AgentDish directory
Paper
Accepted listings with this tag.
| Listing | Category | Score | Trend | Checked | |
|---|---|---|---|---|---|
#2038
↑ +6
PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models
arXiv paper on constraining LLM decoding with incremental parsing to reduce invalid SQL and improve text-to-SQL results. |
AI Research / LLM Decoding / Text-to-SQL | 78 | ↑ +6 | 23 days ago | Details |
#2295
↓ -1
SuperLocalMemory 4.0
An arXiv paper describing a governed, local-first memory system for AI agents, with audit trails, role-based access, verified erasure, and fault-injection results. The page also links to associated code and a Zenodo DOI. |
AI Research / Memory Systems | 74 | ↓ -1 | 12 days ago | Details |
An arXiv paper on detecting AI-generated commercial web content from structural signals rather than word-level text alone. The abstract reports a high-performing detector, attribution results, and released code and artifacts. |
AI Research / Content Detection | 72 | ↑ +1 | 23 days ago | Details |
#2423
↑ +1
Agentic Compilation: Mitigating the LLM Rerun Crisis for Minimized-Inference-Cost Web Automation
An arXiv paper on reducing LLM inference cost for web automation by compiling browser tasks into a deterministic JSON workflow and executing them without repeated model calls. |
Research / Paper | 72 | ↑ +1 | 131 days ago | Details |
#2433
→ 0
Real Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than Recompute
A Hugging Face paper page describing a memory layer for LLMs that stores KV state to encrypted NVMe and reloads it later without recomputing, with results from 50M-token experiments on Gemma models. |
Research / AI Memory / Long-Context | 71 | → 0 | 7 days ago | Details |