# token savings

Published articles for token savings.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Resolution as Attention for Efficient Agent Memory Perception

DevFeed: [Resolution as Attention for Efficient Agent Memory Perception](<https://devfeed.tech/articles/resolution-as-attention-for-efficient-agent-memory-perception-142794.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.24422>)

Author: Siqi Xiang, Zhipeng Xu, Shengrui Liu, Zulong Chen, Chunyan Miao, Shijian Lu

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-memory](<https://devfeed.tech/tags/agent-memory.md>), [agents](<https://devfeed.tech/tags/agents.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [attention](<https://devfeed.tech/tags/attention.md>), [computer-science](<https://devfeed.tech/tags/computer-science.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [layer](<https://devfeed.tech/tags/layer.md>), [llm](<https://devfeed.tech/tags/llm.md>), [management](<https://devfeed.tech/tags/management.md>), [mechanism](<https://devfeed.tech/tags/mechanism.md>), [memory](<https://devfeed.tech/tags/memory.md>), [memory-management](<https://devfeed.tech/tags/memory-management.md>), [multiple](<https://devfeed.tech/tags/multiple.md>), [performance](<https://devfeed.tech/tags/performance.md>), [relevance](<https://devfeed.tech/tags/relevance.md>), [tasks](<https://devfeed.tech/tags/tasks.md>), [token](<https://devfeed.tech/tags/token.md>), [token-consumption](<https://devfeed.tech/tags/token-consumption.md>), [token-savings](<https://devfeed.tech/tags/token-savings.md>)

### AI overview

Resolution as Attention (RAA) allocates perceptual detail across an agent's interaction history by rendering past interactions as images and adjusting each image's resolution according to its relevance to the next decision. A lightweight relevance estimator is trained with teacher guidance and optimized to preserve decision consistency while reducing visual-token use. The abstract reports over 50% lower token consumption without compromising task performance across multiple tasks and backbones. RAA can also be added as a perception layer to existing memory-management methods for further token savings. These claims are based on the supplied abstract; it gives no task-level results or implementation details.

### Source excerpt

arXiv:2611.24422v1 Announce Type: new Abstract: LLM-based agents accumulate extensive interaction histories when solving complex, long-horizon tasks, making efficient memory management critical to their performance and scalability. While existing memory management methods primarily focus on what to retain or retrieve, they often overlook how much perceptual detail should be allocated to individual past interactions. We posit that effective agent memory depends not only on the information preserved, but also on the granularity at which each past interaction is perceived. Motivated by this insight, we propose Resolution as Attention (RAA), a memory perception mechanism that uses visual resolution as a means of attention allocation across interaction histories. RAA renders past interactions as images and dynamically adjusts their resolution at every step according to their relevance to the agent's upcoming decision, preserving fine-grained information for critical interactions while reducing visual-token consumption for less relevant ones. To adaptively determine the perceptual fidelity of each interaction, we train a lightweight relevance estimator with teacher-model guidance and further optimize it to preserve the agent's decision consistency at a reduced visual-token cost. Experiments across multiple tasks and backbones show that RAA reduces token consumption by over 50% without compromising task performance. Moreover, RAA can be integrated as a plug-in perception layer with existing memory management methods, yielding further token savings and revealing adaptive perception as a complementary dimension of agent memory.

## Making Local AI Smarter and Faster

DevFeed: [Making Local AI Smarter and Faster](<https://devfeed.tech/articles/making-local-ai-smarter-and-faster-55162.md>)

Original publisher: [Read original article](<https://blog.jetbrains.com/junie/2026/09/smarter-local-al/>)

Author: Vladimir Sotnikov

Published: 2026-09-18T13:42:27Z

Content type: release

Language: en

Sources: [JetBrains](<https://devfeed.tech/sources/the-jetbrains-blog.md>)

