# In-context learning agents are asymmetric belief updaters

arXiv: https://arxiv.org/abs/2402.03969 · HTML: https://mlsanity.com/paper/2402.03969/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 57 references that are in the map.
- First posted on arXiv 6 Feb 2024.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [Transformers learn in-context by gradient descent](https://mlsanity.com/paper/2212.07677/) (2022)
- [What Can Transformers Learn In-Context? A Case Study of Simple Function Classes](https://mlsanity.com/paper/2208.01066/) (2022)
- [RL2: Fast Reinforcement Learning via Slow Reinforcement Learning](https://mlsanity.com/paper/1611.02779/) (2016)
- [Large Language Models Are State-of-the-Art Evaluators of Translation Quality](https://mlsanity.com/paper/2302.14520/) (2023)
- [Using cognitive psychology to understand GPT-3](https://mlsanity.com/paper/2206.14576/) (2022)
- [Larger language models do in-context learning differently](https://mlsanity.com/paper/2303.03846/) (2023)
- [Learning to reinforcement learn](https://mlsanity.com/paper/1611.05763/) (2016)
- [Data Distributional Properties Drive Emergent In-Context Learning in Transformers](https://mlsanity.com/paper/2205.05055/) (2022)
- [GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models](https://mlsanity.com/paper/2303.10130/) (2023)
- [Language models show human-like content effects on reasoning tasks](https://mlsanity.com/paper/2207.07051/) (2022)
- [Explainable Machine Learning for Scientific Insights and Discoveries](https://mlsanity.com/paper/1905.08883/) (2019)
- [Meta-learning of Sequential Strategies](https://mlsanity.com/paper/1905.03030/) (2019)
- [Meta-in-context learning in large language models](https://mlsanity.com/paper/2305.12907/) (2023)
- [Meta-trained agents implement Bayes-optimal agents](https://mlsanity.com/paper/2010.11223/) (2020)
- [Modeling Human Exploration Through Resource-Rational Reinforcement Learning](https://mlsanity.com/paper/2201.11817/) (2022)
- [In-Context Learning Dynamics with Random Binary Sequences](https://mlsanity.com/paper/2310.17639/) (2023)
- [How should the advent of large language models affect the practice of science?](https://mlsanity.com/paper/2312.03759/) (2023)

## Built on by (most cited first, 14 of 14)

- [Can large language models explore in-context?](https://mlsanity.com/paper/2403.15371/) (2024)
- [Current state of LLM Risks and AI Guardrails](https://mlsanity.com/paper/2406.12934/) (2024)
- [Controlling Large Language Model Agents with Entropic Activation Steering](https://mlsanity.com/paper/2406.00244/) (2024)
- [Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models](https://mlsanity.com/paper/2410.01280/) (2024)
- [Generating Computational Cognitive Models using Large Language Models](https://mlsanity.com/paper/2502.00879/) (2025)
- [Should You Use Your Large Language Model to Explore or Exploit?](https://mlsanity.com/paper/2502.00225/) (2025)
- [Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignment](https://mlsanity.com/paper/2510.14008/) (2025)
- [Large Language Models are Biased Reinforcement Learners](https://mlsanity.com/paper/2405.11422/) (2024)
- [Meta-learning ecological priors from large language models explains human learning and decision making](https://mlsanity.com/paper/2509.00116/) (2025)
- [Cognitive models can reveal interpretable value trade-offs in language models](https://mlsanity.com/paper/2506.20666/) (2025)
- [Large Language Models as Search Engines: Societal Challenges](https://mlsanity.com/paper/2512.08946/) (2025)
- [Reasoning aligns language models to human cognition](https://mlsanity.com/paper/2602.08693/) (2026)
- [Evolving choice hysteresis in reinforcement learning: comparing the adaptive value of positivity bias and gradual perseveration](https://mlsanity.com/paper/2410.19434/) (2024)
- [Conflict and Congruency Effects in Large Language Models: In-Weight and In-Context Competition in a Verbal Conflict Task](https://mlsanity.com/paper/2608.11510/) (2026)

## Abstract (arXiv)

We study the in-context learning dynamics of large language models (LLMs) using three instrumental learning tasks adapted from cognitive psychology. We find that LLMs update their beliefs in an asymmetric manner and learn more from better-than-expected outcomes than from worse-than-expected ones. Furthermore, we show that this effect reverses when learning about counterfactual feedback and disappears when no agency is implied. We corroborate these findings by investigating idealized in-context learning agents derived through meta-reinforcement learning, where we observe similar patterns. Taken together, our results contribute to our understanding of how in-context learning works by highlighting that the framing of a problem significantly influences how learning occurs, a phenomenon also observed in human cognition.