Directory
Papers
Reviewed resources in Papers. 148 resources listed.
A maintained paper list and taxonomy accompanying a TMLR survey on using LLMs to automate phone interfaces, covering prompting, training-based methods, datasets, and benchmarks.
Awesome Self-Evolving AI Agents
github.comAn open survey and evidence map for judging whether an AI agent system genuinely improves itself from feedback, rather than only appearing smarter in a demo.
Volt
vision.rwth-aachen.deA research implementation of a transformer architecture for 3D scene understanding, partitioning a scene into volumetric patches for semantic and instance segmentation.
Next-Latent Prediction Transformer
jaydenteoh.github.ioThe official research codebase for a paper showing that predicting the next latent state, instead of the next token, trains transformers to learn more compact world models.
RAGTrack
arxiv.orgThe official implementation of a CVPR 2026 paper on language-aware RGB-thermal object tracking, combining a multi-modal transformer encoder with retrieval-augmented context reasoning.
Awesome-Speech-Language-Model
github.comA curated list of papers, code, and resources for speech language models and end-to-end speech dialogue systems, covering understanding, benchmarks, and full-duplex modeling.
Awesome-Model-Quantization
github.comA running list of low-bit model quantization research papers from 2020 through 2026, organized by year, covering LLMs, vision-language-action models, and mixture-of-experts.
Awesome Agent Evolution
github.comA curated list of projects, papers, and benchmarks on AI agent self-evolution, memory systems, multi-agent architectures, and self-improvement, organized into a taxonomy with short descriptions of each entry.
Agentic-GRPO-LongHorizon
github.comA research ablation study that diagnoses why GRPO training collapses on long-horizon, multi-tool conversational agents and proposes a combined PRM-Lite and LATA method that achieves a 37 percent relative gain over vanilla GRPO on the tau-bench airline benchmark.
MegaAgent
github.comA research framework for large-scale, autonomous multi-agent LLM systems that generates agents dynamically and splits tasks automatically, coordinating them in parallel without relying on predefined operating procedures written by a human.
MultiWorld: Scalable Multi-Agent Multi-View Video World Models
multi-world.github.ioA research implementation of a unified world-modeling framework that generates consistent multi-camera video while controlling multiple agents at once, scaling across different numbers of agents and camera views.
Awesome MLLM for Code
arxiv.orgA curated list of research papers on using multimodal large language models to generate code from non-text inputs, covering web and mobile UI screenshots, scientific plots, slides, SVG logos, CAD, posters and games.
Awesome Credit Assignment in LLM RL
arxiv.orgA curated research survey covering how reinforcement learning for large language models assigns credit to individual tokens, steps, turns or agents when the only feedback is a single outcome reward at the end of a long trajectory.
minimal-embodiment
doi.orgA reference hardware and software implementation from a research paper that gives a large language model a small physical body: an ESP32 microcontroller with sensors and outputs, plus a Node.js bridge service connecting it to the model.
Hyper-RAG
nature.comA hypergraph-driven retrieval-augmented generation method that models beyond-pairwise relationships between entities in domain-specific knowledge, to reduce hallucinations in medical LLM answers.
Awesome Repository-Level Code Generation
github.comA curated list of research papers on repository-level code generation and automated issue resolution, covering repo-level code completion, translation, unit-test generation, code QA and issue-task synthesis.
ParoQuant
paroquant.z-lab.aiAn INT4 weight-quantization method for LLMs that uses learned pairwise rotations to suppress weight outliers, closing most of the accuracy gap to FP16 while running close to AWQ speed on NVIDIA GPUs and Apple Silicon.
A research codebase for fine-tuning flow-matching robot control policies with online reinforcement learning after an initial imitation-learning stage, evaluated on locomotion and manipulation benchmarks.
An academic survey that formalizes the harness surrounding an LLM — execution loop, tool registry, context manager, state store, lifecycle hooks and evaluation interface — as a primary driver of agent reliability, reviewing over 110 papers across 23 systems.
A curated collection of papers, benchmarks, and open-source projects on graph engineering for coordinating LLM agents, organized around a survey moving from individual agent intelligence to system-level intelligence.
SKILL0
arxiv.orgA research framework for in-context reinforcement learning that internalizes reusable skills into an agent's policy, evaluated on tasks such as ALFWorld and Search-QA.
Awesome KV Cache Optimization
jjiantong.github.ioA curated, taxonomy-organized reading list of papers on system-aware KV-cache optimization for efficient large language model serving, accompanying an ACL 2026 survey.
Machine Dialectology (MDia)
github.comA research framework where language models create persistent symbolic dialects (LSFs) for exchanging reasoning between speaker and listener models, then routes among them under accuracy, token, and reliability constraints.
A curated collection of papers, datasets and benchmarks for multimodal large language models applied to remote sensing, built around a survey of the field.