Topics: [Local AI](<https://devfeed.tech/topics/local-ai.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [junie](<https://devfeed.tech/topics/junie.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [qwen](<https://devfeed.tech/topics/qwen.md>), [Nvidia](<https://devfeed.tech/topics/nvidia.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [data-science](<https://devfeed.tech/tags/data-science.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [junie](<https://devfeed.tech/tags/junie.md>), [local-ai](<https://devfeed.tech/tags/local-ai.md>), [ml](<https://devfeed.tech/tags/ml.md>), [nvidia](<https://devfeed.tech/tags/nvidia.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [release](<https://devfeed.tech/tags/release.md>), [releases](<https://devfeed.tech/tags/releases.md>), [token-savings](<https://devfeed.tech/tags/token-savings.md>), [update](<https://devfeed.tech/tags/update.md>), [updates](<https://devfeed.tech/tags/updates.md>), [windows](<https://devfeed.tech/tags/windows.md>)

### AI overview

This release introduces a blended local coding model for Junie Local by merging Qwen3.6 and Qwen3.8 weights in equal proportions. In an internal 100-task coding benchmark, it completed 37 tasks, compared with 34 for Qwen3.6 with reasoning disabled and 39 for Qwen3.8, while generating 71% fewer output tokens than Qwen3.8. The update also adds experimental NVIDIA support on Windows.

### Source excerpt

We want local coding agents to be smart and fast, with the ability to understand a codebase, do useful work, and finish tasks without long waits. This Junie Local update makes it practical to use a more capable model on your own machine. In the first release, we had to choose between two versions of [...]

## Tokenomics of quality: switch sonar list issues to --format toon for measured token savings

DevFeed: [Tokenomics of quality: switch sonar list issues to --format toon for measured token savings](<https://devfeed.tech/articles/tokenomics-of-quality-switch-sonar-list-issues-to-format-toon-for-measured-token-savings-50237.md>)

Original publisher: [Read original article](<https://www.sonarsource.com/blog/tokenomics-of-quality/>)

Author: Prasenjit Sarkar

Published: 2026-08-17T13:00:00Z

Content type: article

Language: en

Sources: [Sonar Blog](<https://devfeed.tech/sources/sonar-blog.md>)

Topics: [JSON](<https://devfeed.tech/topics/json.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>)

Tags: [agentic-development](<https://devfeed.tech/tags/agentic-development.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [ai-coding-tools](<https://devfeed.tech/tags/ai-coding-tools.md>), [ai-cost-optimization](<https://devfeed.tech/tags/ai-cost-optimization.md>), [code-quality](<https://devfeed.tech/tags/code-quality.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [data-formatting](<https://devfeed.tech/tags/data-formatting.md>), [developer-productivity](<https://devfeed.tech/tags/developer-productivity.md>), [finops](<https://devfeed.tech/tags/finops.md>), [json](<https://devfeed.tech/tags/json.md>), [json-vs-toon](<https://devfeed.tech/tags/json-vs-toon.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-token-usage](<https://devfeed.tech/tags/llm-token-usage.md>), [sonar-list-issues](<https://devfeed.tech/tags/sonar-list-issues.md>), [sonar-vortex](<https://devfeed.tech/tags/sonar-vortex.md>), [sonarqube](<https://devfeed.tech/tags/sonarqube.md>), [sonarqube-cli](<https://devfeed.tech/tags/sonarqube-cli.md>), [token-efficiency](<https://devfeed.tech/tags/token-efficiency.md>), [token-optimization](<https://devfeed.tech/tags/token-optimization.md>), [token-oriented-object-notation](<https://devfeed.tech/tags/token-oriented-object-notation.md>), [token-savings](<https://devfeed.tech/tags/token-savings.md>), [toon-format](<https://devfeed.tech/tags/toon-format.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

This article explains how replacing JSON with TOON, a compact encoding for LLM input, can reduce token usage when AI coding agents process structured data such as issue lists. It describes the format, compares representative payload sizes, and cites benchmark results for uniform datasets.

### Source excerpt

See how sonar list issues with TOON reduces token usage while preserving data and comprehension for AI coding agents and automated workflows.