mlsanityData to 7 Oct 2026

Callability Is Not Operability: Controlled Interface Interventions for LLM Agents

arXiv 2608.23628 ↗First posted 23 Aug 2026cs.SEcited by 0

On the map: LLM agents and tool use → Tool learning and function calling

Abstract (arXiv)

A tool call can be perfectly valid yet still leave an autonomous agent unable to determine what to do next. For example, if an external effect commits but its response is lost, committed and uncommitted states may become indistinguishable to the agent even though they require different continuation actions. We study this gap between callability and operability: whether a tool interface exposes the action-relevant state and semantics needed for an agent to continue safely under operational uncertainty. We operationalize tool operability through Agent-First Tooling (AFT), a set of interface mechanisms spanning selective capability discovery, execution lifecycle and recovery, explicit external-effect semantics, machine-readable results, and postcondition verification. We introduce AFT-Bench, a controlled interface-intervention framework that holds the task, backend, initial state, injected failure, agent, and language model fixed while varying the interface exposed to the agent.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 9 of its 16 references that are in the map. First posted on arXiv 23 Aug 2026.

Builds on

9 of 16 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026Verified Tool Calls Improve LLM Agent Reliability Under Non-Atomic Failures31 Jul
  2. 2026Schema First Tool APIs for LLM Agents: A Controlled Study of Tool Misuse, Recovery, and Budgeted Performance12 Mar

Other references · 7

  1. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,280
  2. 2024ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilitiescited by 272
  3. 2025OSWorld-Human: Benchmarking the Efficiency of Computer-Use Agentscited by 37
  4. 2026Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflowscited by 27
  5. 2026Cordon: Semantic Transactions for Tool-Using LLM Agentscited by 19
  6. 2026CLI-Anything: Towards Agent-Native Computer Usecited by 7
  7. 2026Agent-First Tool API: A Semantic Interface Paradigm for Enterprise AI Agent Systemscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026How Consistent Are LLM Agents? Measuring Behavioral Reproducibility in Multi-Step Tool-Calling Pipelines
  2. 2026AgentAbstain: Do LLM Agents Know When Not to Act?
  3. 2026The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration
  4. 2026LLM Agents Already Know When to Call Tools -- Even Without Reasoning
  5. 2026KAIJU: An Executive Kernel for Intent-Gated Execution of LLM Agents
  6. 2026Beyond Function Calling: Benchmarking Tool-Using Agents under Tool-Environment Unreliability
  7. 2026Robust and Efficient Tool Orchestration via Layered Execution Structures with Reflective Correction
  8. 2025Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations