CATEGORY · 1 OF 38

AI & LLMs

The deepest channel on Edge. Foundation models, agent architectures, retrieval, evals, and the moving line between research and production.

873SUMMARIES
+93THIS WEEK
69SOURCES
Category · AI & LLMs
DAY 01Today JUN 30 · 202617 SUMMARIES
arXiv cs.AIAI & LLMs

Steering LLM Personality via Latent Feature Interventions

Researchers have developed a mechanistic method to steer LLM personality traits by identifying and modifying latent features in the model's residual stream using sparse autoencoders, enabling precise behavioral control without retraining.

arXiv cs.AI
arXiv cs.AIAI & LLMs

MedEvoEval: A Longitudinal Framework for Evaluating Doctor Agents

MedEvoEval is a new evaluation framework that moves beyond static medical QA by testing how doctor agents learn, retain, and adapt clinical decision-making skills across sequences of simulated outpatient episodes.

arXiv cs.AIAI & LLMs

Specialized Clinical AI Outperforms General Models in Real-World Use

A study of 620 real-world clinical queries shows that specialized AI tools significantly outperform general-purpose models across accuracy, utility, and verifiability, highlighting the need for domain-specific evaluation.

arXiv cs.AIAI & LLMs

HyphaeDB: Moving From Passive Storage to Agent-Native Memory

HyphaeDB reinterprets HNSW graph topology as a communication fabric for multi-agent systems, enabling knowledge propagation and emergent consensus rather than just passive retrieval.

arXiv cs.AIAI & LLMs

ComMem: Dual-Memory Systems for VLM Test-Time Adaptation

ComMem improves VLM robustness by mimicking biological memory, using a fast-adapting visual cache and a slow-integrating textual prototype system to maintain cross-modal consistency during test-time adaptation.

arXiv cs.AIAI & LLMs

Agentic Abstention: Improving When LLM Agents Should Stop

LLM agents often fail to stop when a task is impossible, leading to unnecessary tool use. The CONVOLVE method improves timely abstention by distilling interaction trajectories into reusable stopping rules.

arXiv cs.AIAI & LLMs

Agent Safety Is Action Alignment, Not Content Refusal

Treating agent safety like chatbot content moderation is a category error. True agent security requires enforcing least privilege at the action boundary, not training models to refuse requests.

arXiv cs.AIAI & LLMs

Making LLM Self-Evolution Safe with Held-Out Selection

RSEA improves LLM agent performance by recursively evolving natural-language artifacts while using a strict held-out validation gate to prevent performance regression.

arXiv cs.AIAI & LLMs

Stabilizing Critic-Free RL with BV-Blend

BV-Blend improves reinforcement learning stability by blending prompt-local statistics with historical cluster-based moments, preventing training stalls when reward variance is zero.

arXiv cs.AIAI & LLMs

IMCBench: Evaluating Multimodal LLMs in Clinical Conversations

IMCBench is a new multi-turn, image-grounded benchmark for medical AI that reveals a critical gap: accurate clinical descriptions do not guarantee safe patient guidance.

arXiv cs.AIAI & LLMs

ATHENA-R1: An AI Agent for Iterative Biomedical Treatment Reasoning

ATHENA-R1 is an AI agent that performs iterative treatment reasoning by dynamically querying a universe of 212 biomedical tools, outperforming GPT-5 by significant margins in clinical benchmarks.

arXiv cs.AIAI & LLMs

Closing the Loop Between Model Evaluation and Data Intervention

By introducing 'capability slices'—groups of evaluation samples categorized by task and operation—engineers can transform benchmark failures into precise, actionable data interventions rather than relying on intuition.

arXiv cs.AIAI & LLMs

GPTNT: A Real-Time Collaborative Benchmark for AI Agents

GPTNT uses the game 'Keep Talking and Nobody Explodes' to test AI agent collaboration under time pressure, revealing critical failures in state tracking and real-time communication.

arXiv cs.AIAI & LLMs

COMPASS: Improving Compositional Control in Multimodal Models

COMPASS introduces a unified framework that uses a shared 'expert token' to bridge composition perception and generation, enabling precise layout control in multimodal models.

IBM TechnologyAI & LLMs

Optimizing LLM Inference: KV Cache and Paged Attention

LLM inference latency and throughput bottlenecks are often caused by inefficient GPU memory management. Using KV caching, paged attention, and specific tuning techniques like chunked prefill can drastically improve performance.

