# STeCa: Step-level Trajectory Calibration for LLM Agent Learning

arXiv: https://arxiv.org/abs/2502.14276 · HTML: https://mlsanity.com/paper/2502.14276/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 34 of its 44 references that are in the map.
- First posted on arXiv 20 Feb 2025.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 30 of 34)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations](https://mlsanity.com/paper/2312.08935/) (2023)
- [Solving math word problems with process- and outcome-based feedback](https://mlsanity.com/paper/2211.14275/) (2022)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [Training Language Models to Self-Correct via Reinforcement Learning](https://mlsanity.com/paper/2409.12917/) (2024)
- [VirtualHome: Simulating Household Activities via Programs](https://mlsanity.com/paper/1806.07011/) (2018)
- [AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents](https://mlsanity.com/paper/2401.13178/) (2024)
- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://mlsanity.com/paper/2310.12823/) (2023)
- [ScienceWorld: Is your Agent Smarter than a 5th Grader?](https://mlsanity.com/paper/2203.07540/) (2022)
- [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://mlsanity.com/paper/2309.10691/) (2023)
- [FireAct: Toward Language Agent Fine-tuning](https://mlsanity.com/paper/2310.05915/) (2023)
- [Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents](https://mlsanity.com/paper/2403.02502/) (2024)
- [Recursive Introspection: Teaching Language Model Agents How to Self-Improve](https://mlsanity.com/paper/2407.18219/) (2024)
- [Language Models Meet World Models: Embodied Experiences Enhance Language Models](https://mlsanity.com/paper/2305.10626/) (2023)
- [LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models](https://mlsanity.com/paper/2311.18232/) (2023)
- [Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement](https://mlsanity.com/paper/2406.11176/) (2024)
- [Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training](https://mlsanity.com/paper/2501.11425/) (2025)
- [Learning Montezuma's Revenge from a Single Demonstration](https://mlsanity.com/paper/1812.03381/) (2018)
- [The Dawn of GUI Agent: A Preliminary Case Study with Claude 3.5 Computer Use](https://mlsanity.com/paper/2411.10323/) (2024)

## Built on by (most cited first, 30 of 37)

- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution](https://mlsanity.com/paper/2505.20732/) (2025)
- [A Survey on the Optimization of Large Language Model-based Agents](https://mlsanity.com/paper/2503.12434/) (2025)
- [GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators](https://mlsanity.com/paper/2512.19682/) (2025)
- [When Agents go Astray: Course-Correcting SWE Agents with PRMs](https://mlsanity.com/paper/2509.02360/) (2025)
- [CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution](https://mlsanity.com/paper/2604.15840/) (2026)
- [Agentic Uncertainty Quantification](https://mlsanity.com/paper/2601.15703/) (2026)
- [Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory](https://mlsanity.com/paper/2601.07470/) (2026)
- [Exploring Expert Failures Improves LLM Agent Tuning](https://mlsanity.com/paper/2504.13145/) (2025)
- [Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2506.23127/) (2025)
- [Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models](https://mlsanity.com/paper/2601.08955/) (2026)
- [HISR: Hindsight Information Modulated Segmental Process Rewards For Multi-turn Agentic Reinforcement Learning](https://mlsanity.com/paper/2603.18683/) (2026)
- [MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systems](https://mlsanity.com/paper/2605.28732/) (2026)
- [CoMAP: Co-Evolving World Models and Agent Policies for LLM Agents](https://mlsanity.com/paper/2606.02372/) (2026)
- [LLM4Cov: Execution-Aware Agentic Learning for High-coverage Testbench Generation](https://mlsanity.com/paper/2602.16953/) (2026)
- [TARSE: Test-Time Adaptation via Retrieval of Skills and Experience for Reasoning Agents](https://mlsanity.com/paper/2603.01241/) (2026)
- [TRACER: Verifiable Generative Provenance for Multimodal Tool-Using Agents](https://mlsanity.com/paper/2605.09934/) (2026)
- [BenchTrace: A Benchmark for Testing Reflection Ability and Controlled Evolution in LLM Agents](https://mlsanity.com/paper/2605.29225/) (2026)
- [HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning](https://mlsanity.com/paper/2606.10507/) (2026)
- [A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training](https://mlsanity.com/paper/2607.04574/) (2026)
- [Scaling Scientific Discovery Environments for Turn-Level Agentic RL](https://mlsanity.com/paper/2607.28990/) (2026)
- [LLM-Guided Reinforcement Learning: Addressing Training Bottlenecks through Policy Modulation](https://mlsanity.com/paper/2505.20671/) (2025)
- [Guided by Trajectories: Repairing and Rewarding Tool-Use Trajectories for Tool-Integrated Reasoning](https://mlsanity.com/paper/2601.23032/) (2026)
- [EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering](https://mlsanity.com/paper/2602.05242/) (2026)
- [Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents](https://mlsanity.com/paper/2607.12397/) (2026)
- [Interaction as Intelligence Part II: Asynchronous Human-Agent Rollout for Long-Horizon Task Training](https://mlsanity.com/paper/2510.27630/) (2025)
- [Seeing Isn't Believing: Mitigating Belief Inertia via Active Intervention in Embodied Agents](https://mlsanity.com/paper/2604.17252/) (2026)
- [Measuring Harness-Induced Belief Divergence in Multi-Step LLM Agents](https://mlsanity.com/paper/2607.04528/) (2026)
- [Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents](https://mlsanity.com/paper/2608.14339/) (2026)
- [The Unreliable Progress Bar: Can LLM Agents Reliably Report Task Progress Throughout Execution?](https://mlsanity.com/paper/2609.08589/) (2026)

## Abstract (arXiv)

Large language model (LLM)-based agents have shown promise in tackling complex tasks by interacting dynamically with the environment. Existing work primarily focuses on behavior cloning from expert demonstrations or preference learning through exploratory trajectory sampling. However, these methods often struggle to address long-horizon tasks, where suboptimal actions accumulate step by step, causing agents to deviate from correct task trajectories. To address this, we highlight the importance of timely calibration and the need to automatically construct calibration trajectories for training agents. We propose Step-Level Trajectory Calibration (STeCa), a novel framework for LLM agent learning. Specifically, STeCa identifies suboptimal actions through a step-level reward comparison during exploration. It constructs calibrated trajectories using LLM-driven reflection, enabling agents to learn from improved decision-making processes. We finally leverage these calibrated trajectories with successful trajectories for reinforced training. Extensive experiments demonstrate that STeCa significantly outperforms existing methods. Further analysis highlights that timely calibration enables agents to complete tasks with greater robustness. Our code and data are available at https://github.com/WangHanLinHenry/STeCa.