Thinking Inertia: LLMs Keep Thinking When Told Not To
Paper • 2610.11765 • Published • 245
Paul Gonzalez
PaulGonzalez
AI & ML interests
None yet
Recent Activity
liked a model 7 days ago
ConwayResearch/Underdog-Saluki-27B-1.0 upvoted a paper 9 days ago
Thinking Inertia: LLMs Keep Thinking When Told Not To upvoted a paper 11 days ago
What Did the Agent Actually Do? Evidence-Grounded Oversight for Long-Horizon AgentsOrganizations
None yet
upvoted a paper 9 days ago
upvoted a paper 11 days ago
upvoted 2
papers about 1 month ago
upvoted 3
papers about 2 months ago
Editable Visual Design
Paper • 2609.04034 • Published • 44
Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training
Paper • 2608.26730 • Published • 133
Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM
Paper • 2609.04098 • Published • 80
upvoted 3
papers 2 months ago
Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis
Paper • 2608.18940 • Published • 35
Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning
Paper • 2607.29211 • Published • 14
DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces
Paper • 2608.03451 • Published • 34