…Evaluating LLM Agents in Real-World EHR Environments Published on May 4 Submitted by Ruoqi Liu on May 5 Stanford University Authors: , , , , , , , , , , , , Abstract PhysicianBench evaluates LLM agents on real clinical tasks requiring…
…The following papers were recommended by the Semantic Scholar API AgentV-RL: Scaling Reward Modeling with Agentic Verifier (2026) LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning…
…are overly sensitive to privileged tool operations. Generated by Qwen/Qwen2.5-Coder-32B-Instruct Agent skills provide a lightweight mechanism for extending general-purpose agents, but their open format exposes them…
…AI-generated summary Tool-using LLM agents fail through trajectories rather than only final responses, as they may execute unsafe tool calls, follow injected instructions, comply with harmful requests, or over-refuse…
…Existing financial agents remain turn-based and workflow-disposable. We propose InKH, a financial-agent architecture combining: an event-stream view of user/market/tool updates; a bounded working context buffer assembled…
…Step-Aware Online Preference Distillation for Agent Reinforcement Learning (2026) Learn Where Outcomes Diverge: Efficient VLA RL via Probabilistic Chunk Masking (2026) ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use…
…the strongest agent hallucinates 15.1% of its verifiable spatial claims and makes over half of its accusations without grounded evidence. We release the full engine, evaluation framework, toolkit, and logs at…
…Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows (2026) Latent Preference Modeling for Cross-Session Personalized Tool Calling (2026) KnowU-Bench: Towards Interactive, Proactive, and Personalized Mobile Agent Evaluation (2026) Remember…
This is really cool, would love to play around with this and see if can get running on Mac OS w/ a local MCP server and tool call implementations. Where are the…
…AI-generated summary As AI agents move from chat interfaces to systems that read private data, call tools, and execute multi-step workflows, guardrails become a last line of defense against concrete…