Pith. sign in

REVIEW 5 cited by

STeCa: Step-level Trajectory Calibration for LLM Agent Learning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.14276 v2 pith:6TIBPTEM submitted 2025-02-20 cs.LG cs.AIcs.CL

Hanlin Wang , Jian Wang , Chak Tou Leong , Wenjie Li This is my paper · ORCID
classification cs.LGcs.AIcs.CL
keywords agentscalibrationstecatrajectorieslearningstep-leveltaskstrajectory
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Leveraging Trajectory Graphs for Pre-Execution Error Diagnosis in Agentic LLM Systems

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Modeling agent trajectories as action-centric probabilistic graphs lets a GNN warn LLM agents of likely step-level errors before execution, improving pass ratio ~14.7% across four benchmarks.

  2. Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning

    cs.CL 2025-06 conditional novelty 6.0 of 10

    A 7B LLM trained with sparse completion rewards and a GRPO-style algorithm reaches state-of-the-art on ALFWorld and ScienceWorld.

  3. LLM-Guided Reinforcement Learning: Addressing Training Bottlenecks through Policy Modulation

    cs.AI 2025-05 conditional novelty 6.0 of 10

    An LLM identifies critical states, suggests corrective actions, and assigns shaped rewards to refine an existing RL policy, beating several baselines in Pong and MuJoCo.

  4. Bridging Inference-Time Scaling and Episodic Memory with Action-Centric Graphs

    cs.AI 2026-07 conditional novelty 5.0 of 10

    Graph-based action memory with dual-stream TD learning improves best-of-N inference scaling for LLM agents, reporting +20.81% success / +6.17% progress over vanilla baselines.

  5. SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution

    cs.CL 2025-05 conditional novelty 4.0 of 10

    SPA-RL attributes a single final task reward to individual agent steps and uses the attributions plus an executability signal as dense rewards for PPO, yielding modest success-rate gains on WebShop, ALFWorld, and VirtualHome.

Pith tools