LLM Digest

Story

arxiv_cs_lg · Nov 10, 2026 · paper

Source brief

ReTrace: Distilling Tool-Using Agents into Planner-Free Workflows

arxiv.orgNov 10, 2026
original source linked

In brief

Business process automation runs the same Standard Operating Procedure (SOP) again and again on new inputs. Large Language Model (LLM) agents can follow an SOP written in natural language, but they call an LLM to choo...

Feed lens

agent

Read the original at arxiv.org →Open in live feed Read that day’s brief

ReTrace: Distilling Tool-Using Agents into Planner-Free Workflows

Earlier in this thread 4 items

Treating the Model as an Untrusted Component: Deterministic Policy Enforcement, Human Approval and Taint Tracking Against Prompt Injection in Tool-Using Agents, with Validation on Open-Weights Models

SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection

SecureGARD: Dynamic Ontology-Guided Governance for Secure Tool-Using LLM Agents

Prefix Executability: Evaluating Tool-Using Agents Beyond Final Success