From Failure to Mastery: Generating Hard Samples for Tool-use Agents
The advancement of LLM agents with tool-use capabilities requires diverse and complex training corpora. Existing data generation methods, which predominantly follow a paradigm of random sampling and shallow generation, often yield simple and homogeneous trajectories that fail to capture complex, implicit logical dependencies. To bridge this gap, we introduce HardGen, an automatic agentic pipeline designed to generate hard tool-use training samples with verifiable reasoning. Firstly, HardGen establishes a dynamic API Graph built upon agent failure cases, from which it samples to synthesize hard traces. Secondly, these traces serve as conditional priors to guide the instantiation of modular, abstract advanced tools, which are subsequently leveraged to formulate hard queries. Finally, the advanced tools and hard queries enable the generation of verifiable complex Chain-of-Thought (CoT), with a closed-loop evaluation feedback steering the continuous refinement of the process. Extensive evaluations demonstrate that a 4B parameter model trained with our curated dataset achieves superior performance compared to several leading open-source and closed-source competitors (e.g., GPT-5.2, Gemini-3-Pro and Claude-Opus-4.5). Our code, models, and dataset will be open-sourced to facilitate future research.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Generating camera failures as a class of physics-based adversarial examples
While there has been extensive work on generating physics-based adversarial samples recently, an overlooked class of such samples come from physical failures in the camera. Camera failures can occur as a result of an ext…
Reliable and diverse evaluation of LLM medical knowledge mastery
Mastering medical knowledge is crucial for medical-specific LLMs. However, despite the existence of medical benchmarks like MedQA, a unified framework that fully leverages existing knowledge bases to evaluate LLMs' maste…
DiversityMedQALabrador: Exploring the Limits of Masked Language Modeling for Laboratory Data
In this work we introduce Labrador, a pre-trained Transformer model for laboratory data. Labrador and BERT were pre-trained on a corpus of 100 million lab test results from electronic health records (EHRs) and evaluated …
Language ModelingLanguage ModellingMasked Language ModelingTransfer LearningGenerating Counterfactual Hard Negative Samples for Graph Contrastive Learning
Graph contrastive learning has emerged as a powerful tool for unsupervised graph representation learning. The key to the success of graph contrastive learning is to acquire high-quality positive and negative samples as c…
Contrastive LearningcounterfactualGraph LearningGraph Representation Learning+1AdversaBench: Automated LLM Red-Teaming with Multi-Judge Confirmation and Cross-Model Transferability
Scaling adversarial evaluation of large language models requires both a method for generating hard inputs and a reliable way to confirm that resulting failures are real. We present AdversaBench, an end-to-end red-teaming…