#research
Every summary, chronological. Filter by category, tag, or source from the rail.
ε-MemEvo: Adaptive Cross-Task Memory Transfer for LLM Evolution
ε-MemEvo improves LLM-based program evolution by using an adaptive memory transfer mechanism that selectively reuses successful code patterns across different tasks, significantly increasing search efficiency.
Measuring and Restoring Constraint Influence in LLMs
LLMs often ignore complex constraints in long dialogues, treating them as 'dead text.' This research introduces a method to quantify and restore constraint adherence in black-box models.
CAS: A Causal Attribution Score for Explainable AI
The Causal Attribution Score (CAS) provides a unified framework for evaluating AI model interpretability by measuring the causal impact of features on predictions, bridging the gap between local and global explanations.
Reasoning Jury: Improving LLM Evaluation via Multi-Model Consensus
The 'Reasoning Jury' framework improves the reliability of evaluating LLM reasoning traces by using a multi-model consensus approach, reducing the bias and inconsistency inherent in single-model evaluation.
LLMs Hit a Hard Limit on Multi-Constraint Instruction Following
LLMs exhibit 'phase transitions' in performance, where adding a single additional constraint causes a sudden, catastrophic drop in instruction-following capability rather than a gradual decline.
Governed Persistent Memory for Long-Horizon AI Agents
This research introduces a 'Governed Persistent Memory' framework that uses source-bound state semantics and fail-closed release mechanisms to improve reliability and safety in long-horizon AI agents.
MindMemOS: A Self-Evolving Memory Layer for AI Agents
MindMemOS introduces a portable, self-evolving memory operating layer that decouples agent intelligence from long-term storage, enabling persistent, adaptive memory across diverse AI architectures.
AstraZeneca's Agentic R&D Research Assistant
AstraZeneca has developed an agentic AI system designed to automate complex R&D workflows, demonstrating how large-scale pharmaceutical research can leverage autonomous agents to accelerate discovery.
Aligning AI with Human Reasoning Processes
Current AI alignment methods focus on outcomes rather than cognitive processes. To build reliable systems, we must shift toward alignment techniques that mirror human reasoning, ensuring models arrive at conclusions through transparent, human-compatible logic.
Language-Dependent Safety: How Non-English Prompts Alter LLM Behavior
Research indicates that LLMs exhibit varying safety alignment levels across languages, with non-English prompts—specifically Japanese—often triggering more cautious responses to harmful queries compared to English.
Building Lifelong AI Research Partners via Agent Memory
To transform AI from a stateless tool into a lifelong research partner, systems must implement persistent, context-aware memory architectures that allow agents to retain domain-specific knowledge and evolve alongside materials scientists.
Forecasting Side Effects of Activation Steering
Activation steering allows for precise control over LLM behavior, but it often introduces unintended side effects. This research provides a framework to predict these downstream behavioral changes before deployment.
Automating Process Engineering Diagrams with LLMs
This research explores a multi-agent framework for generating and validating Process Flow Diagrams (PFDs) and Piping and Instrumentation Diagrams (P&IDs) using LLMs to reduce manual engineering errors.
TRACE: A Framework for Trustworthy RAG Systems
The TRACE framework addresses reliability in retrieval-augmented generation by implementing a multi-stage verification process to mitigate hallucinations and ensure factual grounding in conversational AI.
Training Data Granularity and Parametric Modularity in LLMs
The research establishes that the granularity of training data directly dictates whether knowledge within an LLM is modular and detachable, or merely decodable but entangled.
Sparse Coding for Latent Communication in VLM Agents
This paper introduces a post-hoc sparse coding method to interpret and analyze the latent communication signals exchanged between vision-language model (VLM) agents, providing a framework for understanding multi-agent internal states.
Evaluation-Conditioned Training for Stronger Oversight
Evaluation-Conditioned Training (ECT) improves model performance by training agents to adapt their behavior based on the strength of the oversight regime they operate under, ensuring better generalization.
Automating LLM Adversarial Attacks with GFlowNets
Generative Flow Networks (GFlowNets) provide a more efficient, diverse, and scalable framework for discovering adversarial prompts compared to traditional gradient-based or evolutionary search methods.
SBCO: Self-Supervised Verifier-Grounded Harness Optimization
SBCO is a framework for optimizing planning agents by using self-supervised, verifier-grounded harness optimization to improve decision-making accuracy without requiring extensive human-labeled data.
MESA: Task-Adaptive Evidence Selection for Agent Memory
MESA improves long-horizon agent performance by using a task-adaptive, multi-structure memory selection framework that retrieves relevant evidence more effectively than standard retrieval methods.
CHORUS: Improving Testbench Coverage via Complementary AI Experts
CHORUS improves hardware verification by using a multi-expert AI framework to generate diverse, high-coverage testbench stimuli, outperforming single-model approaches.
MIDAS: Handling Incomplete Multimodal Sentiment Analysis
The MIDAS framework addresses incomplete multimodal data by disentangling shared and private information while using uncertainty-aware fusion to maintain sentiment prediction accuracy when modalities are missing.
Automating Behavioral Research for AI Agents
This paper introduces a framework for scaling behavioral scientific research on AI agents, moving beyond manual evaluation to automated, reproducible experimental pipelines.
Quantifying the Carbon Footprint of Deep Learning Models
This review analyzes the environmental impact of deep learning, highlighting the massive carbon costs of training large models and proposing strategies for more sustainable AI development.
Agent-MD: Automating Scientific Simulations with LLM Orchestration
Agent-MD introduces a framework for stateful Grand Canonical Monte Carlo (GCMC) and Molecular Dynamics (MD) campaigns, using selective LLM intervention and event-driven escalation to manage complex simulation workflows autonomously.
Preventing AI Research Drift with Structured Scientific Loops
To prevent AI research agents from drifting, researchers must enforce 'scientific taste' and falsifiable constraints within the automated loop, specifically applied here to quadruped navigation.
Detecting LLM Hallucinations via Internal State Probing
LLMs often express high confidence in incorrect answers, but internal state probes can detect these errors before the model generates the output, revealing a 'knowing-saying gap'.
NL2SHACL-Bench: Evaluating LLM Performance on SHACL Generation
NL2SHACL-Bench provides a standardized benchmark suite to evaluate how effectively Large Language Models can translate natural language requirements into SHACL (Shapes Constraint Language) for RDF data validation.
TREAT: Evaluating LLM Reasoning Across Mathematical Representations
The TREAT framework evaluates how effectively AI models access formal mathematical knowledge when presented with equivalent but syntactically different representations, highlighting gaps in model robustness.
Building Argumentative Foundations for AI Evaluation
Current AI evaluation methods lack rigor; the authors propose an argumentative framework that treats model outputs as claims requiring evidence, counter-arguments, and logical justification to improve reliability.
Showing 30 of 298