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