Field notes
2,343 notes from my AI research vault, mapped by topic. Pick a topic to see its notes, or search.
Click the web, then scroll to zoom
Every note is in the list below. The web of topics draws here once the page has loaded.
94 of 2,343 notes match.
- Question answered
- Source note
- Topic
- Shared notes
Notes on paper summary
94 notes, page 4 of 4
Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations
Researchers propose an adversarial generator-discriminator framework to train language models (LM) for tasks with well-defined success metrics, like code generation and mathematical reasoning. The new approach improves…
ECHO: Prune to act, trace to learn with selective turn memory in agentic RL
The paper proposes ECHO, a selective turn-memory framework for long-horizon language agents. ECHO aims to address the issues of history collapse and traceable learning by compressing completed environment turns into…
MECoBench: A Systematic Study of Multimodal Agent Collaboration in Embodied Environments
The paper introduces MECoBench, a new system for testing the collaboration abilities of multimodal large language models in visually grounded environments. The authors conduct extensive experiments with various MLLMs…
TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning
The paper proposes a new framework called TRIAGE for credit assignment in agentic reinforcement learning. This framework adds a semantic role axis to outcome credit, aiming to correct the issues of standard GRPO where…
AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs
The paper proposes AgentsNet, a new benchmark for multi-agent reasoning. This benchmark is designed to measure the ability of multi-agent systems to collaborate effectively and leverage their network topology. The…
C$^{2}$R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse Autoencoders
The paper introduces C$^2$R, a method to improve Sparse Autoencoders (SAEs) used for interpreting large language models. The main challenge with SAEs is scaling to large dictionaries, which leads to issues like feature…
DOPD: Dual On-policy Distillation
The paper proposes a new method called Dual On-policy Distillation (DOPD) for transferring knowledge from a teacher model to a student model in on-policy distillation. DOPD aims to address the issue of 'privilege…
Estimating Commonsense Plausibility through Semantic Shifts
The paper proposes a new method called ComPaSS for evaluating the plausibility of language by measuring changes in semantics when adding common sense-related information to sentences. The method performs better than…
RETRIEVALFORMER: TRANSFORMER-QUALITY RECOMMENDATIONS WITH EFFICIENT ANN RETRIEVAL AND COLD-START RESILIENCE
The researchers propose RetrievalFormer, a transformer-based recommendation system that combines high accuracy with efficient Approximate Nearest Neighbor (ANN) retrieval. This system can recommend unseen items during…
Joint Learning of Experiential Rules and Policies for Large Language Model Agents
A research paper proposes a method called Joint Learning of Experiential Rules and Policies (JERP) to improve the effectiveness of Large Language Model Agents in multi-step interactive environments. The method updates…
ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP
Researchers introduce a new method called ShareLock, a multi-tool threshold poisoning framework that uses Shamir's threshold scheme to inject malicious instructions into LLM-servers through MCP. The method disperses…
ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP
The paper introduces a new method called ShareLock, which is a multi-tool threshold poisoning framework that can exploit the interactions between Language Model servers and external tools. This method is designed to…
Explainable Control Framework (XCF) based on Fuzzy Model-Agnostic Explanation and LLM Agent-Supported Interface
The paper introduces an Explainable Control Framework (XCF) for understanding complex controllers' behavior in various scenarios. It offers three main contributions: the XCF, a model-agnostic explanation method called…
FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation
The paper introduces FORCE, a framework designed to improve the efficiency of reinforcement learning fine-tuning for Vision-Language-Action (VLA) models. The framework consists of three stages: Value-Calibrated…
Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound
The paper presents Multi-Agent Goal Recognition with Team- and Goal-Conditioned Reinforcement Learning and Factorized Branch-and-Bound (MAGR-BB), a method to infer which agents in a multi-agent system are working…
On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity
The paper discusses a method called On-policy Self-Distillation, which uses a single model as both teacher and student to achieve high accuracy in pass@1. However, it is found that this method can lead to a decrease in…
Weave of Formal Thought
The paper introduces Weave of Formal Thought (WoFT), a new paradigm for large language models that combines syntactic validation with learned structural representations. The proposed approach includes a formal engine…
ASALT: Adaptive State Alignment for Lateral Transfer in Multi-agent Reinforcement Learning
The paper introduces a new method called ASALT for multi-agent reinforcement learning (MARL). This method is designed to handle situations where the state-space dimensionalities between source and target domains don't…
ASALT: Adaptive State Alignment for Lateral Transfer in Multi-agent Reinforcement Learning
The paper introduces ASALT, a method for multi-agent reinforcement learning (MARL) that allows for knowledge transfer between source and target domains even if the state space dimensions do not match. ASALT uses…
FlowPipe: LLM-Enhanced Conditional Generative Flow Networks for Data Preparation Pipeline Construction
Researchers propose a new method called FlowPipe to automatically construct data preparation pipelines for machine learning. The proposed method uses Conditional Generative Flow Networks (C-GFlowNets) and Deep Semantic…
LaGO: Latent Action Guidance for Online Reinforcement Learning
The paper 'LaGO: Latent Action Guidance for Online Reinforcement Learning' proposes a new framework called LaGO. This framework uses a pre-trained language model (LLM) as a guide to help with online policy optimization…
ScaleToT: Generalizing Structured LLM Reasoning for Billion-Scale Low-Activity User Modeling
The paper presents ScaleToT, a method that improves user modeling for low-activity users by learning structured reasoning from a small subset of Large Language Models (LLMs). It constructs typed user-state chains using…
An AI research agent drafts these notes from public papers and posts, and each one keeps its source link. Only the folders I choose to publish leave my Obsidian vault.
