Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Bootstrapping Task Spaces for Self-Improvement

About

Progress in many task domains emerges from repeated revisions to previous solution attempts. Training agents that can reliably self-improve over such sequences at inference-time is a natural target for reinforcement learning (RL), yet the naive approach assumes a fixed maximum iteration depth, which can be both costly and arbitrary. We present Exploratory Iteration (ExIt), a family of autocurriculum RL methods that directly exploits the recurrent structure of self-improvement tasks to train LLMs to perform multi-step self-improvement at inference-time while only training on the most informative single-step iterations. ExIt grows a task space by selectively sampling the most informative intermediate, partial histories encountered during an episode for continued iteration, treating these starting points as new self-iteration task instances to train a self-improvement policy. ExIt can further pair with explicit exploration mechanisms to sustain greater task diversity. Across several domains, encompassing competition math, multi-turn tool-use, and machine learning engineering, we demonstrate that ExIt strategies, starting from either a single or many task instances, can produce policies exhibiting strong inference-time self-improvement on held-out task instances, and the ability to iterate towards higher performance over a step budget extending beyond the average iteration depth encountered during training.

Minqi Jiang, Andrei Lupu, Yoram Bachrach• 2025

Related benchmarks

TaskDatasetResultRank
Machine learning engineeringMLE-bench (held-out task instances)
Accuracy (%)58.6
6
Mathematical ReasoningMath held-out task instances (test)
Accuracy20.4
6
Tool UseTool-use multi-turn (test)
Accuracy76.8
6
Showing 3 of 3 rows

Other info

Follow for update