[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation
☆811Apr 24, 2026Updated last week
Alternatives and similar repositories for LightMem
Users that are interested in LightMem are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [NeurIPS 2025 D&B (Spotlight🌟)] TIME: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenario☆31Oct 5, 2025Updated 7 months ago
- ☆36Oct 22, 2025Updated 6 months ago
- The official implementation of the paper "Mem-α: Learning Memory Construction via Reinforcement Learning"☆200Dec 25, 2025Updated 4 months ago
- Official implementation for paper "How Far Are We from Genuinely Useful Deep Research Agents?"☆65Dec 10, 2025Updated 4 months ago
- ☆65Dec 11, 2025Updated 4 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆825Aug 13, 2024Updated last year
- MV-RAG combines retrieval with multi-view generation to create accurate 3D-consistent visuals. By retrieving reference images and text, i…☆24Nov 29, 2025Updated 5 months ago
- Benchmarking Chat Assistants on Long-Term Interactive Memory (ICLR 2025)☆739Oct 24, 2025Updated 6 months ago
- A Collection of Papers about Memory for Language Agents☆470Apr 26, 2026Updated last week
- THEORY OF SPACE: a benchmark for evaluating whether foundation models can actively explore under partial observability efficiently to bui…☆74Feb 27, 2026Updated 2 months ago
- 😊 TPTT: Transforming Pretrained Transformers into Titans☆62Nov 24, 2025Updated 5 months ago
- ☆309Jan 3, 2026Updated 4 months ago
- CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval☆25Jun 28, 2025Updated 10 months ago
- A benchmark for testing memorization abilities of LMs☆24Oct 15, 2024Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- FROM $f(x)$ AND $g(x)$ TO $f(g(x))$: LLMs Learn New Skills in RL by Composing Old Ones☆66Jan 26, 2026Updated 3 months ago
- The paper list of "Memory in the Age of AI Agents: A Survey"☆1,904Mar 4, 2026Updated 2 months ago
- [AAAI'25] The implementation of paper "Federated Foundation Models on Heterogeneous Time Series" | The first work to explore time series …☆22Feb 2, 2026Updated 3 months ago
- [ICLR 2026] SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models☆92Mar 9, 2026Updated last month
- Demo for Qwen2.5-VL-3B-Instruct on Axera device.☆15Sep 3, 2025Updated 8 months ago
- ☆28Aug 19, 2025Updated 8 months ago
- This is the official implementation of TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data☆13Jul 21, 2024Updated last year
- Repository for “PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makers”, NAACL24☆154Jun 16, 2024Updated last year
- [ICCV 2025] Factorized Learning for Temporally Grounded Video-Language Models☆24Apr 18, 2026Updated 2 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [arXiv'25] LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning☆42Jan 6, 2026Updated 4 months ago
- [AAAI 2026] Test-Time Reinforcement Learning for GUI Grounding via Region Consistency https://arxiv.org/abs/2508.05615☆64Nov 8, 2025Updated 5 months ago
- Code for MemoryBench☆61Apr 15, 2026Updated 3 weeks ago
- [KDD 2025] AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation☆33Nov 18, 2025Updated 5 months ago
- this is a work about UpliftRec☆10Dec 10, 2024Updated last year
- ☆21Sep 5, 2023Updated 2 years ago
- The source code of Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents.☆52Jan 31, 2026Updated 3 months ago
- [Arxiv 2025] Official code and datasets of paper: GNNs as Predictors of Agentic Workflow Performances☆20Jan 15, 2026Updated 3 months ago
- Official implementation of paper "ACON: Optimizing Context Compression for Long-horizon LLM Agents"☆70Oct 14, 2025Updated 6 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆24Jul 2, 2025Updated 10 months ago
- [ICML 2026] RLAnything & DemyAgent: General and scalable agentic RL algorithms across terminal, GUI, SWE, and tool-call settings☆481Feb 27, 2026Updated 2 months ago
- [ICLR 26] The official code repository for the paper "Mirage or Method? How Model–Task Alignment Induces Divergent RL Conclusions".☆17Feb 9, 2026Updated 2 months ago
- ☆39Mar 17, 2026Updated last month
- A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.☆1,022Jul 31, 2025Updated 9 months ago
- [EMNLP 2024] OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs.☆147Nov 13, 2024Updated last year
- ☆101Sep 10, 2025Updated 7 months ago