6/30/2026
A3M: Adaptive, Adversarial and Multi-Objective Learning for Strategic Bidding in Repeated Auctions
A3M framework combining reinforcement learning and adversarial reasoning for strategic bidding in multi-unit auctions.
6/30/2026
FlipGuard: Defending Large Language Models Against Quantization-Conditioned Backdoor Attacks
FlipGuard defense framework protecting LLMs against backdoor attacks that activate only after quantization.
6/30/2026
Beyond the Mean: Three-Axis Fidelity for Aligning LLM-Based Survey Simulators from Small Pilot Data
Methods for calibrating LLM-based survey simulators to recover statistical properties of human populations from pilot data.
6/30/2026
The strength of clinical evidence is recoverable from language model representations but not from their stated grades
Analysis of whether LLM internal representations capture clinical evidence strength differently from stated confidence grades.
6/30/2026
A Comparative Study on Affective Cues in Text Embeddings Across Psychological Emotion Theories
Study examining how text embeddings capture psychological emotion theories for sentiment analysis and emotion recognition.
6/30/2026
Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks
LLMs integrated with evolutionary search to optimize across 371 tasks including GPU kernel design and mathematical conjectures.
6/30/2026
Selective Memory Retention for Long-Horizon LLM Agents
TraceRetain framework for memory management in frozen LLM agents. Scores memory entries by interpretable features and evicts lowest-scoring ones at capacity. Tested on ALFWorld with gpt-4-mini.
6/30/2026
Shipwright Harness – open-source autonomous delivery agent for Claude Code (MIT)
Open-source autonomous coding agent for Claude Code that plans, builds, reviews and ships tasks through pipeline.
6/30/2026
Show HN: TinyAgents – a Rust based recursive LLM harness
Rust-based recursive LLM harness for orchestrating sub-agents, inspired by LangGraph and LangChain with Rust transpiler.
6/30/2026
Why Won't Europe Build AI Data Centers in Iceland?
Europe plans to triple AI data centers but overlooks Iceland's geothermal infrastructure. Explores EU tech sovereignty and infrastructure challenges.
6/30/2026
Show HN: Agentic Orchestrator, a TUI for long-running coding agents
Terminal UI for orchestrating long-running coding agents through engineering workflow phases: requirements, design, implementation, review.
6/30/2026
Show HN: Let an AI manage your homelab over MCP without giving it SSH
Tool allowing AI agents to manage homelab infrastructure via MCP protocol without SSH access. Open source developer tool for AI agent orchestration.
6/30/2026
Tau – Learn how coding agents are built
Educational Python coding agent project demonstrating agent architecture with readable layers, tool calling, and session management.
6/30/2026
Show HN: PDF Insight – local-first AI that sorts your PDFs on-device
PDF Insight: local-first on-device AI tool that classifies, sorts, and merges PDF documents without cloud upload. Privacy-focused developer tool.
6/30/2026
Show HN: AMA2, messenger built for AI agent
AMA2: messaging runtime specifically designed for AI agents to manage context and multi-step tasks. Open source Show HN project addressing agent-tool integration gaps.
6/30/2026
Open Memory Protocol – One Memory Store for Claude, ChatGPT, Curso
Protocol enabling shared memory storage across Claude, ChatGPT, and Curso. Standardizes LLM context persistence.
6/30/2026
Introducing GeneBench-Pro
GeneBench-Pro benchmark evaluates AI agent judgment in computational biology: interpreting patterns, assessing data quality, decision-making.
6/30/2026
Inside Genebench-Pro
GeneBench-Pro: research-level benchmark measuring AI agent performance on computational biology tasks with ambiguous scientific data.
6/29/2026
How to Optimize Tools for Agents
Guide on optimizing tools for AI agents. Limited detail without content provided.
6/29/2026
Show HN: Crudio – Turn an OpenAPI spec into a stateful mock back end
Crudio: CLI tool converts OpenAPI 3.x specifications into stateful mock API backends with schema validation and persistence. Developer testing tool.
6/29/2026
Show HN: OpenSfM v1.0
OpenSfM v1.0 revived: Structure-from-Motion engine for aerial/GIS imagery processing. Faster, more scalable open source computer vision tool.
6/29/2026
Open-source AI agent workflow for auditing Solidity smart contracts
Open-source workflow using AI agents to audit Solidity smart contracts. Headline only, limited details.
6/29/2026
Zeus – a local AI agent orchestrator with web and phone UI (open source)
Local open-source AI agent orchestrator with web/phone UI. Runs agents for file ops, browser control, web search, task management.
