remote filesystems.
-
🧩 AI Agents Need Contracts, Not Better Prompts (5/10)
How versioned agent contracts define scope, tools, budgets, refusal, escalation and evidence, and turn AI governance into enforceable runtime behavior.