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 ↗831 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.
- Hacker News · Posted on Hacker News · First archived
Reflex, a TUI that compiles Claude Code and Codex transcripts into agent skills ↗
Hacker News discussion.
- GitHub · Repository created · First archived
TonyBucket/keys-keys ↗
An open-source Adaptive Hybrid Minecraft Server Copilot
- GitHub · Repository created · First archived
angelkurten/keel ↗
Context layer for AI agents in vertical SaaS: domain events in, a bitemporal context graph per end-customer out, five MCP tools for every agent.
- arXiv · Published · First archived
Co-Evolving Acting and Forecasting for Language Agents ↗
Training language agents is bottlenecked by the high cost of long-horizon rollouts, yet standard agentic reinforcement learning (RL) learns only from a terminal scalar reward, leaving the supervision in intermediate steps largely unused. Prior work exploits this supervision through value targets that estimate per-step success probabilities or observation targets that fit environment response. Both are hard to construct well: (1) value targets come from the same single scalar signal for each step in the trajectory, and (2) observation targets, such as web pages and terminal logs, are long and n…
- arXiv · Published · First archived
Price of Anarchy of First-Price Auctions in Agentic Markets ↗
An agentic market is a decentralized serving-time market where AI agents bid to claim each user prompt. An agent's bid is based on its expected value for the prompt, which is the expectation of the reward for its response minus its inference costs. First-price auctions (FPAs), in which the highest bidder pays its bid and receives the prompt, are a natural way to allocate prompts in such a market, since they are simple and transparent to run, and do not require central knowledge of private capabilities and costs. However, FPAs are not truthful: participants may bid less than their true value in…
- arXiv · Published · First archived
One Task, Many Interfaces: Simple Cross-Interface Consistency Training Improves LLM Agent Robustness ↗
Post-training binds the competence of an LLM agent to the interface it was trained on. Semantics-preserving perturbations of that interface, such as renaming an action or changing the notation, leave the underlying task unchanged yet make the agent worse at it. Scoring each sample independently means interface randomization only broadens this dependence from a single interface to the training interface distribution, so out-of-distribution perturbations still degrade the agent. We propose Cross-Interface Policy Regularization (CIPR), a self-supervised objective that replaces action names with u…
- arXiv · Published · First archived
Beyond LLM Judge: Mechanical Verification for Agentic Autoformalization ↗
We introduce a novel method for verifying Lean formalizations that goes beyond LLM-judged faithfulness. Unlike most verification methods, which rely on LLMs or trained models, our method combines LLM-based semantic review with mechanical numerical and vacuity checks, providing checkable feedback and detecting errors missed by LLM judges. We apply this method, along with our Extract-Verify-Proof autoformalization pipeline, to construct the Formalized Library of Mathematical Functions (FLMF), a partial formalization of the NIST Digital Library of Mathematical Functions (DLMF). On three labeled d…
- arXiv · Published · First archived
Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation ↗
Long-form agentic video generation must turn a screenplay into shots that remain spatially and temporally consistent across nonconsecutive requests. Passing prompts or recent frames between shots does not provide a shared spatial frame for revisiting a scene or a time-indexed record for replaying an earlier event. We present Any Time, Any Space (ATAS), which compiles a screenplay into shot requests with explicit location, camera, and event-time references. Before generation, it retrieves relevant evidence from a scene memory of registered static geometry and an event memory of dynamic observat…
- arXiv · Published · First archived
PhySGA: A Physics-Space Grounded Agentic Framework for Generalizable and Interactive 3D Composition ↗
3D object composition is pivotal to digital content creation and robot simulation, while also serving as a critical testbed for physical intelligence in foundation models. Previous methods either leverage large language models to directly predict object coordinates, or utilize generative diffusion priors to synthesize composite images for visual alignment, both of which rely on static priors in digital spaces. However, these methods consistently struggle with complex compositions such as precise hanging, gravity-driven settling and hidden containment, as these tasks require interactive constru…
- Hacker News · Posted on Hacker News · First archived
Show HN: A webcomic for AI agents, written and drawn by Claude ↗
Hacker News discussion.
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.