6/29/2026
A bounty to forge a synthetic identity past our hardware-bound auth
Security bounty for synthetic identity authentication. Loan application with device-bound cryptographic verification using QR and NFC.
6/29/2026
Next-Edit in Kilo, Powered by Inception Diffusion LLMs
Code editor feature using LLM to predict next edits based on context and history. Powered by Inception diffusion models.
6/29/2026
Show HN: Khazad – Transparent Semantic Cache for LLM Calls on Redis Vector Sets
Semantic cache layer for LLM API calls using Redis vectors. Transparent, 50% fewer calls, 96% faster hits.
6/29/2026
Show HN: Turn documents into lip-synced video readers
Tool converts PDFs into lip-synced video presentations. Combines document reading with AI-generated video narration and synchronized playback.
6/29/2026
GitHub Issues as Untrusted Input
Discussion of security risks when using GitHub Issues as untrusted input for LLM agent workflows. Explores injection attack vectors.
6/29/2026
Show HN: TypeScript7 LSP Claude Code Plugin
TypeScript 7 language server plugin using Claude Code. Faster native Go implementation replacing Node-based wrapper.
6/29/2026
Build an agent first Kanban board
Open source Kanban board designed for AI agents to communicate and track tasks across multiple agent instances.
6/29/2026
KitForge–generate an AI agent manifest; scaffold with enforced approval gates
Developer tool for generating AI agent manifests with approval gate scaffolding.
6/29/2026
Show HN: Halgorithem – an open-source tool for detecting AI hallucinations
Open-source tool for detecting LLM hallucinations. Show HN project with practical utility.
6/29/2026
Why Tool AIs Want to Be Agent AIs (2016)
2016 essay on architectural differences between tool and agent AI systems. Foundational thinking piece.
6/29/2026
Micro-Agent: Beat Frontier Models with Collaboration Inside Model API
Multi-agent collaboration framework using model APIs to match frontier model performance.
6/29/2026
Show HN: Context Warp Drive – deterministic folding for LLM agents
Deterministic context folding technique for LLM agents. Show HN project with technical implementation focus.
6/29/2026
LoopFlow – design loops that prompt your coding agent
LoopFlow: YAML-based system for designing agentic loops with Claude that iterate until verification gates pass, enabling autonomous code agents.
6/29/2026
Magpie-Search, THE BEST SEARCH ENGINE FOR LLM'S
Search engine optimized for LLM queries. Limited technical details provided.
6/29/2026
Show HN: Crossbeam-CLI – Connect Claude to Crossbeam without the enterprise tier
crossbeam-cli: open-source tool connecting Claude LLM to Crossbeam API without enterprise tier, enabling natural language queries on account data.
6/29/2026
TraceLab: Characterizing Coding Agent Workloads for LLM Serving
TraceLab characterizes coding agent workloads for optimizing LLM serving infrastructure.
6/29/2026
Show HN: AST-guard A gradient-immune structural guard against RL reward hacking
AST-guard: deterministic gate detecting structural reward hacking in RL-trained code generation models. Research artifact for code model safety.
6/29/2026
An interactive PyTorch debugger that looks deep inside your neural net
PyTorch debugging tool for visualizing neural network activations, gradients, and receptive fields during training. Interactive interpretability tool.
6/29/2026
Does DSPy prompt optimization weaken adversarial robustness?
Research measuring how DSPy prompt optimization affects adversarial robustness against prompt-injection attacks in LLM agents using AgentDojo.
6/29/2026
The Discoverable Evidence of AI-Assisted Software Porting
Case study examining artifacts left by AI code generation (Codex) during software porting tasks.
6/29/2026
Relay – open-source coding agent for non-mainstream/Chinese LLM providers
Open-source coding agent supporting non-mainstream and Chinese LLM providers like DeepSeek.
6/29/2026
Metasearch Tooling for Agents
Metasearch MCP server for agents built on Dogpile search with metered API integration.
6/29/2026
What LLMs are doing to conference programs
Discussion on impact of LLM-generated content on academic conference program submissions.
6/29/2026
Show HN: MCP-compress-router – MCP Compressor
MCP-compress-router reduces token overhead from multiple MCP servers by selectively routing tools.
6/29/2026
Show HN: Create and Maintain Filesystem Structures for LLMs [v1.0.13 Out]
Tool for creating and maintaining filesystem structures optimized for LLM context.
6/29/2026
Recognising and mitigating LLM Pollution in online behavioural research
Research on detecting and mitigating LLM pollution in online behavioral research studies.
6/29/2026
Show HN: Toolnexus for .NET – MCP and agent skills as tools for any LLM
Toolnexus .NET library integrating MCP and agent skills as tools for any LLM.