# Learning CLI Agents with Structured Action Credit under Selective Observation

arXiv: https://arxiv.org/abs/2605.08013 · HTML: https://mlsanity.com/paper/2605.08013/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 28 of its 79 references that are in the map.
- First posted on arXiv 8 May 2026.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 28 of 28)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Group Sequence Policy Optimization](https://mlsanity.com/paper/2507.18071/) (2025)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Kimi K2.5: Visual Agentic Intelligence](https://mlsanity.com/paper/2602.02276/) (2026)
- [SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning](https://mlsanity.com/paper/2602.08234/) (2026)
- [FireAct: Toward Language Agent Fine-tuning](https://mlsanity.com/paper/2310.05915/) (2023)
- [ZeroSearch: Incentivize the Search Capability of LLMs without Searching](https://mlsanity.com/paper/2505.04588/) (2025)
- [EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle](https://mlsanity.com/paper/2510.16079/) (2025)
- [MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory](https://mlsanity.com/paper/2601.03192/) (2026)
- [SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization](https://mlsanity.com/paper/2604.02268/) (2026)
- [Reinforcing Multi-Turn Reasoning in LLM Agents via Fine-Grained Reward Structure and Credit Assignment](https://mlsanity.com/paper/2505.11821/) (2025)
- [LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners](https://mlsanity.com/paper/2505.11942/) (2025)
- [SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution](https://mlsanity.com/paper/2505.20732/) (2025)
- [Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks](https://mlsanity.com/paper/2602.22817/) (2026)
- [GRPO-λ: Credit Assignment improves LLM Reasoning](https://mlsanity.com/paper/2510.00194/) (2025)
- [From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models](https://mlsanity.com/paper/2604.09459/) (2026)
- [ProRL Agent: Rollout-as-a-Service for RL Training of Multi-Turn LLM Agents](https://mlsanity.com/paper/2603.18815/) (2026)
- [RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback](https://mlsanity.com/paper/2603.08561/) (2026)
- [Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization](https://mlsanity.com/paper/2511.14846/) (2025)
- [What Do Agents Learn from Trajectory-SFT: Semantics or Interfaces?](https://mlsanity.com/paper/2602.01611/) (2026)
- [Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces](https://mlsanity.com/paper/2603.06713/) (2026)
- [GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning](https://mlsanity.com/paper/2604.02721/) (2026)
- [LAMMI-Pathology: A Tool-Centric Bottom-Up LVLM-Agent Framework for Molecularly Informed Medical Intelligence in Pathology](https://mlsanity.com/paper/2602.18773/) (2026)
- [ToolRLA: Multiplicative Reward Decomposition for Tool-Integrated Agents](https://mlsanity.com/paper/2603.01620/) (2026)
- [SLEA-RL: Step-Level Experience Augmented Reinforcement Learning for Multi-Turn Agentic Training](https://mlsanity.com/paper/2603.18079/) (2026)

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

- [DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent Training](https://mlsanity.com/paper/2609.04094/) (2026)

## Abstract (arXiv)

Command line interface (CLI) agents are emerging as a practical paradigm for agent-computer interaction over evolving filesystems, executable command line programs, and online execution feedback. Recent work has used reinforcement learning (RL) to learn these interaction abilities from verifiable task feedback, yet few methods exploit the native structured attributes of CLI actions as learning signals. Beyond this underused action structure, CLI learning also couples two bottlenecks for coding agents. First, the agent must identify task-relevant evidence in a large codebase from partial observations. Second, sparse terminal rewards must be assigned to the actions that shape a long multi-turn trajectory. We study these bottlenecks through shell-driven information extraction and file editing tasks. For selective observation, we introduce σ-Reveal, an inference-time mechanism that selects token-budgeted context for the same CLI. For credit assignment, we propose Action Advantage Assignment (A3), a native agentic RL method that preserves the algorithmic complexity of standard agentic RL. A3 constructs turn-level advantages from episode-level relative feedback, abstract syntax tree (AST) based action sub-chain residuals, and tree-level trajectory margins. To further evaluate this problem setting, we construct ShellOps, a verifiable dataset suite covering CLI tasks in repository environments.