# Agent-UCT: Upper Confidence Bounds Applied to Trees for Agentic Workflow Optimization with Cost-Awareness

arXiv: https://arxiv.org/abs/2607.24162 · HTML: https://mlsanity.com/paper/2607.24162/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation.
- Builds on 2 of its 5 references that are in the map.
- First posted on arXiv 27 Jul 2026.

## Placed in

- Retrieval-augmented generation / [Agentic RAG, agents and memory](https://mlsanity.com/rag/agentic-rag-agents-and-memory/)
- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 2 of 2)

- [LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs](https://mlsanity.com/paper/2406.15319/) (2024)
- [Bandit Algorithms for Tree Search](https://mlsanity.com/paper/1408.2028/) (2014)

## Built on by (most cited first, 1 of 1)

- [ASCT: Attentive Search over Counterfactual Trees for Credit Assignment in Agentic Reinforcement Learning](https://mlsanity.com/paper/2609.35215/) (2026)

## Abstract (arXiv)

Workflow search pays for complete quality observations, whose execution cost changes as reusable prefixes accumulate. AgentUCT uses an economic model of the remaining evaluation cost to guide UCT selection while backing up raw quality. Query-prefix accounting connects the search decisions to reusable execution state. For finite fixed-reward trees with bounded adaptive cold-cost estimates and successful persistent caching, we prove an O(log T) bound on cumulative quality regret over T complete evaluations. Across five paired seeds, AgentUCT achieves 69.57% test F1 versus 68.01% for UCT at a 32M weighted-token budget on a retrospective HotpotQA panel. On GSM8K, it reaches 93.07% mean accuracy at the first budget, compared with 92.60% for UCT and 91.60% for AFlow. Single-factor RAG controls show that online prices and historical continuations improve the selected workflows at equal retained evaluation counts.