Research
Library
This is where I keep the collections. Nine ADS libraries I curate on NASA ADS, three thematic literature explorers, a podcast library, essays, and a live feed of what's been added recently. It's the reading side of the research.
Research libraries
NASA ADS ↗-
Coding Agents
85 documents
Software-engineering agents: architectures, multi-agent coding, and how developers work with them.
- Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction
- Developer Interaction Patterns with Proactive AI: A Five-Day Field Study
-
Benchmarks
62 documents
Evaluating coding agents and code models on real software work.
- Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering
- IDE-Bench: Evaluating Large Language Models as IDE Agents on Real-World Software Engineering Tasks
-
Code Generation & Retrieval
41 documents
Code generation, context retrieval, and localization for coding agents.
- ShortCoder: Knowledge-Augmented Syntax Optimization for Token-Efficient Code Generation
- Compressed code: the hidden effects of quantization and distillation on programming tokens
-
Agent Memory
35 documents
Long-horizon memory for LLM agents: storage, consolidation, and forgetting.
- From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
- Same Ranking, Different Winner: How Scoring Targets Shape LLM Memory Benchmarks
-
Scientific Search & SciX
84 documents
Navigating scientific literature: NASA ADS / SciX information systems, scientific language models, and fine-grained classification of research text.
- Decades of Transformation: Evolution of the NASA Astrophysics Data System's Infrastructure
- Improving astroBERT Using Semantic Textual Similarity
Thematic explorers
Navigable, themed maps of recent literature. Each one starts from an ADS library and structures the papers into themes using SciX MCP.
-
Agentic Memory Systems
108 papers · 9 themes
Procedural & SkillsReflection & ExperienceBenchmarksEval MethodologySynthetic DataArchitecturesSecurity & GovernanceApplications & PersonalizationForgetting & Consolidation -
Memory Design Considerations
51 papers · 11 themes
Retrieval & RankingConsolidation & DistillationKnowledge RepresentationTemporality & UpdatingForgetting & LifecycleStorage SubstrateMulti-Agent & Shared MemoryWorking Memory & ContextEvaluation & CostInterop, Schema & GovernanceFoundations & Landscape -
Enterprise Multi-Agent Reliability
50 papers · 8 themes
Reliability & failure modesRecovery & durable stateObservability & tracingEvaluation & assuranceCost, routing & schedulingTopology & coordinationSecurity & governanceHuman oversight & collaboration
Resource libraries
Podcast library
podcastDeep-dive episodes generated from the literature surveys.
Essays & newsletters
essayWriting across Medium, Sourcegraph, and on-site essays.
- How we're using Sourcegraph and a Slack bot to detect vulnerabilities and react quickly
- Why coding agents fail in large codebases (and what to do about it)
- Running coding agents in enterprise codebases
- What it actually takes to run code intelligence in-house
- I used two multi-agent pipelines for everything I built this week. Here's what happened.
- The Sourcegraph guide to surviving Big Code
- Applying creativity research to agentic workflows
- Detecting supply chain attacks at scale with Deep Search
+10 more
What's new
Recent papers across all libraries, ordered by publication date. This is the recency prior from the hybrid scorer in my code-intelligence-digest app.
These libraries anchor the open threads. See the threads →