# Benchmarking In-context Experiential Learning Through Repeated Product Recommendations

arXiv: https://arxiv.org/abs/2511.22130 · HTML: https://mlsanity.com/paper/2511.22130/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 50 references that are in the map.
- First posted on arXiv 27 Nov 2025.

## Builds on (most cited first, 30 of 33)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [Aligning Large Multimodal Models with Factually Augmented RLHF](https://mlsanity.com/paper/2309.14525/) (2023)
- [Session-based Recommendations with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06939/) (2015)
- [τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://mlsanity.com/paper/2506.07982/) (2025)
- [Improving alignment of dialogue agents via targeted human judgements](https://mlsanity.com/paper/2209.14375/) (2022)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [ScienceWorld: Is your Agent Smarter than a 5th Grader?](https://mlsanity.com/paper/2203.07540/) (2022)
- [Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging](https://mlsanity.com/paper/2310.11564/) (2023)
- [MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical Reasoning](https://mlsanity.com/paper/2406.00922/) (2024)
- [Large Language Models as Zero-Shot Conversational Recommenders](https://mlsanity.com/paper/2308.10053/) (2023)
- [CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalization](https://mlsanity.com/paper/2310.10134/) (2023)
- [LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models](https://mlsanity.com/paper/2311.18232/) (2023)
- [Improved Recurrent Neural Networks for Session-based Recommendations](https://mlsanity.com/paper/1606.08117/) (2016)
- [LLM Generated Persona is a Promise with a Catch](https://mlsanity.com/paper/2503.16527/) (2025)
- [LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners](https://mlsanity.com/paper/2505.11942/) (2025)
- [LLM-Rec: Personalized Recommendation via Prompting Large Language Models](https://mlsanity.com/paper/2307.15780/) (2023)
- [PERSONA: A Reproducible Testbed for Pluralistic Alignment](https://mlsanity.com/paper/2407.17387/) (2024)
- [PersonalLLM: Tailoring LLMs to Individual Preferences](https://mlsanity.com/paper/2409.20296/) (2024)
- [Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning](https://mlsanity.com/paper/1805.10627/) (2018)
- [StreamBench: Towards Benchmarking Continuous Improvement of Language Agents](https://mlsanity.com/paper/2406.08747/) (2024)
- [Training a Generally Curious Agent](https://mlsanity.com/paper/2502.17543/) (2025)
- [From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?](https://mlsanity.com/paper/2506.08295/) (2025)

## Built on by (most cited first, 1 of 1)

- [Interpretable experiential learning based on state history and global feedback](https://mlsanity.com/paper/2605.00940/) (2026)

## Abstract (arXiv)

To navigate ever-shifting real-world environments, agents must grapple with incomplete knowledge and adapt their strategies through experience. However, current evaluations of LLM-based agents largely overlook this capability. Crucially, we stress not just the ability to contend with uncertainty within a task (episode), as episode-specific information is progressively revealed across turns, but also the refinement of such adaptive ability across similar episodes, as agents accumulate experiences and infer their shared latent structure. Repeated product recommendation offers a natural setting to isolate this need for experiential learning: within each interaction, an intelligent recommender must elicit unknown customer preferences through questions; across multiple interactions, it should tailor its questioning strategy to the observed customer and product distributions. We instantiate the Benchmark for Experiential Learning and Active exploration (BELA) by combining (1) a rich catalog of real-world products from Amazon, (2) a diverse collection of synthetic customer personas aimed to capture heterogeneous latent preferences, and (3) an LLM-based customer simulator framework that emulate preference-revealing interactions. Rather than aiming to faithfully replicate real consumer behavior, BELA provides a controlled and scalable testbed for whether agents can exploit consistent latent preferences across episodes. Benchmarking current models reveals that they can learn across turns, but struggle to improve across episodes. This underscore the need for frontier models to advance in experiential learning capabilities.