Code for Paper: Benchmarking Multi-step Scientific Tool-use in LLM Agents
☆41Jul 5, 2026Updated last month
Alternatives and similar repositories for SciAgentGYM
Users that are interested in SciAgentGYM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR2026] Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models☆30Apr 19, 2026Updated 4 months ago
- A Hermes Agent example on Fly.io Machines☆23Jun 23, 2026Updated 2 months ago
- Benchmark and execution environment for evaluating LLM agents on end-to-end AI Research. [ICLR 2026]☆39May 31, 2026Updated 2 months ago
- Heterogeneous Scientific Foundation Model Collaboration☆23May 1, 2026Updated 3 months ago
- This is Official implementation for T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasonin…☆24Mar 5, 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.
- [TrimKV] Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs - [DBTrimKV] Make Each Token Count: Towards Improving Lo…☆18Jul 26, 2026Updated last month
- ☆29Mar 10, 2026Updated 5 months ago
- Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination.☆22Jul 18, 2025Updated last year
- [EMNLP 2026] Official implementation for paper "Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive R…☆43Aug 23, 2026Updated last week
- Executive Memory for Coherent Long-Horizon Reasoning!☆86Jan 14, 2026Updated 7 months ago
- Jointly Optimizing Large Language Models for Reasoning and Self-Refinement☆14Apr 22, 2026Updated 4 months ago
- ☆16Apr 15, 2026Updated 4 months ago
- Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows☆169Jun 2, 2026Updated 2 months ago
- MUA-RL: MULTI-TURN USER-INTERACTING AGENT REINFORCEMENT LEARNING FOR AGENTIC TOOL USE☆67Nov 5, 2025Updated 9 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Lab Cookbook☆42Aug 5, 2026Updated 3 weeks ago
- ☆12May 23, 2018Updated 8 years ago
- Squeeze verbose LLM agent tool output down to only the relevant lines☆23Apr 27, 2026Updated 4 months ago
- [ICML 2026] <MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier>☆94May 18, 2026Updated 3 months ago
- Imbalanced Gradients: A New Cause of Overestimated Adversarial Robustness. (MD attacks)☆11Aug 29, 2020Updated 6 years ago
- this is for the ACM MM paper---Backdoor Attack on Crowd Counting☆17Jul 10, 2022Updated 4 years ago
- Find the hidden meaning of LLMs☆42Nov 13, 2025Updated 9 months ago
- [CVPRW 2026 Oral] Less Detail, Better Answers: Degradation-Driven Prompting for VQA☆20Apr 25, 2026Updated 4 months ago
- ☆10Mar 31, 2023Updated 3 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Agentic research control plane: queue state, worker preflight, wake-gated execution, evidence sync, dashboard, alerts, and AI-generated p…☆17Jul 21, 2026Updated last month
- ☆12Jun 16, 2023Updated 3 years ago
- [CVPR2020] Clean-Label Backdoor Attacks on Video Recognition Models☆41Jun 19, 2020Updated 6 years ago
- UQ: Assessing Language Models on Unsolved Questions☆30Aug 26, 2025Updated last year
- ☆32Jun 13, 2026Updated 2 months ago
- ☆20Jan 18, 2026Updated 7 months ago
- [ACL 2026] This is the repo of Data Darwinism.☆27Apr 16, 2026Updated 4 months ago
- Official source code repository for paper BubbleRAG.☆17Jun 1, 2026Updated 2 months ago
- Official repo for "TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders"☆27Apr 9, 2026Updated 4 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.
- [JMLR] Gradual Domain Adaptation: Theory and Algorithms☆11Jan 14, 2025Updated last year
- ☆21Apr 3, 2026Updated 4 months ago
- An arbitrage bot is a smart contract connected to an external automation script that controls its operation.☆2,690Updated this week
- ☆48Apr 8, 2026Updated 4 months ago
- Catalogue of Life toolkit for Python☆11Aug 4, 2020Updated 6 years ago
- Agent-RRM: Exploring Reasoning Reward Model for Agents☆70Mar 17, 2026Updated 5 months ago
- AdvT-shirt-1K A Physical-world Adversarial T-shirt Dataset for Adversarial Robustness Evaluation☆16Aug 7, 2025Updated last year