Tooling5d ago
OpenAI Agents API ships Auto Review, async compaction, experimental time awareness and mid-session tool updates
The OpenAI Developers account shared a post by Steve (@stevendcoffey), who works on the API at OpenAI, listing five Agents API updates this week: Codex-style Auto Review of commands before execution, compaction that runs in the background, an experimental time-awareness feature, updating a session's tools at any time, and automatic caching of system prompts across all sessions. As of writing, the official API changelog does not list these items yet.
Tooling47d ago
Inco open-sources Splash: ~144 tok/s for Qwen3.8-27B on M5 Max
Inco AI open-sourced Splash, a local inference engine built for Apple silicon and models like Qwen3.8-27B. On an M5 Max MacBook Pro it reports about 144 tok/s—up to 3× Ollama, 2× oMLX, and nearly 4× when an agent fans out sub-agents. LM Studio shipped day-0 support under Settings > Runtime > Experimental backends.
Agents19d ago
Mosaic: Multi-Session Agentic Reinforcement Learning for Context Compaction and Subagent Forking
Standard agentic reinforcement learning assumes single-session trajectories with continuously accumulated context, clashing with production agent techniques like context compaction and subagent forking. Researchers introduce Mosaic (arXiv:2610.22174), a critic-free hierarchical optimization framework for Multi-Session Agentic RL. By incorporating session-usage signals at the trajectory level and shaping per-session advantages by marginal contribution, Mosaic outperforms trajectory-level broadcasting on BrowseComp across both compaction and subagent scenarios while using fewer sessions.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.