Paper page - Towards Automating Scientific Review with Google's Paper Assistant Tool
… As a step toward this future, we introduce the Paper Assistant Tool PAT , an agentic AI framework built for deep scientific review and verification. …
Search
Paper page - A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks
… This enables sampling valid tool sequences that cover a vast range of tool combinations. …
Paper page - ToolSense: A Diagnostic Framework for Auditing Parametric Tool Knowledge in LLMs
… The following papers were recommended by the Semantic Scholar API Internalizing Tool Knowledge in Small Language Models via QLoRA Fine-Tuning 2026 NTILC: Neural Tool Invocation via Learned Compression 2026 Diagnosing Knowledge Gaps in LLM Tool Use: An Agentic Benchmark for Novel API Acquisition 202… …
Paper page - Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification
… Generated by Qwen/Qwen2.5-Coder-32B-Instruct LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks. …
Paper page - RocketSmith: Agentic Additive Manufacturing of High-Powered Rockets
… The following papers were recommended by the Semantic Scholar API EngiAI: A Multi-Agent Framework and Benchmark Suite for LLM-Driven Engineering Design 2026 Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design 2026 AerialClaw: An Open-Source Framework for LLM-Driv… …
Paper page - SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning
… At its core is SimCoder , a tool/skill-augmented coding agent that writes and executes engine-level code to construct physically grounded 3D worlds from language/image instructions. …
Paper page - An Empirical Study of Automating Agent Evaluation
… AI-generated summary Agent evaluation requires assessing complex multi-step behaviors involving tool use and intermediate reasoning, making it costly and expertise-intensive. …
Paper page - MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment Simulation
… The following papers were recommended by the Semantic Scholar API ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox 2026 EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL 2026 UniToolCall: Unifying Tool-Use Representa… …
Paper page - The Last Harness You'll Ever Build
… The framework shifts manual harness engineering into automated harness engineering, and takes one step further—automating the design of the automation itself. …
Paper page - ScrambleToolBench: Agents Search Exhaustively Even When Their Own Map Points to the Next Step
… Unveiling the Fragility of Static Training in Tool Use 2026 STAGE-Claw: Automated State-based Agent Benchmarking for Realistic Scenarios 2026 MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents 2026 AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-W… …