arXiv Computation and Language
LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Sep 25
Stale Does Not Mean Unsafe: Guard Precision for Tool-Using LLM Agents under Infrastructure State Races
The paper investigates how tool‑using language‑model agents can safely commit changes to infrastructure when external state may change between read and commit. By distinguishing invalidating races from predicate‑preserving and irrelevant ones, the authors evaluate three commit‑time guard granularities—global epoch, read‑set version, and semantic commit predicate—using a deterministic simulator and three quantized model families. The study finds that only the complete predicate guard consistently eliminates unsafe commits, while freshness‑based guards block a large proportion of benign races and model‑side signals fail to replace precise semantic enforcement.
arXiv Computation and Language
Sep 23
FIRE: Failure-Informed Runtime Engineering for Reliable Language-Model Agents
arXiv:2609.26048v1 Announce Type: cross Abstract: Language-model agents often reach a working solution and then fail to consistently deliver it. We study runtime policies: targeted natural-language i...
arXiv AI
Aug 5
Designing for Doubt: The Case for Informed Abstention in Autonomous Agents
arXiv:2606. 02965v2 Announce Type: replace Abstract: As large language models gain tool access and are deployed as autonomous agents capable of editing records, executing transactions, and modifying infrastructure, we still evaluate them based on the sole metric of task completion.
arXiv AI
Jun 19
LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents
arXiv:2606. 20529v1 Announce Type: new Abstract: Policy-adherent tool-calling agents in customer-service domains must maintain task states across turns while calling tools and obeying domain policies.
arXiv AI
Oct 15
When "Must" Becomes "Maybe": Erosion of Workflow Constraints in LLM Agent Handoffs
arXiv:2608.24569v2 Announce Type: replace Abstract: Large language model (LLM) agents build on one another's work through summaries, plans, and other intermediate artifacts. These records let a downs...
arXiv AI
Oct 21
Local Allow, Global Deny: Why Per-Action Authorization Does Not Compose in LLM Agents
arXiv:2610.27620v1 Announce Type: cross Abstract: Autonomous LLM agents act through tools under per-action authorization: a local guard screens each tool call in isolation. We show that local authori...