cs.SENov 5, 2026

SPRING-5: Measuring Tool Documentation Repair for LLM Agents by Efficiency

Authors: Guan Zheng Huang

Organizations: Railtown AI

Abstract

Methods that repair tool documentation automatically are mostly evaluated on task accuracy. We report a benchmark that scores them on cost. SPRING-5 is 20 tool families and 344 tasks, each with a deliberately degraded specification, a hand-written honest one, a deterministic backend and an answer key, scored on calls charged against the ideal call path. A wrong answer is charged the full call budget, so this cost index largely tracks the completion rate, and we report calls per correct task beside it, which carries no such charge. Over 2,644 baseline sessions, 54% of wrong answers arrive with no rejected call, no refusal and no retry. The benchmark carries three validity instruments. A build-time ceiling assertion requires the honest specification to reach the ideal path and fails systematically on only one family. A dud rule names the families a stronger model solves cold and catches four. A directly measured noise floor shows that two evaluations of a byte-identical specification differ by a 95% factor of 0.64 to 1.56, so about one comparison in eight crosses a conventional win threshold on noise alone, and the cheap way of estimating that floor is biased by which families happen to go unedited. Against these instruments, a schema-only method closes 1% of the baseline-to-ideal cost gap, an online self-evolution loop 13%, one batch rewrite over every training transcript 33%, and a variant given correctness labels 58%. The batch advantage over the loop is the evidence it reads: held to the loop's exposure it is no longer detectable. With five and ten tools in context the effect survives, the baseline cost does not change, and only machine-written descriptions sent calls to the wrong tool. On BFCL, 62% of held-out queries are already answered from the shipped documentation, which explains a pooled null there. Code, data and runs are released.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Jul 6, 2026

ToolFailBench: Diagnosing Tool-Use Failures in LLM Agents

Tool calling is central to modern language model agents, but aggregate benchmark scores often hide where tool use fails. A model that never calls a needed tool and a model that calls the tool but ignores the result can look similar under final task accuracy. We introduce ToolFailBench, a diagnostic benchmark for measuring tool-use failures across 1,000 tasks in finance, medicine, law, cybersecurity, and real estate. Tool-required tasks return values the model wouldn't guess, forcing it to trust the tool while control tasks attach the same tools but should be answered directly. We label each trace with Tool-Skip, Result-Ignore, Output-Fabrication, and Unnecessary-Tool-Use, using a rule classifier and two LLM judges aggregated by majority vote. Across 19 headline models, the best reaches 86.33% Clean Tool-Use Rate, showing that faithful tool use is not saturated. More importantly, models with similar aggregate scores fail in different ways: most stay disciplined on no-tool controls, while Llama-3.1 models show an Always-Call pattern, and at the same parameter scale Llama-3.1-70B and Qwen2.5-72B differ by 89 percentage points on control-task accuracy. Tool-use evaluation should measure not only whether agents call tools, but whether they use tool outputs correctly and avoid tools when none is needed.
Apr 2, 2026

ToolMisuseBench: An Offline Deterministic Benchmark for Tool Misuse and Recovery in Agentic Systems

Tool using agents often fail for operational reasons even when language understanding is strong. Common causes include invalid arguments, interface drift, weak recovery, and inefficient retry behavior. We introduce ToolMisuseBench, an offline deterministic benchmark for evaluating tool misuse and recovery under explicit step, call, and retry budgets. The benchmark covers CRUD, retrieval, file, and scheduling environments with replayable fault injection. It reports success, invalid call behavior, policy violations, recovery quality, and budgeted efficiency. We release a public dataset with 6800 tasks and a reproducible evaluation pipeline. Baseline results show fault specific recovery gains for schema aware methods, while overall success remains limited under the released authorization and hard failure settings.
May 10, 2026

LLM Agents Already Know When to Call Tools -- Even Without Reasoning

Tool-augmented LLM agents tend to call tools indiscriminately, even when the model can answer directly. Each unnecessary call wastes API fees and latency, yet no existing benchmark systematically studies when a tool call is actually needed. We propose When2Tool, a benchmark of 18 environments (15 single-hop, 3 multi-hop) spanning three categories of tool necessity -- computational scale, knowledge boundaries, and execution reliability -- each with controlled difficulty levels that create a clear decision boundary between tool-necessary and tool-unnecessary tasks. We evaluate two families of training-free baselines: Prompt-only (varying the prompt to discourage unnecessary calls) and Reason-then-Act (requiring the model to reason about tool necessity before acting). Both provide limited control: Prompt-only suppresses necessary calls alongside unnecessary ones, and Reason-then-Act still incurs a disproportionate accuracy cost on hard tasks. To understand why these baselines fail, we probe the models' hidden states and find that tool necessity is linearly decodable from the pre-generation representation with AUROC 0.89--0.96 across six models, substantially exceeding the model's own verbalized reasoning. This reveals that models already know when tools are needed, but fail to act on this knowledge during generation. Building on this finding, we propose Probe&Prefill, which uses a lightweight linear probe to read the hidden-state signal and prefills the model's response with a steering sentence. Across all models tested, Probe&Prefill reduces tool calls by 38% with only 1.7% accuracy loss, while the best baseline at comparable accuracy only reduces 6% of tool calls, or achieves a similar tool call reduction but incurs a 5×\times higher accuracy loss. Our code is available at https://github.com/Trustworthy-ML-Lab/when2tool