arXiv Machine Learning
Aug 11
The Range Shrinks, the Threat Remains: Re-evaluating LLM Package Hallucinations on the 2026 Frontier-Model Cohort
arXiv:2605. 17062v3 Announce Type: replace-cross Abstract: Spracklen et al.
Closed-World Resolution Against Tool Hallucination in LLM Agents
The paper investigates a new failure mode of tool‑augmented large language model agents: calling non‑existent tools with arguments that do not match any declared schema. It introduces a five‑class taxonomy of tool hallucination, presents a training‑free closed‑world resolver that checks registry membership and signatures, and demonstrates that hallucinations persist across ten hosted models and various invocation surfaces, including the Model Context Protocol. The authors release a Hallucinated‑Tools Benchmark to enable comparison of resolver methods.
Related stories
arXiv AI
Aug 5
TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic Workflows
arXiv:2608. 02680v1 Announce Type: cross Abstract: Tool-using language-model agents repeatedly rediscover procedures they have already executed, producing traces that mix reusable structure with retries, exploration, accidental ordering, and repeated lookups.
arXiv AI
Jun 9
Executable World Models for ARC-AGI-3 in the Era of Coding Agents
arXiv:2605. 05138v2 Announce Type: replace Abstract: We evaluate an initial coding-agent system for ARC-AGI-3 in which the agent maintains an executable Python world model, verifies it against previous observations, refactors it toward simpler abstractions as a practical proxy for an MDL-like simplicity bias, and plans through the model before acting.
arXiv AI
Jul 29
Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales
arXiv:2607. 25364v1 Announce Type: new Abstract: Tool-using agents expose structured calls but commonly attach free-form rationales.
arXiv AI
Sep 2
Long-Horizon State Tracking in LLMs: Executing MD5 through a Deep Sequence of Dependent Tool Calls
The paper introduces a benchmark for evaluating large language models (LLMs) on long‑horizon state tracking by having them compute the MD5 hash through 196 dependent tool calls across 64 rounds, carrying four 32‑bit words in context. It shows that a mixture‑of‑experts LLM can maintain the full state and produce correct digests in most runs, even when all primitive tools are replaced by another LLM. The study isolates state‑tracking difficulty from instruction interpretation and identifies key factors—contextual reasoning and worker voting—that enable success.
arXiv AI
Sep 10
Typed Federated Artifacts for the Agentic Web:Sharing Tool-Routing Knowledge Across Frozen,Heterogeneous LLM Agents
The paper proposes typed federated artifacts—schema‑validated objects with per‑field privacy and dispute resolution—to enable tool‑routing knowledge sharing among frozen, heterogeneous LLM agents. By replacing flat text prompts with typed fields, the authors achieve near‑centralized routing performance on StableToolBench while reducing data size to 20 MB JSON per client. The study also highlights that a simple TF‑IDF classifier can outperform LLM routing on labeled benchmarks, indicating limitations in current evaluation methods.
arXiv AI
Sep 15
When Tool Calls Succeed but Workflows Fail: Anomalies at the Agent-Tool Boundary
The paper investigates how AI agents that run long workflows using external tools can experience inconsistencies when retries, speculative execution, concurrency, or partial failures occur. It introduces an effect‑history model that distinguishes between actual external events and the agent’s observations, and catalogs eight common external‑effect anomalies. The authors analyze the standard Model Context Protocol tool interface, finding that its annotations are too coarse to fully express the necessary capabilities to prevent these anomalies, thereby motivating the need for reusable transactional contracts at the agent‑tool boundary.
arXiv AI
Aug 6
Diagnosing Tool-Selection Reasoning in LLM Agents with Canary Tools
arXiv:2608. 04719v1 Announce Type: new Abstract: Agent evaluations tell us that a model picked the wrong tool, but rarely why.
arXiv Computation and Language
Aug 31
Fidelity Is Not Enough: Dispatch-Level Instrumentation for Agentic Datasheet Extraction
The paper reports that a model can pass fidelity checks—verifying that extracted values match the source—without actually opening a datasheet, due to a hidden constraint that disables tool use. To address this, the authors log every tool call in an agentic benchmark and develop two instruments: a rule‑based failure‑attribution classifier and a silent‑failure detector that flags runs based solely on which tools were invoked. While the detector shows low false positives on clean extractions and recovers all planted faults, its recall against correct tool usage but incorrect answers remains unmeasured, and a partial causal chamber confirms only a subset of claims, highlighting limitations in physical verification.
arXiv Computation and Language
Sep 15
Fabrication After Tool Failure: Tool-Augmented Agents Assert Values Their Tools Did Not Return
arXiv:2609.14758v1 Announce Type: cross Abstract: Tool-augmented language models are evaluated on whether they reach the right answer, not on whether they report honestly when a tool fails to supply...
arXiv AI
Sep 23
APEXA: Execution-Integrity Enforcement for Multi-Agent LLM Automation of Synchrotron Data Reduction
arXiv:2609.24165v1 Announce Type: new Abstract: Synchrotron data reduction, detector calibration followed by azimuthal integration of terabyte-scale diffraction series, is a multi-step, expert-bound...
arXiv AI
Aug 11
Persistent Semantic Entities in Tool-Augmented LLM Systems
arXiv:2608. 07952v1 Announce Type: cross Abstract: Tool-augmented LLM agents can harbor implicit state that persists across sessions, activates through events, and propagates across agent boundaries---largely invisible to standard debugging.