AI Paper Atlas

Research map / Large language models / Agents, code and math

Do Large Language Models Know What They Are Capable Of?

Casey O. Barkan, Sidney Black, Oliver Sourbut

ICLR 2026 · Large language models › Agents, code and math · approach: Agent instruction-following benchmarks · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
scale up to newer or larger LLMs within a familyLlama, GPT and Claude models · BigCodeBench in-advance confidenceAUROCMixed
add in-context experience of past successes and failuresClaude Sonnet models and GPT 4.5 · resource acquisition contractsprofitImproved
add in-context experience of past successes and failuresGPT 4.1 · resource acquisition contractsprofitNo clear effect
use reasoning LLMs instead of non-reasoning LLMsSWE-Bench Verified confidence estimation · SWE-Bench Verifiedoverconfidence and AUROCNo clear effect
progress through more steps of a multi-step taskClaude Sonnet models · SWE-Bench VerifiedoverconfidenceHurt
progress through more steps of a multi-step taskOpenAI models except GPT 5.1 · SWE-Bench VerifiedAUROCImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy