Stephanie Jarmak

concepts

The concept map

The canonical concept vocabulary drawn as a graph: concepts, the topics they anchor to, and co-occurrence edges derived from digest issues and explorer papers. Click a concept for its evidence — digest issues, explorer sections, papers — or read the structured list below.

Agent memory

How agents store, retrieve, and forget context across turns and sessions; memory architectures and their design tradeoffs.

tagged in 50 of 97 digest issues, most recently 2026-07-22

Digest issues

Agent tooling

Harnesses, skills, and tool interfaces that let agents act: the plumbing between a model and the systems it operates.

tagged in 44 of 97 digest issues, most recently 2026-07-22

Digest issues

Agentic coding

Agents that write, refactor, and maintain software: coding assistants, autonomous dev loops, and the workflows around them.

tagged in 60 of 97 digest issues, most recently 2026-07-22

Digest issues

AI agents

Systems that plan, call tools, and act over multiple steps to accomplish a goal.

tagged in 0 of 97 digest issues

AI economics

Cost structure of AI: token pricing, inference margins, usage limits, and unit economics.

tagged in 17 of 97 digest issues, most recently 2026-07-22

Digest issues

AI for science

AI applied to scientific discovery and research workflows, from literature synthesis to hypothesis generation.

tagged in 7 of 97 digest issues, most recently 2026-07-14

Digest issues

AI governance

Rules for AI systems: regulation, policy, export controls, and organizational governance of agents.

tagged in 13 of 97 digest issues, most recently 2026-07-13

Digest issues

AI industry

The business landscape of AI: labs, funding, acquisitions, and competitive strategy.

tagged in 5 of 97 digest issues, most recently 2026-07-14

Digest issues

AI infrastructure

Compute, serving, and platform layers under AI systems: GPUs, inference stacks, and datacenter buildout.

tagged in 9 of 97 digest issues, most recently 2026-06-29

Digest issues

AI safety

Preventing harmful model and agent behavior: alignment, oversight, and safety evaluation.

tagged in 10 of 97 digest issues, most recently 2026-07-16

Digest issues

AI security

Securing AI systems and using AI in security: prompt injection, sandboxing, supply-chain risk, and agent attack surfaces.

tagged in 24 of 97 digest issues, most recently 2026-07-22 · 18 papers · 1 explorer section

Digest issues

Explorer sections

Papers

Code intelligence

Understanding codebases at scale: search, navigation, and agents that reason over source.

tagged in 0 of 97 digest issues

Code review

Automated and agent-assisted review of code changes: quality gates, review bots, and human-agent review workflows.

tagged in 7 of 97 digest issues, most recently 2026-07-13

Digest issues

Context engineering

Deciding what goes into a model's context window and when: packing, pruning, and structuring working context for long-running tasks.

tagged in 5 of 97 digest issues, most recently 2026-07-18

Digest issues

Developer productivity

How AI tooling changes software work: measured impact, adoption patterns, and workflow shifts.

tagged in 6 of 97 digest issues, most recently 2026-07-16

Digest issues

Evaluation

Measuring whether AI systems work: benchmark design, eval harnesses, and comparison of models, agents, and search systems.

tagged in 65 of 97 digest issues, most recently 2026-07-22 · 19 papers · 2 explorer sections

Digest issues

Explorer sections

Papers

Human in the loop

Where people sit in agent workflows: approval gates, escalation, and oversight interfaces.

tagged in 0 of 97 digest issues

Information retrieval

Finding the right information at the right time: ranking, hybrid search, and retrieval over scientific and code corpora.

tagged in 44 of 97 digest issues, most recently 2026-07-22 · 3 papers · 1 explorer section

Digest issues

Explorer sections

Papers

  • Engram: A Bi-Temporal Memory Engine Where a Lean Retrieved Context Beats the Full History — The read path retrieves through four channels in parallel — dense semantic, BM25 lexical, graph n-hop from query entities, and recency/salience — fuses them with Reciprocal Rank Fusion, then applies an 'as-of' filter and an abstention gate; the assembled context is hybrid (conflict-resolved facts plus raw session chunks) because facts alone lose recall.
  • Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory — At read time an agentic procedure lets the LLM iteratively call memory tools — inspect intermediate results, expand local context around matches, assemble evidence — rather than take a single top-k step; the agentic variant beats a hybrid summary+BM25 reader (79.3% vs 76.0% on LongMemEval_S).
  • T-Mem: Memory That Anticipates, Not Archives — T-Mem retrieves through a top-down topic -> scene -> item cascade, scoring each layer with reciprocal rank fusion over both a shared BM25 lexical index and a per-type dense index (bge-m3). On top of these node indices, four write-time 'trigger' families surface host nodes on the query's behalf: items expose three independently-encoded views (concept-only, bridge-only, joint) and the trigger score is the nan-aware max across views, attributed back to the host item. Scenes/items reached through associative triggers bypass the topic prefilter, because gating them by surviving topics would re-impose the similarity-only neighbourhood the system is built to escape.

Memory consolidation

Distilling episodic traces into durable knowledge and skills, and deciding what an agent should forget.

19 papers · 2 explorer sections · tagged in 0 of 97 digest issues

Explorer sections

Papers

Model Context Protocol

The open protocol connecting models to tools and data sources, and the server/client ecosystem built on it.

tagged in 5 of 97 digest issues, most recently 2026-07-06

Digest issues

Model releases

New model launches and availability changes across frontier and open providers.

tagged in 31 of 97 digest issues, most recently 2026-07-22

Digest issues

Multi-agent orchestration

Coordinating multiple agents on shared work: topologies, delegation patterns, shared memory, and production reliability.

tagged in 47 of 97 digest issues, most recently 2026-07-22

Digest issues

Open models

Open-weight model releases and the ecosystem around running, fine-tuning, and evaluating them.

tagged in 20 of 97 digest issues, most recently 2026-07-20

Digest issues

Reliability

Failure modes, recovery, and durable state for agent systems running unattended or at production scale.

tagged in 4 of 97 digest issues, most recently 2026-07-11 · 15 papers · 1 explorer section

Digest issues

Explorer sections

Papers

  • ReAct: Synergizing Reasoning and Acting in Language Models — Interleaves chain-of-thought reasoning with tool actions so a model can plan, query external sources, and self-correct — reducing hallucination on decision tasks.
  • Is Multi-Agent Debate (MAD) the Silver Bullet? Empirical Analysis in Code Summarization & Translation — Structured multi-agent debate yields minimal-to-inconsistent gains over a strong single-agent baseline on software-engineering tasks.
  • Why Do Multi-Agent LLM Systems Fail? (MAST failure taxonomy) — 14 failure modes in 3 categories — specification issues, inter-agent misalignment, task verification — built with an LLM-as-judge pipeline at Cohen's κ=0.88.
  • λ_A: A Typed Lambda Calculus for LLM Agent Composition — Well-formedness / termination guarantees for agent composition via a typed calculus.
  • TraceFix: Repairing Agent Coordination Protocols with TLA+ Counterexamples — Uses TLA+ counterexamples to repair coordination protocols.
  • TrajAudit: Automated Failure Diagnosis for Agentic Coding Systems — RootSE distills 93 real repository-level agent failures (over 4,500 execution steps) into a diagnosis benchmark whose target is the earliest decisive error step - the single early mistake, such as a misread requirement or flawed plan, whose cumulative consequence is the eventual system failure.
  • SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work? — A 5-bucket failure taxonomy over 526 agent-attributable failures: implementation failure (41.6%) and timeout (31.4%) dominate, then reward hacking (15.4%), premature termination (7.6%), and poor self-verification (4.0%); long context degrades behavior actively — pass rate falls monotonically with consecutive-duplicate run length (claude-code 41.9%→3.2%) and compaction/summarizer trials pass at 0% vs 8.9% without.
  • XFlow: An Executable Protocol Programming System for Reliable Multi-Agent Workflows — The paper makes the failure taxonomy explicit before scaling fan-out: a single agent's hallucinated/malformed/misinterpreted output becomes shared state and corrupts downstream decisions. Concrete failure modes observed: tau3-bench baseline reaches the right end state via an invalid path (treats a parameter clarification as authorization to mutate); CorpusQA fails on the interpretation rule not the retrieved value; SWE-bench baseline submits a patch after local validation already failed. The cloud-edge fan-out is gated: edge workers see only assigned chunks, write only declared outputs, and must pass schema + coverage checks before entering global state.
  • AgentArmor: A Framework, Evaluation, & Mitigation of Coding Agent Failures — Decomposes non-adversarial coding-agent failure into three sequential points — forming the correct target (underspecification), pursuing it (capability error), and executing it through the harness (stochastic sampling, context decay) — with a chain-rule risk P(unsafe)=1-(1-f1)(1-f2)(1-f3) and scenarios that isolate each stage, cross-cut by four active modes (greenfield, editing, deployment, monitoring) over 8 scenarios, 20 environments, and 59 transcript templates at n>=500 across three frontier models.
  • RigorBench: Benchmarking Engineering Process Discipline in Autonomous AI Coding Agents — Names a failure taxonomy for the lab-to-production gap — fragile fixes (patches pass tests but leave latent bugs), token waste (trial-and-error instead of a planned approach), false confidence (never abstaining on impossible/ambiguous tasks), and broken intermediates (codebase left broken between steps). Baseline ReAct agents fail badly against it: no baseline abstained on any of the 6 impossible tasks, and even disciplined agents abstained correctly only 62% of the time. Recovery is the hardest mode and the one scaffolding does NOT fix — smallest gain of all five pillars, token-waste cut only 34%, doom loops persist when root cause isn't in the error message; the authors conclude recovery may need architectural changes beyond configuration-level frameworks.
  • NOVA: A Verification-Aware Agent Harness for Architecture Evolution in Industrial Recommender Systems — NOVA's verification cascade checks architecture semantics before expensive training or deployment, catching runnable-but-structurally-invalid candidates that pass unit tests but violate recommender-specific invariants like sequence masking; failed-verification diagnostics become reusable 'forbidden directions' that shape later search.
  • Glite ARF: Verifier-Driven Research with Parallel LLM Coding Agents — Glite ARF enforces task-level worktree isolation and immutability with a corrections overlay after an incident where one agent step recomputed and corrupted 20,304 historical training rows across 38 feature sets; completed task folders can't be modified, so fixes are separate, auditable downstream tasks.
  • Govern the Repository, Not the Agent: Measuring Ecosystem-Level Risk in AI-Native Software — Across 930,000+ agent-authored pull requests, multilevel models show about half the variance in integration friction survives after accounting for the contribution, its author, size, and agent, and it is a repository-level property. Agent-authored contributions concentrate this repository-level friction roughly twice as much as human ones (ICC 0.30 vs 0.16).
  • AgentAbstain: Do LLM Agents Know When Not to Act? — The paper gives an agent-native failure taxonomy of 8 abstention scenarios, organized by when a trigger becomes observable (pre-execution reasoning vs. runtime discovery) and where it resides (query, environment state, or tools). Across 17 frontier LLMs in 4 harnesses the best agent, Gemini 3.1 Pro, reaches only 59.5% Paired Accuracy and 13 of 17 stay below 50%, and abstention capability tracks largely independently of general task-solving skill. The signature failure is post-hoc abstention: an agent commits an irreversible action, such as cancelling a flight before checking rebooking availability, then verbally acknowledges the problem, leaving unrecoverable side effects.
  • Beyond the Strongest LLM: Multi-Turn Multi-Agent Orchestration vs Single LLMs

Retrieval-augmented generation

Grounding model output in retrieved evidence: dense retrieval foundations, agentic search loops, and RAG system design.

tagged in 0 of 97 digest issues

Synthetic data

Model-generated training and evaluation data: generation pipelines, quality control, and contamination risk.

8 papers · 1 explorer section · tagged in 0 of 97 digest issues

Explorer sections

Papers

Test-time compute

Spending inference-time computation to improve results: reasoning-intensive retrieval, reranking, and search at query time.

5 papers · 1 explorer section · tagged in 0 of 97 digest issues

Explorer sections

Papers