# PEARL: Self-Evolving Assistant for Time Management with Reinforcement Learning

arXiv: https://arxiv.org/abs/2601.11957 · HTML: https://mlsanity.com/paper/2601.11957/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 17 of its 44 references that are in the map.
- First posted on arXiv 17 Jan 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 17 of 17)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [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)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [Self-Play Preference Optimization for Language Model Alignment](https://mlsanity.com/paper/2405.00675/) (2024)
- [Where LLM Agents Fail and How They can Learn From Failures](https://mlsanity.com/paper/2509.25370/) (2025)
- [Learning Planning-based Reasoning by Trajectories Collection and Process Reward Synthesizing](https://mlsanity.com/paper/2402.00658/) (2024)
- [METAL: A Multi-Agent Framework for Chart Generation with Test-Time Scaling](https://mlsanity.com/paper/2502.17651/) (2025)
- [Thought of Search: Planning with Language Models Through The Lens of Efficiency](https://mlsanity.com/paper/2404.11833/) (2024)
- [Calendar.help: Designing a Workflow-Based Scheduling Agent with Humans in the Loop](https://mlsanity.com/paper/1703.08428/) (2017)
- [Interactive and Expressive Code-Augmented Planning with Large Language Models](https://mlsanity.com/paper/2411.13826/) (2024)
- [EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generation](https://mlsanity.com/paper/2512.24731/) (2025)
- [Control Large Language Models via Divide and Conquer](https://mlsanity.com/paper/2410.04628/) (2024)

## Built on by (most cited first, 4 of 4)

- [Useful Memories Become Faulty When Continuously Updated by LLMs](https://mlsanity.com/paper/2605.12978/) (2026)
- [Multi-Turn Agentic Scientific Literature Search via Workflow Induction](https://mlsanity.com/paper/2607.00597/) (2026)
- [BioInsight: Multi-Agent Orchestration for Interactive Biomedical Knowledge Discovery](https://mlsanity.com/paper/2606.20997/) (2026)
- [Long-Horizon Embodied Decision-Making via Multimodal Memory Compression](https://mlsanity.com/paper/2608.01456/) (2026)

## Abstract (arXiv)

Overlapping calendar invitations force busy professionals to repeatedly decide which meetings to attend, reschedule, or decline. We refer to this preference-driven decision process as calendar conflict resolution. Automating this decision process is crucial yet challenging. Scheduling logistics can drain hours, and human delegation often fails at scale, which motivates us to ask: Can we trust large language models (LLMs) or language agents to manage time? To enable a systematic study of this question, we introduce CalConflictBench, a benchmark for long-horizon calendar conflict resolution. In CalConflictBench, conflicts are presented to agents round-by-round over a calendar year, requiring them to infer and adapt to user preferences progressively. Our experiments show that current LLM agents perform poorly with high error rates, e.g., Qwen-3-30B-Think has an average error rate of 35%. To address this gap, we propose PEARL, a reinforcement-learning framework that (i) augments the language agent with an external preference memory that stores and updates inferred strategies (e.g., attendee priorities, topic importance, time/location preferences), and (ii) optimizes the agent with round-wise rewards that directly supervise decision correctness, ranking quality, and memory usage across rounds. Experiments on CalConflictBench show that PEARL achieves an error reduction rate of 0.76 and a 55% improvement in average error rate compared to the strongest baseline.