SRA-Bench and SR-Agents: a benchmark and toolkit for skill-retrieval-augmented LLM agents.
☆107Jul 2, 2026Updated 3 months ago
Alternatives and similar repositories for SR-Agents
Users that are interested in SR-Agents are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A smart skill search engine for agents with multi-field retrieval and quality signals.☆23Apr 15, 2026Updated 5 months ago
- Code for AAAI 2024 paper Wikiformer☆20Dec 21, 2023Updated 2 years ago
- Code for JuDGE, SIGIR 2025 Long Paper☆37Aug 7, 2025Updated last year
- Code for MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems☆92Sep 15, 2026Updated 2 weeks ago
- ☆29Mar 10, 2026Updated 6 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.
- SkillRouter: Retrieve-and-Rerank Skill Selection for LLM Agents at Scale☆262Jun 25, 2026Updated 3 months ago
- Source code of our paper MIND, ACL 2024 Long Paper☆66Nov 14, 2025Updated 10 months ago
- Code for RACE.☆15Nov 12, 2025Updated 10 months ago
- Skill retrieval benchmark dataset and evaluation code.☆26Sep 25, 2026Updated last week
- StaRD: Statute Retrieval Dataset based on Real-World Legal Consultation☆26Apr 24, 2025Updated last year
- Code for Parametric RAG, SIGIR 2025 Full Paper☆236May 1, 2025Updated last year
- Focused Papers, Delivered Simply ：）☆54Dec 25, 2025Updated 9 months ago
- The implementation for SIGIR 2026: Learning to Retrieve from Agent Trajectories.☆62Sep 17, 2026Updated 2 weeks ago
- ☆30Jul 28, 2024Updated 2 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- A general framework used on evaluating the performance of large language models (LLMs) based on the peer review mechanism among LLMs☆19Aug 3, 2024Updated 2 years ago
- Implementation of SLIM, a framework of dynamics skill lifecycle management for agentic reinforcement learning☆22Sep 25, 2026Updated last week
- [AAAI'26, Oral] Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG☆34Apr 14, 2026Updated 5 months ago
- ☆25Apr 8, 2026Updated 5 months ago
- Official codebase of the paper -- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills☆299May 1, 2026Updated 5 months ago
- [ACL 2026 Findings] Repo for paper "Agentic-R: Learning to Retrieve for Agentic Search"☆95Apr 9, 2026Updated 5 months ago
- ☆19Sep 18, 2024Updated 2 years ago
- ☆47Jan 19, 2026Updated 8 months ago
- ☆48Apr 8, 2026Updated 5 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.
- [ICLR 2026] BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs☆18May 21, 2025Updated last year
- EvoEmbedding: Evolvable Representations for Long-Context Retrieval and Agentic Memory☆58Jul 24, 2026Updated 2 months ago
- AgentIR is a retriever specialized for Deep Research agents (COLM 2026).☆64Aug 28, 2026Updated last month
- Repository of paper "Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis" (ACL 2025 Main)☆20Jul 19, 2025Updated last year
- COS-PLAY: Co-Evolving LLM Decision and Skill Bank Agents for Long-Horizon Game Play☆31Jul 11, 2026Updated 2 months ago
- [NeurIPS 2026] "Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory"☆18Sep 26, 2026Updated last week
- WSDM'2021, PROP and SIGIR'2021,B-PROP☆111May 18, 2023Updated 3 years ago
- The official repo for our SIGIR'23 Full paper: Constructing Tree-based Index for Efficient and Effective Dense Retrieval☆28Jun 7, 2023Updated 3 years ago
- A Multimodal Reasoning Agent with Stateful Experiences☆27Mar 31, 2026Updated 6 months ago
- 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.
- Code for paper "WildReward: Learning Reward Models from In-the-Wild Human Interactions"☆23Feb 26, 2026Updated 7 months ago
- MINER: Multi-Interest Matching Network for News Recommendation☆29Dec 26, 2022Updated 3 years ago
- ☆106Mar 13, 2026Updated 6 months ago
- ☆25Nov 11, 2025Updated 10 months ago
- ☆21Aug 30, 2026Updated last month
- LegalOne: A Family of Foundation Models for Reliable Legal Reasoning☆77Feb 3, 2026Updated 8 months ago
- ☆49Aug 12, 2026Updated last month