Mcp + Agents + Code Generation

67.0

Create an automated visual mapper for agent reasoning chains. Help users understand why an agent reached a specific conclusion by rendering its internal decision tree.

Mcp + Agents + Code Generation

Signals (91)

A Discordance-Aware Multimodal Framework with Multi-Agent Clinical Reasoning

On Solving the Multiple Variable Gapped Longest Common Subsequence Problem

Mapping High-Performance Regions in Battery Scheduling across Data Uncertainty, Battery Design, and Planning Horizons

Zindex – Diagram Infrastructure for Agents

FD-NL2SQL: Feedback-Driven Clinical NL2SQL that Improves with Use

SCATR: Simple Calibrated Test-Time Ranking

"Excuse me, may I say something..." CoLabScience, A Proactive AI Assistant for Biomedical Discovery and LLM-Expert Collaborations

Show HN: Marky – A lightweight Markdown viewer for agentic coding

Weak-Link Optimization for Multi-Agent Reasoning and Collaboration

Show HN: Runner – A Better Claude Cowork

Mango: Multi-Agent Web Navigation via Global-View Optimization

On Accelerating Grounded Code Development for Research

Imperfectly Cooperative Human-AI Interactions: Comparing the Impacts of Human and AI Attributes in Simulated and User Studies

assistant-ui/assistant-ui

AI4Finance-Foundation/FinRL-Trading

Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval

Claude Code Removed from $20-a-Month "Pro" Subscription for New Users

Demonstration of Pneuma-Seeker: Agentic System for Reifying and Fulfilling Information Needs on Tabular Data

GroupDPO: Memory efficient Group-wise Direct Preference Optimization

EchoChain: A Full-Duplex Benchmark for State-Update Reasoning Under Interruptions

zilliztech/claude-context

pingdotgg/t3code

A Pascal's Wager for AI doomers

Reciprocal Co-Training (RCT): Coupling Gradient-Based and Non-Differentiable Models via Reinforcement Learning

Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization

EvoMap/evolver

Multimodal Claim Extraction for Fact-Checking

MoonshotAI/kimi-cli

How to Ground a Korean AI Agent in Real Demographics with Synthetic Personas

Reinforcement Learning via Value Gradient Flow

The World Leaks the Future: Harness Evolution for Future Prediction Agents

RiskWebWorld: A Realistic Interactive Benchmark for GUI Agents in E-commerce Risk Management

Tug-of-War within A Decade: Conflict Resolution in Vulnerability Analysis via Teacher-Guided Retrieval-Augmented Generations

alexzhang13/rlm

DeepER-Med: Advancing Deep Evidence-Based Research in Medicine Through Agentic AI

Injecting Structured Biomedical Knowledge into Language Models: Continual Pretraining vs. GraphRAG

Why having “humans in the loop” in an AI war is an illusion

PolicyBank: Evolving Policy Understanding for LLM Agents

Bilevel Optimization of Agent Skills via Monte Carlo Tree Search

archestra-ai/archestra

A new way to explore the web with AI Mode in Chrome

Shubhamsaboo/awesome-llm-apps

Preference Estimation via Opponent Modeling in Multi-Agent Negotiation

Agent orchestration

LLMs Corrupt Your Documents When You Delegate

Preregistered Belief Revision Contracts

Thoughts and feelings around Claude Design

Evaluating LLM Simulators as Differentially Private Data Generators

Optimistic Policy Learning under Pessimistic Adversaries with Regret and Violation Guarantees

Claude Code to be removed from Pro Tier?

Non-Stationarity in the Embedding Space of Time Series Foundation Models

dimensionalOS/dimos

Credo: Declarative Control of LLM Pipelines via Beliefs and Policies

Sampling for Quality: Training-Free Reward-Guided LLM Decoding via Sequential Monte Carlo

EviSearch: A Human in the Loop System for Extracting and Auditing Clinical Evidence for Systematic Reviews

7 ways to travel smarter this summer, with help from Google

Anthropic says OpenClaw-style Claude CLI usage is allowed again

Artifacts: Versioned storage that speaks Git

Positive-Only Drifting Policy Optimization

MemGround: Long-Term Memory Evaluation Kit for Large Language Models in Gamified Scenarios

SetFlow: Generating Structured Sets of Representations for Multiple Instance Learning

Scaling Codex to enterprises worldwide

The Vercel breach: OAuth attack exposes risk in platform environment variables

Show HN: Daemons – we pivoted from building agents to cleaning up after them

KWBench: Measuring Unprompted Problem Recognition in Knowledge Work

SocialGrid: A Benchmark for Planning and Social Reasoning in Embodied Multi-Agent Systems

Stein Variational Black-Box Combinatorial Optimization

Run High-Throughput Reinforcement Learning Training with End-to-End FP8 Precision

Show HN: Ilha – a UI library that fits in an AI context window

Towards Scalable Lightweight GUI Agents via Multi-role Orchestration

Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agents

AutomationBench

tractorjuice/arc-kit

ReactBench: A Benchmark for Topological Reasoning in MLLMs on Chemical Reaction Diagrams

ProtoTTA: Prototype-Guided Test-Time Adaptation

github/awesome-copilot

AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation

Beyond Verifiable Rewards: Rubric-Based GRM for Reinforced Fine-Tuning SWE Agents