Harness optimization is getting real receipts. AutoSaddler is offline harness learning from agent failure traces. Not another prompt tweak loop. It patches prompts, tools, and middleware as code. Then it keeps updates that survive a held out set. On the test sets (Pass@1): GAIA2: 53.0 → 62.0 (+9.0) SWE-Bench Pro: 37.3 → 46.9 (+9.6) Terminal-Bench 2.0: 40.0 → 50.0 (+10.0) That TB2 number also clears the expert tuned Terminus KIRA at 47.5. Kill generalization aware selection and GAIA2 falls to 50.6, under the default agent. Deep diagnosis and structured patches help. Dev set filtering is what stops the harness from overfitting the mini batch. On GAIA2, Figure 1b, about 147 leveraged traces to the best dev score vs about 1,400 for Meta-Harness.

Inference Optimizations Behind the MiMo-V2.5 Series API Price Reductions Read the full technical blog: The V2.5 model family, including MiMo-V2.5 and MiMo-V2.5-Pro, is built on a Hybrid Sliding Window Attention (Hybrid SWA) architecture, which compresses KVCache storage to roughly 1/7 that of Full Attention. However, architectural advantages rarely translate directly into measurable gains in production serving. To realize these gains, we redesigned KVCache management, tiered caching, and the prefix-cache tree; addressed key challenges in SWA KVCache handling; and optimized scheduling as well as the Prefill/Decode pipeline. Validated on real production traffic, these optimizations have increased effective KVCache capacity by nearly 5x, with server-side cache hit rates averaging 93%–95% across mainstream harness frameworks. Together with MoE configuration tuning and multimodal inference optimizations, they enable more efficient long-context inference and form part of what makes the recent API price cuts possible.

Can AI make portfolio optimization accessible to non-quants? We gave FPE Intelligence, @FactSet’s coding agent, one sentence: “Replicate the S&P 500 with fewer than 50 securities, sector exposures within 1% of benchmark.” Read our full article for the results:

still deep in optimization work on the system, but as all these pieces fall into place and get applied to dozens of real businesses, i can see the future where this system scales up to THOUSANDS of businesses. brain is in hyper mode on this. 🧠🚀

Automated harness optimization methods keep improving, but which scenarios you train on is usually fixed from the start. This paper makes that "curriculum" itself adaptive. Title: ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization URL: 📝 Overview ActiveSaddler reframes which training scenarios feed agent harness optimization as an automated curriculum-learning problem, adapting that selection dynamically as optimization proceeds instead of fixing it upfront. ❗ Problem it solves Fixed scenario ordering abandons unresolved weaknesses too early or wastes rollouts on already-fixed issues. The value of revisiting known weaknesses versus exploring new ones shifts during optimization, but static schedules can't track that. 🛠️ Method Curriculum selection is modeled as a non-stationary bandit with dynamically instantiated arms — each arm a failure pattern, not an individual scenario. An LLM-based Arm Prioritizer scores learning potential every iteration across severity, fixability, breadth, and side-effect risk, while an Exploration Controller adaptively decides whether to exploit known weaknesses or explore unseen scenarios based on how many actionable targets remain. 📊 Results Pass@1 reached 59.8% on GAIA2 (+4.4 points over fixed random ordering) and 80.0% on Terminal-Bench 2.0 (+7.5 points). It's also far more cost-efficient — on GAIA2 it hits a target accuracy for $298 versus $1,360 for other methods. #AgentOptimization# #CurriculumLearning#

The token optimization talk from executives is so funny to me because it exposes four realities of white collar labor Companies almost never know: 1. Who are their *actual* top performers 2. The right metrics 3. What their employees do all day 4. Which tasks drive value If you know these things the right number of tokens is roughly unlimited tokens. AI just exposes that you have no idea who should be firing them and what they should be firing them at

5 FABLE 5.1 OPTIMIZATIONS YOU CAN USE RIGHT NOW: 1. Set effort to low 2. Run /claude-api cost-optimize 3. Run claude-api prompt-audit 4. Change effort mid-conversation without a cache hit 5. Update your API config with claude-api migrate