# Evaluating the Goal-Directedness of Large Language Models

arXiv: https://arxiv.org/abs/2504.11844 · HTML: https://mlsanity.com/paper/2504.11844/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 66 references that are in the map.
- First posted on arXiv 16 Apr 2025.

## Builds on (most cited first, 30 of 36)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [GPT-4V(ision) is a Generalist Web Agent, if Grounded](https://mlsanity.com/paper/2401.01614/) (2024)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change](https://mlsanity.com/paper/2206.10498/) (2022)
- [Alignment faking in large language models](https://mlsanity.com/paper/2412.14093/) (2024)
- [Long-context LLMs Struggle with Long In-context Learning](https://mlsanity.com/paper/2404.02060/) (2024)
- [Large Language Models for Mathematical Reasoning: Progresses and Challenges](https://mlsanity.com/paper/2402.00157/) (2024)
- [Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale](https://mlsanity.com/paper/2409.08264/) (2024)
- [AI Agents That Matter](https://mlsanity.com/paper/2407.01502/) (2024)
- [LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks](https://mlsanity.com/paper/2402.01817/) (2024)
- [Large Language Models Understand and Can be Enhanced by Emotional Stimuli](https://mlsanity.com/paper/2307.11760/) (2023)
- [Generalized Planning in PDDL Domains with Pretrained Large Language Models](https://mlsanity.com/paper/2305.11014/) (2023)
- [Harms from Increasingly Agentic Algorithmic Systems](https://mlsanity.com/paper/2302.10329/) (2023)
- [Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals](https://mlsanity.com/paper/2210.01790/) (2022)
- [Goal Misgeneralization in Deep Reinforcement Learning](https://mlsanity.com/paper/2105.14111/) (2021)
- [The Ethics of Advanced AI Assistants](https://mlsanity.com/paper/2404.16244/) (2024)
- [Is Power-Seeking AI an Existential Risk?](https://mlsanity.com/paper/2206.13353/) (2022)
- [LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench](https://mlsanity.com/paper/2409.13373/) (2024)
- [QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?](https://mlsanity.com/paper/2503.22674/) (2025)
- [Zero-Shot Goal-Directed Dialogue via RL on Imagined Conversations](https://mlsanity.com/paper/2311.05584/) (2023)
- [Planning Anything with Rigor: General-Purpose Zero-Shot Planning with LLM-based Formalized Programming](https://mlsanity.com/paper/2410.12112/) (2024)
- [Discovering Agents](https://mlsanity.com/paper/2208.08345/) (2022)
- [Context-Aware Language Modeling for Goal-Oriented Dialogue Systems](https://mlsanity.com/paper/2204.10198/) (2022)
- [Are Long-LLMs A Necessity For Long-Context Tasks?](https://mlsanity.com/paper/2405.15318/) (2024)
- [SelfGoal: Your Language Agents Already Know How to Achieve High-level Goals](https://mlsanity.com/paper/2406.04784/) (2024)

## Built on by (most cited first, 16 of 16)

- [From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms](https://mlsanity.com/paper/2605.06716/) (2026)
- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [SafePred: A Predictive Guardrail for Computer-Using Agents via World Models](https://mlsanity.com/paper/2602.01725/) (2026)
- [Towards Strategic Persuasion with Language Models](https://mlsanity.com/paper/2509.22989/) (2025)
- [What Is Your Agent's GPA? A Framework for Evaluating Agent Goal-Plan-Action Alignment](https://mlsanity.com/paper/2510.08847/) (2025)
- [Propensity Inference: Environmental Contributors to LLM Behaviour](https://mlsanity.com/paper/2604.21098/) (2026)
- [Training Agents to Self-Report Misbehavior](https://mlsanity.com/paper/2602.22303/) (2026)
- [Goal-Directedness is in the Eye of the Beholder](https://mlsanity.com/paper/2508.13247/) (2025)
- [Technical Report: Evaluating Goal Drift in Language Model Agents](https://mlsanity.com/paper/2505.02709/) (2025)
- [BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format](https://mlsanity.com/paper/2509.02655/) (2025)
- [A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents](https://mlsanity.com/paper/2602.08964/) (2026)
- [Motivation in Large Language Models](https://mlsanity.com/paper/2603.14347/) (2026)
- [Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework](https://mlsanity.com/paper/2604.22119/) (2026)
- [Causal Foundations of Collective Agency](https://mlsanity.com/paper/2605.00248/) (2026)
- [SchemeArena: Factorized Stress Testing of Scheming in LLM Agents](https://mlsanity.com/paper/2609.08126/) (2026)
- [Shutdown Sabotage Propensities in Multi-Agent Systems](https://mlsanity.com/paper/2609.28274/) (2026)

## Abstract (arXiv)

To what extent do LLMs use their capabilities towards their given goal? We take this as a measure of their goal-directedness. We evaluate goal-directedness on tasks that require information gathering, cognitive effort, and plan execution, where we use subtasks to infer each model's relevant capabilities. Our evaluations of LLMs from Google DeepMind, OpenAI, and Anthropic show that goal-directedness is relatively consistent across tasks, differs from task performance, and is only moderately sensitive to motivational prompts. Notably, most models are not fully goal-directed. We hope our goal-directedness evaluations will enable better monitoring of LLM progress, and enable more deliberate design choices of agentic properties in LLMs.