Skip to content

Breaking the Environment Wall: Evolving LLM Agent Environments for Recursive Self-Improvement

Sep 2026 · 0 citations · 19 references
Computer Science

TL;DR

Env-Rethink is proposed, a system with 27B post-trained model that supports three main capabilities that adaptively builds Collection Maps and Event Logs to supplement necessary context and evolves environments through virtual event histories that alter environmental states and evidence relationships.

Abstract

Many real-world tasks (e.g., office workflows, scientific experimentation) require LLM agents to interact repeatedly with their environments for context-dependent operations. However, such environments are often not agent-ready. First, information is often scattered and fragmented across the environment. Second, relevant evidence in the environment is often mixed with misleading information and conflicting versions. Third, environments evolve over time, introducing new noise and more challenging tasks. These challenges can substantially degrade performance for state-of-the-art AI agents (e.g., from 83.9% to 57.6%). To address these challenges, we propose Env-Rethink (a system with 27B post-trained model) that supports three main capabilities: (1) It adaptively builds Collection Maps (for organizing related files) and Event Logs (for contextualizing cross-data relationships) to supplement necessary context; (2) It further leverages the post-trained model (through offline trajectory learning) to identify underlying noise issues in the environment; (3) It ultimately evolves environments through virtual event histories that alter environmental states and evidence relationships, producing more tricky ones for further agent improvement. Experiments show that Env-Rethink can effectively improve downstream task performance (with over 15.1% rubric pass rate improvement across nine models on 30 tasks).

View source

Similar papers

Preprint Sep 2026

Breaking the Environment Wall: A Unified Framework for Preparing and Evolving Agent-Native Environments

Env-Rethink is proposed, a system with 27B post-trained model that supports three main capabilities that adaptively builds Collection Maps and Event Logs to supplement necessary context and evolves environments through virtual event histories that alter environmental states and evidence relationships.

Yu-Kai Wu, Yuan-Jing Yang, Leon Zhou et al. · 0 citations
#artificial intelligence Preprint Aug 2026

Learning Simple Test-Time Environments for LLM Web Agents

This work proposes that LLM web agents can learn simple environment observations at test time, and introduces trial steps for agents to decompose a complex environment observation into sub-modules, and implements a label-free learning method, Test-Time Environment Decomposition (TTED), to adapt agent behaviors with exp...

Jun-Xuan Li, Zijun Liu, Zi-Yi Huang et al. · 0 citations

AnyAct: Universal Action for Self-Evolving Agents

AnyAct is a universal action layer that unifies available capabilities into a self-evolving action space, enabling agents to operate efficiently and reliably in large-scale, dynamic tool ecosystems and optimizes for a balance between task success rate and execution cost.

Ling-Rui Xu, Ya Jiang, Jia-Chang Zhang et al. · 0 citations

RefCon: Iterative Refinement and Contrastive Memory Extraction for Context-Evolving Agent

This work proposes RefCon, which combines sequential self-refinement with parallel self-contrast to extract higher-quality memories without gold labels, and generalizes across model scales and to software engineering tasks, where it surpasses even ground-truth baselines.

Ubaidillah Ariq Prathama, Bo Liu, Yeonsun Hong et al. · 0 citations
Conference Open access Sep 2026

A Review on Test-Time Scaling for Agentic Large Language Models

A novel RAIE taxonomy along four scaling dimensions is proposed, which optimizes the entire thought process through search algorithms and self-verification, and introduces a task-oriented guideline for choosing the best TTS strategy.

Jia-Yu An, Zheng Chen, Yong-Cheng Jing et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.