Search “Reasoning”

English translation is being prepared.

TinyFish Makes Search Free: Breaking Down the Real Cost of AI Agents Reading Web Pages

TinyFish announced that, within limits, it will waive retrieval fees for Search and Fetch: Search is limited to 30 requests per minute and 500 per hour, while Fetch is limited to 150 URLs per minute and 1,000 per day. The article notes that free retrieval does not eliminate the inference costs of downstream models; the same article of about 4,300 characters returns an estimated 1,184 to 42,774 tokens across different providers, and three pages of unfiltered content can fill a 128K context window. In the September 28, 2026 Artificial Analysis snapshot, TinyFish Search scored 71 at $9.30 per 1,000 tasks, the lowest total cost among the displayed configurations but also the lowest score, with about 59 seconds per task.

English translation is being prepared.

A Guide to "Agent Engineering in Practice: Eight Lectures": Engineering Methods from Working Prototype to Production-Ready

The Tencent Cloud Developer Community has published a guide to "Agent Engineering in Practice: Eight Lectures," centered on how to upgrade a prototype capable of calling models and tools into a system that can complete business tasks, explain failures, control costs, and iterate continuously. The series runs through two fictional teaching cases—a case-filing assistant Agent and a postoperative follow-up Agent—covering eight topics: task contracts, reasoning and collaboration, context and memory, reliable tool execution, observability and replay, evaluation and calibration, security boundaries, and production operations. The article emphasizes that a model being able to suggest the next step does not mean the system can deliver business results; the example fields, budgets, and figures are all teaching calculations and do not constitute legal advice.

English translation is being prepared.

Google Gemini 4 Argon scores 97.5% on ARC-AGI-3, but drops to 49.8% when the test environment is changed

Google DeepMind's new frontier model Gemini 4 Argon scored 97.5% on ARC-AGI-3 in the Provider Adapter Harness test environment at a cost of $4,800, becoming the second lab after OpenAI to cross 95%, second only to GPT-6 Astra's 99.9%. Under the Standard Harness, which allows only simple notes, the low-reasoning setting's score dropped to 49.8%, and due to API issues it was unable to complete all 55 games. On Epoch AI's ECI index, Argon scored 165, on par with Fable 5.1, but ranked eighth on the math ECI and sixth on the software engineering index.

English translation is being prepared.

ARC Prize announces evaluation results of Gemini 4 Argon on the ARC-AGI series

ARC Prize announces the validated results of Google Gemini 4 Argon on ARC-AGI: ARC-AGI-3 reaches 97.5% (provider adapter harness, cost $4.8K), and 49.8% under the standard harness (cost $5.8K); ARC-AGI-2 is 91.3%, at $0.32 per task; ARC-AGI-1 is 98.5%, at $0.16 per task. ARC Prize states that Google DeepMind is the second frontier AI lab to exceed 95% on ARC-AGI-3, and Argon's 97.5% is second only to GPT-6 Astra's 99.9%. The standard harness test failed to complete all 55 games due to API issues, and the high reasoning tier completed only 19 games so no score was published; costs are calculated at the current discounted price of $2 per million input tokens and $10 per million output tokens.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

How Cerebras Keeps Autoresearch Loops From Going Off Track: Lessons From 71 Experiments

Cerebras had an AI agent run 71 experiments across two task types—training optimization and model compression—and found that when the loop scope is tightened, it reliably produces real conclusions, while once the guardrails are loosened, the agent drifts from the goal within hours. In experiment one, codex-autoresearch-harness was used to wrap Codex in a bash loop; GPT-5.4 and Codex-Spark each independently converged on a learning-rate warmdown schedule within 6 hours, but GPT-5.4 had a proposal acceptance rate of 67% versus only 17% for Spark, showing that proposal quality determines total cost more than single-inference speed. In experiment two, REAP plus INT4 quantization compressed a 717 GB model to 92 GB, with dynamic expert swap-in/swap-out taking 0.151 seconds, but after 12 hours of unattended operation the agent changed to asking a different question on its own; the authors corrected this by clearing context, isolating directories, and adding more frequent validation checkpoints.