Level Up CodingAI & LLMs

Building a Text-JEPA Model from Scratch

Text-JEPA moves away from auto-regressive token prediction by learning world model representations in latent space, offering a potential path toward more efficient, non-generative intelligence.

TechCrunch — AIAI & LLMs

Why Vibe Coding Platform Base44 is Building Its Own AI Model

Base44 is transitioning to a vertically integrated stack by training its own LLM to gain control over latency, costs, and performance, signaling a shift toward defensibility for AI-native startups.

DAY 02Yesterday JUN 29 · 202613 SUMMARIES
Level Up CodingAI & LLMs

Stop Blaming Your RAG Pipeline: 16 Production Techniques

Most RAG failures are pipeline issues, not model limitations. Improving retrieval precision through hybrid search, reranking, and rigorous evaluation is more effective than simply swapping models.

Level Up Coding
Level Up CodingAI & LLMs

Ornith-1.0: Coding Models That Learn Their Own Harness

Ornith-1.0 achieves state-of-the-art performance for its size by incorporating the coding harness into the model's training gradient, allowing the model to dynamically generate its own execution scaffolds rather than relying on static, human-written ones.

Level Up CodingAI & LLMs

Optimizing RAG Retrieval with Hierarchical Search

Hierarchical RAG improves precision and reduces computational costs by replacing flat, corpus-wide similarity searches with a two-stage process: document-level filtering followed by targeted chunk retrieval.

Level Up CodingAI & LLMs

The Hidden Costs of AI Agentic Loop Engineering

AI agentic loops are powerful for isolated, deterministic tasks but dangerous for complex, high-context environments where they can propagate errors and inflate costs silently.

AI EngineerAI & LLMs

Building Great Agent Skills: The Missing Manual

To escape 'skill hell,' developers must treat agent skills as structured, maintainable code by optimizing triggers, minimizing context bloat, using 'leading words' for steering, and aggressively pruning irrelevant instructions.

Google Cloud TechAI & LLMs

Building Production-Grade Multi-Agent Systems with ADK

Learn to build robust, state-aware multi-agent systems using Google's Agent Development Kit (ADK) and the Model Context Protocol (MCP) to handle orchestration, security, and persistence.

arXiv cs.AIAI & LLMs

Tandem Reinforcement Learning: Aligning AI Reasoning with Humans

Tandem Reinforcement Learning (TRL) forces stronger models to co-generate reasoning with weaker models, resulting in more legible, robust, and human-compatible chains of thought without sacrificing performance.

arXiv cs.AIAI & LLMs

Architecting an Agent-Native Immune System (ANIS) for AI Security

The Agent-Native Immune System (ANIS) moves security from external training-time alignment to an endogenous, runtime defense architecture that protects autonomous agents from hijacking and manipulation.

arXiv cs.AIAI & LLMs

ATOD: Hybrid Training for High-Performance AI Agents

ATOD combines on-policy distillation with reinforcement learning to overcome the performance ceiling of imitation learning, using an annealed schedule and turn-level reweighting to improve long-horizon agent training.

arXiv cs.AIAI & LLMs

Tree of Evidence: Hierarchical Fact-Checking Against AI Misinformation

ToE (Tree of Evidence) is a hierarchical framework that combats AI-generated misinformation by decomposing claims into dynamic argument trees, using reinforcement learning to retrieve and verify evidence across multiple sources.

arXiv cs.AIAI & LLMs

Mitigating Rollout Error in Graph World Models

Graph World Models (GWMs) face unique long-horizon errors where local inaccuracies propagate through topology. The Error-Aware GWM framework uses spectral regularization and critical-node weighting to maintain stability during dynamic-edge rollouts.

arXiv cs.AIAI & LLMs

Improving LLM Planning with Symbolic Feedback Loops

To solve LLM planning errors in long-horizon tasks, this framework uses symbolic verification to provide corrective, interpretable feedback, forcing the model to iteratively refine its plans.

arXiv cs.AIAI & LLMs

Reducing LLM Agent Hallucinations with Grounded Iterative Planning

Grounded Iterative Language Planning (GILP) combines LLM reasoning with a lightweight, trained transition predictor to catch and correct hallucinated state changes, significantly improving planning accuracy.

Showing 30 of 873