THE INTERNET IS THINKING
Earlier sources: AI agents
AI agents use models to choose actions, call tools, and work toward a goal. This thread follows agent frameworks, memory, orchestration, evaluation, and safeguards; autonomy and reliability vary between systems.
SYMTRI organizes observations from public sources into a living map. Connections reflect shared subject matter; they do not establish causation or endorse a source.
Open in the map ↗865 classified signals in the fourteen-day window. These counts include signals awaiting readable evidence.
Earlier sources
Up to ten sources with readable evidence, ordered by their feed timestamp. These archive sources can be older than the live fourteen-day window. This list is a sample, not a measure of total activity. Dates distinguish paper publication, repository creation, model/dataset activity, Hacker News posts, and KEV catalog additions. “First archived” records when SYMTRI first stored the signal.
- GitHub · Repository created · First archived
alphaparkinc/genpark-automated-treasury-cash-sweep-optimizer-skill ↗
Corporate treasury cash pooling and automated liquidity rebalancing optimizing yield sweeps and zero-overdraft safety buffers.
- Hacker News · Posted on Hacker News · First archived
Show HN: Stepgate – AI agents that can't skip steps, in one portable file ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Show HN: Ghostfox – Self-hosted stealth browser for AI agents ↗
Hacker News discussion.
- arXiv · Published · First archived
PReCache: Efficient KV Cache Sharing for Multi-LoRA Agents via Low-Rank Precomputation and Neutral Reconstruction ↗
Multi-LoRA agent systems enable efficient role specialization by sharing a common backbone model. However, each agent repeatedly processes the growing shared trajectory and constructs its own KV cache, introducing substantial memory and computation redundancy in long-horizon tasks. Existing KV cache sharing methods reduce this repeated prefill, but they either require additional training or architectural constraints or retain substantial model computation. Moreover, direct cache reuse causes the current agent to rely on cache states generated by the previous agent's adapter, weakening the role…
- OpenAlex · Published · First archived
Enabling AI Agents for Semantic 3D City Models through Automated Domain Context Generation ↗
Semantic 3D city models offer rich urban information yet remain largely inaccessible to non-expert users due to their complex schemas, deep class hierarchies, and heterogeneous data structures. Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding and code generation. But applying them to domain-specific databases requires contextual knowledge that far exceeds what can be manually written and maintained. This paper presents a framework that automatically generates domain context from CityGML data stored in 3DCityDB instances. The framework dec…
- OpenAlex · Published · First archived
Ontology-Driven Agents Skills for Selection of Building Datasets with various specifications ↗
Selecting the correct dataset among Taiwan's nine building specifications requires knowledge of production lineage, legal basis, completeness constraints, and spatial-unit semantics that are rarely represented in machine-readable form, leaving large language model (LLM) agents prone to structurally unsuitable recommendations. This study proposes a framework that integrates OWL ontology reasoning with an agent skills architecture to address this gap. A four-dimensional attribute framework first characterizes the nine datasets across data identification, spatiotemporal characteristics, productio…
- arXiv · Published · First archived
UOPD: Uncertainty-Aware Intervention for On-Policy Distillation of Multi-Turn Agents ↗
On-policy distillation (OPD) trains a student on its own rollouts using dense supervision from a teacher. In multi-turn environments, a mistake at a critical decision step can redirect the subsequent rollout toward poor outcomes. We use low teacher confidence on student actions to select high-uncertainty steps for correction. In a controlled ALFWorld study, a single teacher correction at a low-confidence step improves subsequent student behavior and task success, motivating selective intervention during distillation. We propose UOPD, an uncertainty-aware intervention method for on-policy disti…
- arXiv · Published · First archived
Maat: Independent Deterministic Contract-Based Governance for Multi-Agent LLM Workflows ↗
Large-language-model multi-agent systems (LLM-MAS) introduce a characteristic reliability problem: an error produced by one agent can be accepted as context by downstream agents and propagate across the workflow. Many proposed safeguards rely on learned or LLM-based judges whose verdicts are themselves probabilistic; we ask whether a deterministic layer can instead stop contract-detectable handoff defects. We present Maat, a runtime governance layer that validates agent-to-agent handoffs against a versioned workflow contract, or anchor, with no language model in the validation or scoring path.…
- arXiv · Published · First archived
RICE-Alpha: Reliability-Informed Correction with Event Graphs for LLM-Agent Stock Forecasting ↗
Equity-relevant news evolves through temporally dependent corporate events, making historical information useful only when event continuity, information availability, and transition reliability are modeled. Existing LLM-based financial agents incorporate historical evidence, yet they provide limited support for preserving issuer-specific chronology under point-in-time constraints and for identifying when historical transitions contribute information beyond the current forecast. We present RICE-Alpha (Reliability-Informed Correction with Event Graphs), a point-in-time stock-scoring framework th…
- GitHub · Repository created · First archived
Ramillax/claude-code-control-room ↗
Run several Claude Code sessions in parallel from any browser, phone included: live tmux terminals, per-session state from hooks (working / waiting for your permission), a shared board with hierarchical locks so agents don't collide, and skills that keep what each session learned. No frameworks: bash + Python stdlib.
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about AI agents
Check each original source for its methods, release status, limitations, and supporting data. A repository announcement, a preprint, and a published study provide different kinds of evidence. SYMTRI’s subject classification helps discovery; it does not independently validate the source’s claims.
See the collection and counting methodology ↗ · Read the weekly synthesis ↗
Related threads
Explore related regions
These navigation suggestions are part of the map’s editorial structure, rather than measured evidence of a connection.