Agentic Transformers Provably Learn to Search via Reinforcement Learning

arXiv cs.LG Papers

Summary

This paper theoretically studies how transformer-based policies acquire search capabilities from reinforcement learning training dynamics in a stochastic tree environment. It shows that a two-head transformer can implement depth-first search and that this mechanism emerges naturally from sparse reward signals under a depth-wise curriculum.

arXiv:2606.00183v1 Announce Type: new Abstract: Tree search is a central abstraction behind many language-agent reasoning and decision-making tasks: agents must explore actions, remember failures, and backtrack toward promising alternatives. Yet, we lack a theoretical understanding of how transformer-based policies acquire such search capabilities from the training dynamics of reinforcement learning (RL). We study this question in a stochastic $k$-ary tree environment, where an agentic transformer observes only its trajectory history through interaction and receives a terminal reward for reaching a hidden leaf goal node. We first construct a two-head transformer that implements randomized depth-first search (DFS): one head tracks previous actions, while the other detects failure outcomes and triggers backtracking. We then analyze the training dynamics of policy gradient under a depth-wise curriculum, showing that this same DFS mechanism emerges in stages from sparse reinforcement feedback without expert demonstrations. The resulting policy exhibits depth generalization: after training only on depth-$1$ and depth-$2$ trees, it succeeds on deeper full trees. We further show that, under imbalanced goal distributions, discounting the return leads to a ranked DFS policy that prioritizes higher-probability branches. Overall, our results identify a mechanistic normal form for transformer-based search, in which attention heads specialize and cooperate to extract decision-relevant traces from context and convert them into agentic action selection via RL training.
Original Article
View Cached Full Text

Cached at: 06/02/26, 03:39 PM

# Agentic Transformers Provably Learn to Search via Reinforcement Learning
Source: [https://arxiv.org/abs/2606.00183](https://arxiv.org/abs/2606.00183)
[View PDF](https://arxiv.org/pdf/2606.00183)

> Abstract:Tree search is a central abstraction behind many language\-agent reasoning and decision\-making tasks: agents must explore actions, remember failures, and backtrack toward promising alternatives\. Yet, we lack a theoretical understanding of how transformer\-based policies acquire such search capabilities from the training dynamics of reinforcement learning \(RL\)\. We study this question in a stochastic $k$\-ary tree environment, where an agentic transformer observes only its trajectory history through interaction and receives a terminal reward for reaching a hidden leaf goal node\. We first construct a two\-head transformer that implements randomized depth\-first search \(DFS\): one head tracks previous actions, while the other detects failure outcomes and triggers backtracking\. We then analyze the training dynamics of policy gradient under a depth\-wise curriculum, showing that this same DFS mechanism emerges in stages from sparse reinforcement feedback without expert demonstrations\. The resulting policy exhibits depth generalization: after training only on depth\-$1$ and depth\-$2$ trees, it succeeds on deeper full trees\. We further show that, under imbalanced goal distributions, discounting the return leads to a ranked DFS policy that prioritizes higher\-probability branches\. Overall, our results identify a mechanistic normal form for transformer\-based search, in which attention heads specialize and cooperate to extract decision\-relevant traces from context and convert them into agentic action selection via RL training\.

## Submission history

From: Yuejie Chi \[[view email](https://arxiv.org/show-email/403b6d8d/2606.00183)\] **\[v1\]**Fri, 29 May 2026 14:58:03 UTC \(1,178 KB\)

Similar Articles

Revealing Safety-Critical Scenarios for UTM via Transformer

arXiv cs.AI

This research paper proposes a transformer-based reinforcement learning framework to automatically generate safety-critical test scenarios for Unmanned Traffic Management (UTM) systems, achieving an 8× improvement in vulnerability discovery efficiency over expert-guided testing.