…Repurposing Git Commit Messages as a Structured Knowledge Protocol for AI Coding Agents (2026) Test-Driven AI Agent Definition (TDAD): Compiling Tool-Using Agents from Behavioral Specifications (2026) Project Prometheus: Bridging the…
…In this paper, we equip these context optimizers with Wikipedia search and browser tools for active information seeking . We show that naively adding these tools to a standard sequential context optimization pipeline…
…Measuring Exploits in LLM Agents with Tool Use (2026) When RLHF Fails: A Mechanistic Taxonomy of Reward Hacking, Collapse, and Evaluator Gaming (2026) Debate as Reward: A Multi-Agent Reward System for…
…Gianluca Barmina , , , Lukas Galke Poech , Abstract BrainSurgery is a tool for robust and reproducible tensor manipulation of neural network checkpoints through declarative YAML plans with built-in validation. Generated by Qwen/Qwen2…
…An Extensible Agentic Framework for Benchmarking Evidence-Grounding Defects in LLM Agents (2026) Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems (2026) Towards Self-Improving Error Diagnosis in Multi-Agent…
…Rather than relying on an LLM to directly produce a final scene, Function2Scene performs iterative evaluation and refinement through a tool-augmented check-and-repair loop , combining geometric measurements , LLM-based contextual…
…Extensive experiments demonstrate that our method significantly outperforms existing baselines on fine-grained benchmarks, while maintaining the flexibility to support tool-assisted inference workflows. View arXiv page View PDF Project page GitHub…
…Adversarial Evolution of Constraint Graphs for Mathematical Reasoning Data Synthesis (2026) Scaling Agentic Capabilities via Grounded Interaction Synthesis (2026) EVE: Verifiable Self-Evolution of MLLMs via Executable Visual Transformations (2026) Knowledge-to…
…Likewise, since video technologies became widely adopted, video has served not only as a powerful tool for recording and communicating visual information, but also as a vehicle for emotions, attitudes, and social…
…diversity, difficulty, and quality, using model internals extracted with Sparse Autoencoder (SAE), an advanced mechanistic interpretability tool. Each property grounds a concrete data engineering operation: SAE-space clustering with moderate batch mixing…