Update README.md

README.md

@@ -25,10 +25,10 @@ pipeline_tag: text-generation
 
 ## Overview
 
-LIMI is an agentic model fine‑tuned from GLM‑4.5 (355B) using compact, high‑quality data to emphasize:
+LIMI is an agentic model fine‑tuned from [GLM‑4.5](https://huggingface.co/zai-org/GLM-4.5) using compact, high‑quality data to emphasize:
 
 - Targeted capabilities: tool use, multi‑turn correction, spec compliance
-- Long‑context reasoning with tokenizer‑filtered samples (≤128k tokens)
+- Long‑context trajectory with tokenizer‑filtered samples (≤128k tokens)
 - OpenAI‑style `messages` with optional function/tool calls
 
 ## Model Details
@@ -36,7 +36,7 @@ LIMI is an agentic model fine‑tuned from GLM‑4.5 (355B) using compact, high
 - Base model: `zai-org/GLM-4.5`
 - Context: up to 128k tokens (training budget)
 - Training framework: slime
-- Training data: curated conversations from [GAIR/limi](https://huggingface.co/datasets/GAIR/limi)
+- Training data: curated conversations from [GAIR/LIMI](https://huggingface.co/datasets/GAIR/LIMI)
 
 ## Key Results
  
@@ -141,7 +141,7 @@ print(out[0].outputs[0].text)
 
 ```bibtex
 @article{LIMI2025,
-  title   = {Less is More for Agentic Intelligence},
+  title   = {Less is More for Agency},
   author  = {LIMI Authors},
   year    = {2025},
   journal = {arXiv preprint arXiv:2502.03387}