AI Paper Atlas

Research map / Large language models / Agents, code and math

EffGen: Enabling Small Language Models as Capable Autonomous Agents

Gaurav Srivastava, Aafiya Hussain, Chi Wang, Yingyan Celine Lin, Xuan Wang

ICML 2026 · Large language models › Agents, code and math · approach: Long-horizon LLM agents · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add prompt optimization (ablation)EffGen · 13-benchmark averageaverage accuracy: 36.21 -> 47.44 (1.5B)Improved
add prompt optimization (ablation)EffGen Qwen2.5-32B · 13-benchmark averageaverage accuracy: 68.54 -> 70.97Improved
add complexity routing (ablation)EffGen Qwen2.5-1.5B · 13-benchmark averageaverage accuracy: 43.87 -> 47.44Improved
add complexity routing (ablation)EffGen Qwen2.5-32B · 13-benchmark averageaverage accuracy: 63.12 -> 70.97Improved
add task decomposition (ablation)EffGen Qwen2.5-7B · 13-benchmark averageaverage accuracy: 58.42 -> 63.07Improved
add three-tier memory system (ablation)EffGen Qwen2.5-1.5B · 13-benchmark averageaverage accuracy: 45.68 -> 47.44Improved
EffGen framework versus raw ReAct (all components) (ablation)Qwen2.5-1.5B · 13-benchmark averageaverage accuracy: 34.28 -> 47.44Improved
use LangChain instead of raw modelQwen2.5-1.5B · 13-benchmark averageaverage accuracy: 34.28 -> 32.81Hurt
use agentic frameworks on GSM8K (large model)Qwen2.5-32B · GSM8Kaccuracy: 95.60 -> 95.75No clear effect
give raw model direct search tool access (Raw+Search) (ablation)Qwen2.5-1.5B · SimpleQAaccuracy: 4% -> 8% (EffGen 40%)Improved
add standard retrieval frameworks (LangChain)Qwen2.5-1.5B · ARC-Challengeaccuracy: 67.24 -> 59.13Hurt
add EffGen filtering of retrieved contentQwen2.5-1.5B · ARC-Challengeaccuracy: 67.24 -> 78.34Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy