AtomSearch: Evidence-Grounded Tree Search for Agent Skill Optimization
cs.CL, cs.AI, cs.LG
Submitted: 2026-10-14
Updated: 2026-10-14
Comments: 15 pages, 5 figures, 5 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine
- SkillReducer: Optimizing LLM Agent Skills for Token Efficiency
- EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers
- LiveMathematicianBench: A Live Benchmark for Research-Level Mathematical Reasoning with Proof Sketches
- DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines
- Contrastive Reflection for Iterative Prompt Optimization
- SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
- SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation
- Self-Refine: Iterative Refinement with Self-Feedback
- Progressive Agent Skill Generation via Reinforcement Learning
- Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement
- Large Language Models as Optimizers
- SkillOpt: Executive Strategy for Self-Evolving Agent Skills
- Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
- Large Language Models Are Human-Level Prompt Engineers
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering