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 1 of 4
SAPO: Single-Rollout Autoregressive Policy Optimization for Agentic Reinforcement Learning
A new reinforcement learning method called Single-rollout Autoregressive Policy Optimization (SAPO) is proposed to address the memory overhead, computation efficiency, and performance issues of existing methods. SAPO…
Eureka: Task-Conditioned Meta-Agent Orchestration for Scientific Discovery
The paper introduces Eureka, a meta-agent system designed for scientific discovery tasks. Eureka forms specialized agents through planning, promotion, and minimal-sufficient compilation, adapting to recurring…
ORBITER: Conflict-Aware Decision-Making for Agentic Last-Mile Delivery
The paper introduces ORBITER, a system designed to make decisions for last-mile delivery by couriers. It models the courier service through decision points and uses language models (LLMs) to reason about individual…
rEDMRec: Distilling Large Language Model Reasoning into an Editable Experience Memory for Recommendation
The authors propose a system called rEDMRec that improves recommendation quality by compressing the reasoning of a large language model (LLM) into a compact, editable memory. This memory is maintained by an LLM memory…
Robust Risk Under Evolving Uncertainty: A Wasserstein Counterpart of the Entropic Value-at-Risk
The paper proposes a new risk measure called Wasserstein Entropic Value-at-Risk (WEVaR) for an agent learning its environment. The WEVaR is designed to account for the reachable catastrophes that the current entropic…
SPADE: Self-Play in Adaptive Synthetic Executable Environments
The paper introduces SPADE (Self-Play in Adaptive Synthetic Executable Environments), a framework that allows a language model to design and learn in its own self-generated, diverse, adaptive environments. This…
SPADE: Self-Play in Adaptive Synthetic Executable Environments
The paper introduces SPADE, a reinforcement learning framework that allows a language model to act as both an Environment Designer and a Reasoning Agent. The Environment Designer generates long-horizon training…
Chronocooked: A Benchmark for Implicit Interval Timing in Reinforcement Learning Agents
The paper introduces Chronocooked, a benchmark suite for studying how reinforcement learning (RL) agents make decisions over time. It's inspired by Overcooked and includes cooking scenarios that require temporal…
ReLTEx: Reliable LLM-based Taxonomy Expansion
The paper discusses a new framework called ReLTEx for improving the reliability of Large Language Model (LLM)-based taxonomy expansion. The framework combines LLM-driven candidate generation with structure-aware…
sLTN: Structural Logic Tensor Networks
The paper introduces sLTN, an extension of Logic Tensor Networks (LTN), which is a neurosymbolic framework that combines first-order logic with tensor operations for differentiable learning. The new version can handle…
BDH-CQ: In-Context Learning with Recurrent Latent Reasoning
The paper introduces BDH-CQ, a model that combines in-context learning and recurrent latent reasoning. The model updates its memory based on inputs presented during inference, solves queries through iterative…
Comparative Approaches to Agent Retrieval over Large Skill Libraries
The research compares two systems for deciding which skills to load from a large skill library when creating agents. One system combines lexical and dense-embedding retrieval, while the other uses a typed knowledge…
EnvACE: Internalizing Environment Dynamics via World Rehearsal for Agentic Reinforcement Learning
The researchers introduce EnvACE, a method for reinforcement learning that replaces external environment interactions during training with world rehearsal. This method allows the policy to internalize the relationship…
Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation
Researchers propose Observation-Calibrated Self-Distillation (OCSD) to address a confounding issue in On-Policy Self-Distillation (OPSD), a method used to train large language model agents. OCSD aims to attribute…
Chained Recursive Language Models for Multi-Iteration Reasoning
The paper proposes a new architecture for large language models called Chained Recursive Language Models (Chained RLM). This architecture is designed to handle long context reasoning tasks that require extraction…
Chained Recursive Language Models for Multi-Iteration Reasoning
The paper proposes Chained Recursive Language Models (Chained RLM), an architecture for multi-iteration reasoning in large language models (LLMs). It addresses the difficulty in tasks requiring extraction, counting…
From Score Matrices to Football-Aware Match-State Simulation: An Auditable LLM Harness for Exact-Score Reranking
The paper presents an auditable information harness that combines dynamic Poisson-family models and large language models (LLMs) to forecast football scores. The system goes through four iterations, each improving on…
ORACLE: A Multi-Objective Reinforcement Learning-Based Analog Circuit Design Optimizer with Large Language Models-Guided Exploration
The paper presents ORACLE, a multi-objective reinforcement learning-based framework for optimizing analog circuit design. The framework addresses limitations of existing methods by using vector-valued learning and…
A foundation model of numerical intelligence with cross-disciplinary generalization
The paper introduces UNified In-Context Operator Networks (UNICON), a model that demonstrates numerical intelligence across various disciplines. It is capable of inferring predictive relations from graph-based examples…
MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems
The paper introduces MANTA, a framework for adapting communication structures in multi-agent systems during inference time. This allows for more efficient problem solving by enabling agents to adjust their roles…
MemHarness: Memory Is Reconstructed, Not Replayed
Researchers propose MemHarness, a framework for enhancing large language models that allows them to adapt and reconstruct past experiences based on the current context, rather than simply replaying them verbatim as…
SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution
The paper introduces SkillRise, a reinforcement learning framework that allows large language model agents to learn and reuse skills across related yet distinct tasks. SkillRise improves Pass@1 performance on ALFWorld…
UrbanDS: A Graph-Guided LLM Multi-Agent System for Data-Intensive Urban Tasks
The paper presents UrbanDS, a multi-agent system that uses a graph to organize and analyze large-scale and heterogeneous urban data. The system includes a Data Profiling Agent, a Relation Agent, a Planner Agent…
ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding
The paper introduces ClinFusion, a system designed for holistic medical understanding using multimodal large language models (MLLMs). ClinFusion addresses challenges in the medical domain by unifying diverse 2D and…
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.
