Skip to content
Papers.

Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory research paper by Accenture, 2026

Accenture · Mar 4, 2026 · Reasoning · 12 citations · 19 upvotes · unverified 6 months ago

Read on arXiv

What it shows

A memory mechanism called Memex enables large language model agents to handle long-horizon tasks more effectively by maintaining compact context through structured summaries while storing full interaction details in an external database, allowing selective retrieval based on learned criteria.

UnverifiedHugging Face's summary; not yet checked by hand.

More from Accenture

All 3
PaperCitations
Chiaroscuro Attention: Spending Compute in the DarkCHIAR-Former uses spectral entropy-based routing to dynamically select between DCT, RBF, and self-attention operators, achieving improved efficiency on large text datasets while maintaining performance through hybrid attention mechanisms.Architectures · Jun 2026 · Unverified3 months ago0
LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language ModelsLayerRoute is a lightweight adapter that selectively skips transformer blocks during inference based on input type, achieving compute savings while maintaining or improving model quality through gated routing and LoRA adaptation.Agents and evaluation · Jun 2026 · Unverified3 months ago1

Other reasoning papers

Topic
PaperCitations
Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsAsking a model to write out its intermediate steps (chain of thought) sharply improves its math and logic answers.Google · Jan 20224 years ago22.1k
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language ModelsDeepSeekMath 7B improves mathematical reasoning through enhanced data pre-training and Group Relative Policy Optimization, achieving high scores on MATH benchmark without external tools.DeepSeek · Feb 2024 · Unverified2 years ago9,044
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement LearningReinforcement learning taught a model long step-by-step reasoning on par with OpenAI o1.DeepSeek · Jan 20251 year ago5,718
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code IntelligenceDeepSeek-Coder-V2, a Mixture-of-Experts language model, excels in code-specific tasks by enhancing coding and mathematical reasoning capabilities while expanding language support and context length.DeepSeek · Jun 2024 · Unverified2 years ago504
MolmoAct: Action Reasoning Models that can Reason in SpaceAction Reasoning Models (ARMs) integrate perception, planning, and control to enable adaptable and explainable robotic behavior, achieving superior performance across various tasks and settings.Ai2 · Aug 2025 · Unverified1 year ago187
ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent PlanningThinkAct, a dual-system framework, uses reinforced visual latent planning to enable few-shot adaptation, long-horizon planning, and self-correction in embodied AI tasks by bridging high-level reasoning with low-level action execution.NVIDIA · Jul 2025 · Unverified1 year ago174
About this paper
Authors
Zhenting Wang, Huancheng Chen, Jiayun Wang and 1 more
arXiv
2603.04257 · PDF
Venue
arXiv.org
Citations
12, 0 influential · Semantic Scholar
Upvotes
19 · Hugging Face
Code
github.com/Accenture/MemexRL
Lab
Accenture · on Companies · on Acquisitions · on Quarterly · on Paydays

Changes

What changed
Influential citationsfirst count: 0Sep 28, 2026today
Citationsfirst count: 12Sep 28, 2026today
New paperFound by the weekly scan, unverifiedSep 28, 2026today

New papers by email

Monday afternoons, only in weeks with new papers from the labs.

Double opt-in. Unsubscribe any time.