# Reflection-Bench: Evaluating Epistemic Agency in Large Language Models

arXiv: https://arxiv.org/abs/2410.16270 · HTML: https://mlsanity.com/paper/2410.16270/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 72 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents](https://mlsanity.com/paper/2410.09024/) (2024)
- [Using cognitive psychology to understand GPT-3](https://mlsanity.com/paper/2206.14576/) (2022)
- [PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change](https://mlsanity.com/paper/2206.10498/) (2022)
- [To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning](https://mlsanity.com/paper/2409.12183/) (2024)
- [On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning](https://mlsanity.com/paper/2212.08061/) (2022)
- [Don't Make Your LLM an Evaluation Benchmark Cheater](https://mlsanity.com/paper/2311.01964/) (2023)
- [Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making](https://mlsanity.com/paper/2410.07166/) (2024)
- [Thinking Fast and Slow in Large Language Models](https://mlsanity.com/paper/2212.05206/) (2022)
- [Benchmarking Benchmark Leakage in Large Language Models](https://mlsanity.com/paper/2404.18824/) (2024)
- [Can large language models explore in-context?](https://mlsanity.com/paper/2403.15371/) (2024)
- [Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents](https://mlsanity.com/paper/2407.00993/) (2024)
- [From task structures to world models: What do LLMs know?](https://mlsanity.com/paper/2310.04276/) (2023)
- [FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents](https://mlsanity.com/paper/2406.14884/) (2024)
- [Understanding Human Intelligence through Human Limitations](https://mlsanity.com/paper/2009.14050/) (2020)
- [Belief Revision: The Adaptability of Large Language Models Reasoning](https://mlsanity.com/paper/2406.19764/) (2024)
- [Evaluating Large Language Models with Psychometrics](https://mlsanity.com/paper/2406.17675/) (2024)
- [Eliciting the Priors of Large Language Models using Iterated In-Context Learning](https://mlsanity.com/paper/2406.01860/) (2024)
- [A LLM Benchmark based on the Minecraft Builder Dialog Agent Task](https://mlsanity.com/paper/2407.12734/) (2024)

## Built on by (most cited first, 7 of 7)

- [Designing Domain-Specific Agents via Hierarchical Task Abstraction Mechanism](https://mlsanity.com/paper/2511.17198/) (2025)
- [LR^2Bench: Evaluating Long-chain Reflective Reasoning Capabilities of Large Language Models via Constraint Satisfaction Problems](https://mlsanity.com/paper/2502.17848/) (2025)
- [Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents](https://mlsanity.com/paper/2510.17491/) (2025)
- [Diagnostics of cognitive failures in multi-agent expert systems using dynamic evaluation protocols and subsequent mutation of the processing context](https://mlsanity.com/paper/2509.15366/) (2025)
- [Mechanistic Origin of Moral Indifference in Language Models](https://mlsanity.com/paper/2603.15615/) (2026)
- [Separable Pathways for Causal Reasoning: How Architectural Scaffolding Enables Hypothesis-Space Restructuring in LLM Agents](https://mlsanity.com/paper/2604.20039/) (2026)
- [Set-shifting Behavioral Test for Harnessed Agents](https://mlsanity.com/paper/2607.13396/) (2026)

## Abstract (arXiv)

With large language models (LLMs) increasingly deployed as cognitive engines for AI agents, the reliability and effectiveness critically hinge on their intrinsic epistemic agency, which remains understudied. Epistemic agency, the ability to flexibly construct, adapt, and monitor beliefs about dynamic environments, represents a base-model-level capacity independent of specific tools, modules, or applications. We characterize the holistic process underlying epistemic agency, which unfolds in seven interrelated dimensions: prediction, decision-making, perception, memory, counterfactual thinking, belief updating, and meta-reflection. Correspondingly, we propose Reflection-Bench, a cognitive-psychology-inspired benchmark consisting of seven tasks with long-term relevance and minimization of data leakage. Through a comprehensive evaluation of 16 models using three prompting strategies, we identify a clear three-tier performance hierarchy and significant limitations of current LLMs, particularly in meta-reflection capabilities. While state-of-the-art LLMs demonstrate rudimentary signs of epistemic agency, our findings suggest several promising research directions, including enhancing core cognitive functions, improving cross-functional coordination, and developing adaptive processing mechanisms. Our code and data are available at https://github.com/AI45Lab/ReflectionBench.