FastContext: Training Efficient Repository Explorer for Coding Agents
Paper ā¢ 2606.14066 ā¢ Published ā¢ 91 ā¢
3
Yuling
YerbaPage
AI & ML interests
None yet
Recent Activity
commentedon a paper 9 days ago
FastContext: Training Efficient Repository Explorer for Coding Agents authored a paper 9 days ago
FastContext: Training Efficient Repository Explorer for Coding Agents liked a model 9 days ago
microsoft/FastContext-1.0-4B-SFTOrganizations
commented a
paper 9 days ago
authored a
paper 9 days ago
liked a
model 9 days ago
upvoted a paper 10 days ago
reacted to their post with šš„š¤ 10 days ago
Post
5297
Why your LLM agent starts "forgetting" things? š¤Æ
New survey breaks down everything about context compression for long-horizon agents š
- what to compress
- how to compress it
- who decides when
Plus a curated paper collection to go with it ā
š Paper: https://doi.org/10.20944/preprints202605.2065.v1
ā Repo: https://github.com/YerbaPage/Awesome-Agent-Context-Compression
New survey breaks down everything about context compression for long-horizon agents š
- what to compress
- how to compress it
- who decides when
Plus a curated paper collection to go with it ā
š Paper: https://doi.org/10.20944/preprints202605.2065.v1
ā Repo: https://github.com/YerbaPage/Awesome-Agent-Context-Compression
posted an update 10 days ago
Post
5297
Why your LLM agent starts "forgetting" things? š¤Æ
New survey breaks down everything about context compression for long-horizon agents š
- what to compress
- how to compress it
- who decides when
Plus a curated paper collection to go with it ā
š Paper: https://doi.org/10.20944/preprints202605.2065.v1
ā Repo: https://github.com/YerbaPage/Awesome-Agent-Context-Compression
New survey breaks down everything about context compression for long-horizon agents š
- what to compress
- how to compress it
- who decides when
Plus a curated paper collection to go with it ā
š Paper: https://doi.org/10.20944/preprints202605.2065.v1
ā Repo: https://github.com/YerbaPage/Awesome-Agent-Context-Compression
authored 3
papers 15 days ago
SWE-Explore: Benchmarking How Coding Agents Explore Repositories
Paper ā¢ 2606.07297 ā¢ Published ā¢ 119
ShredBench: Evaluating the Semantic Reasoning Capabilities of Multimodal LLMs in Document Reconstruction
Paper ā¢ 2604.23813 ā¢ Published
Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playing
Paper ā¢ 2605.04733 ā¢ Published
upvoted a paper 16 days ago
submitted a
paper to Daily Papers 16 days ago
commented a
paper 16 days ago
authored 2
papers 3 months ago
published a
dataset 3 months ago
updated a
dataset 3 months ago
authored a
paper 4 months ago
upvoted a paper 4 months ago