AITOPAI热报
PapersSelected

Researchers Make Skill Granularity a Runtime Decision for Coding Agents

DAIR.AI@dair_ai
Post
View the post
Why we picked it

Fixed macro execution works only when the skill matches the task; making granularity adaptive turns brittle agent failures into recoverable ones. Developers building coding agents can apply the macro-to-micro fallback pattern to improve reliability without hand-tuning heuristics. The learned router beating a hand-written heuristic on the 12-task study shows the approach scales beyond scripted workflows.

Researchers propose treating skill granularity as a runtime decision for coding agents rather than a fixed design choice. For each task, the agent can use primitive tool calls, a macro skill, or a macro skill that falls back to primitive steps on failure. A controller selects the granularity based on task structure, execution state and earlier macro failures, while a finite-state executor handles fallback as an explicit transition. In a 12-task routing study, a learned router reached 100% success where a hand-written heuristic failed.

Original · DAIR.AI

Nice work on using skills more effectively for coding agents.

(bookmark it)

In this work, researchers treat skill granularity as a runtime decision. For each task, the agent can use primitive tool calls, a macro skill, or a macro skill that falls back to primitive steps when it fails.

Fixed macro execution is efficient when the skill fits and brittle when it does not.

The controller picks the level from task structure, execution state, and earlier macro failures, and a finite-state executor handles the fallback as an explicit transition instead of an informal retry.

In a 12-task routing study, a learned router reaches 100% success where a hand-written heuristic fails. With macro-to-micro fallback, the agent recovers controlled macro failures that fixed granularity leaves unresolved.

https://t.co/Ze4OjNcK5S

Chat with Paper: https://t.co/yfLayeF1pT

#coding assistants#agents#skills

Keep reading

Recent stories with the same tag or section
PapersBuildersSelected21:02
EC²-Bench benchmarks edge-cloud collaboration for long-horizon agents

Cost and privacy trade-offs in agent execution do not move together — once task completion converges, strategy choice is mostly a privacy decision, and the best-scoring setup is also the most exposed. Teams deploying on-device agents can pick a collaboration mode based on edge model size: route execution to the cloud for small models, use cloud advisory for 9B-class ones. The comparison against Tsinghua-affiliated GLM-5.3 makes the findings directly applicable to Chinese open-source model stacks.

#EC2-Bench#OpenBMB#GLM-5.3#Qwen
OpenBMB@OpenBMBSource
PapersBuildersSelected17:32
University of Chicago Paper Finds LLMs Misreport Their Own Cruxes

Sampling multiple answers and diffing them beats asking a model to explain itself — a cheap workflow change that applies to any high-stakes LLM use like research triage or forecasting. The 86x compute saving from the reranker makes it practical to run on everyday tasks. Practitioners building review pipelines or agent self-checks in Singapore and the wider ASEAN developer community can adopt this with any API-based model.

#LLM evaluation#reasoning models#Metaculus#University of Chicago
rohanpaul_ai@rohanpaul_aiSource
PapersBuildersSelected08:33
Meta and Carnegie Mellon RL-trained 8B Qwen3 beats 402B Maverick on tool picking

The result argues that tool selection can be moved off the flagship model entirely: a small RL-trained selector handles catalogs of 10,000+ tools that cannot fit in context, where retrievers alone rank only by relevance. Teams building agents with large tool catalogs can swap in a lightweight selector while keeping their main model unchanged. The performance gap over a prompted 402B model, 41.5% versus 30.6% exact picks, makes the cost saving concrete.

#Qwen3#Llama-4-Maverick#ToolBench#agents
Event
rohanpaul_ai@rohanpaul_ai2 sourcesSource