Trajectory Supervision for Continual Tool-Use Learning in LLMs
Most language-model training data shows final artifacts, not the process that produced them. We study a tractable version of this question in tool use: when a model learns a stream of new API domains, does keeping tool-use trajectories help compared with stripping the intermediate API trace? We fine-tune Llama 3.1 8B Instruct with QLoRA on API-Bank using four sequential domain blocks. Condition A strips previous API request/response lines from the prompt and trains the model to predict the next API call. Condition B keeps the trajectory context. In a single-seed pilot, full held-out generation evaluation shows that Condition B reaches 56.9\% final exact full-call accuracy compared with 39.2\% for Condition A. B also improves final API-name accuracy by 7.7 points. However, B uses 25.1\% more training tokens, the run uses one seed, and the task is next-call prediction rather than full dialogue success.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks
Skills have become the de facto way to enable LLM agents to perform complex real-world tasks with customized instructions, workflows, and tools, but how to learn them automatically and effectively remains unclear. We int…
Continual LearningTowards Practical Tool Usage for Continually Learning LLMs
Large language models (LLMs) show an innate skill for solving language based tasks. But insights have suggested an inability to adjust for information or task-solving skills becoming outdated, as their knowledge, stored …
Continual LearningMatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching
Tool-Integrated Reasoning (TIR) empowers large language models (LLMs) to tackle complex tasks by interleaving reasoning steps with external tool interactions. However, existing reinforcement learning methods typically re…
Reinforcement LearningAligning Multi-Trajectory Supervision with Policy Optimization for VLA Driving
Vision-language-action (VLA) driving methods increasingly combine multi-trajectory imitation learning with group-relative policy optimization (GRPO), making trajectory selection critical to final performance. However, so…
TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning
Tool-Integrated Reasoning (TIR) enables LLMs to solve complex tasks through iterative tool interactions. However, existing reinforcement learning methods often rely on trajectory-level supervision, limiting fine-grained …
Reinforcement Learning