CRITICTOOL: Evaluating Self-Critique Capabilities of Large Language Models in Tool-Calling Error Scenarios (2025 · 12 citations)
LLM agents that call external tools often run into problems during long, multi-step tasks. Existing tool-use benchmarks mostly compare final outputs with gold answers, so they do not show whether a model can notice a mistake, diagnose it and recover. The authors first examined failures on several established tool…
UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision (2026 · 11 citations)
Unified Multimodal Models (UMMs) often judge images accurately but cannot produce scenes of the same quality themselves.
Beyond Accuracy: Unveiling Inefficiency Patterns in Tool-Integrated Reasoning (2026 · 2 citations)
Agents that alternate between LLM reasoning and external tool calls are usually judged on accuracy. When efficiency is reported, it is often reduced to counting tokens or tool invocations. The authors argue that these counts misrepresent real inference latency in Tool-Integrated Reasoning (TIR). Pauses for tool…

Co-authors here

11 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 23 times (of the 149,439 papers whose bibliographies we read); 15 citing papers with a page here →.

Updated 2 November 2026