Hamish Ivison

hamishivi's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a dataset 8 days ago

TMaxxx/agent-task-recursive-task-synthesis

Updated 8 days ago • 11.5k • 5

updated 2 datasets 9 days ago

TMaxxx/agent-task-facet-terminal-6k

Preview • Updated 9 days ago • 5.96k • 4

TMaxxx/agent-task-terminal-lego-15k

Updated 9 days ago • 6.27k • 2

authored 5 papers 9 days ago

Learning to Solve Hard Problems in RL for LLMs by Never Giving Up

Paper • 2609.13443 • Published 15 days ago • 13

Tmax: A simple recipe for terminal agents

Paper • 2606.23321 • Published Jun 22 • 16

Meta-Reinforcement Learning with Self-Reflection for Agentic Search

Paper • 2603.11327 • Published Mar 11 • 11

The Delta Learning Hypothesis: Preference Tuning on Weak Data can Yield Strong Gains

Paper • 2507.06187 • Published Jul 8, 2025

Generalizing Verifiable Instruction Following

Paper • 2507.02833 • Published Jul 3, 2025 • 1

updated 4 datasets 14 days ago

hamishivi/agent-task-cli-gym

Viewer • Updated 14 days ago • 1.55k • 104

hamishivi/agent-task-swe-smith

Updated 14 days ago • 122

TMaxxx/agent-task-calibforge

Preview • Updated 14 days ago • 678 • 1

TMaxxx/agent-task-litecoder-terminal-rl-preview

Viewer • Updated 14 days ago • 8 • 824

updated 2 datasets 15 days ago

hamishivi/agent-task-openthoughts-agent-rl-5k

Viewer • Updated 15 days ago • 5k • 148

TMaxxx/agent-task-openthoughts-agent-rl-5k

Updated 15 days ago • 61

updated a collection 15 days ago

tmax-1.1

Collection

Apptainer SIF pools for tmax-1.1 environments, with source task dataset links and unified download manifests. • 6 items • Updated 2 days ago