AIAny - Natural Language Processing Papers

ReAct: Synergizing Reasoning and Acting in Language Models

2022

Shunyu Yao, Jeffrey Zhao +5

This paper introduces ReAct, an approach that integrates reasoning and acting in large language models (LLMs). ReAct enables LLMs to generate both reasoning traces and task-specific actions in an interleaved manner. This synergy allows reasoning to help induce, track, and update action plans, while actions interface with external sources like knowledge bases to gather more information, overcoming issues of hallucination and error propagation in prior methods.

paper LLM NLP ai-agent google+1

LightRAG

2024

Zirui Guo, Lianghao Xia +3

LightRAG is an open-source framework designed for simple and fast Retrieval-Augmented Generation (RAG), integrating knowledge graphs, vector search, and efficient LLM-based processing to enhance question-answering over large document collections.

RAG LLM NLP github ai-development+5

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

2025

DeepSeek-AI, Aixin Liu +262

DeepSeek-V3.2 is an open large language model that balances high computational efficiency with superior reasoning and agent capabilities. Key innovations include DeepSeek Sparse Attention (DSA) for reduced complexity in long contexts, a scalable reinforcement learning framework achieving GPT-5-level performance, and a large-scale agentic task synthesis pipeline for improved generalization in tool-use scenarios.

deepseek LLM paper RL ai-agent

UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering

2026

Yingdong Shi, Ruiming Zhang +5

Learns a text-conditioned flow (a conditional velocity field) in LLM residual activations to steer frozen models at inference by partially transporting and regenerating activations under target textual conditions — enabling unified control over persona, style, truthfulness, compositional constraints, and activation-space classification.

LLM NLP paper transformers foundation-model

Draft-OPD: On-Policy Distillation for Speculative Draft Models

2026

Haodi Lei, Yafu Li +9

Introduces Draft-OPD, an on-policy distillation method for training lightweight draft models used in speculative decoding — it focuses learning on draft-induced errors via target-assisted rollouts and replay, improving acceptance length and enabling >5× lossless LLM inference acceleration.

paper NLP llm ai-inference ai-serving+2

Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism

2026

Haoxiang Zhang, Qixin Xu +5

Analyzes when masking stale observations improves long-horizon search agents and why, identifying an asymmetric inverted-U relationship between masking benefit, retriever quality, and model capacity; explains a token-for-turn trade-off and releases evaluation scaffolds and trajectories.

paper code github nlp llm+4

COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation

2026

Tianyi Zhou, Dongrui Liu +3

Automates distillation of heterogeneous traces from a target person or role into versioned, inspectable skill packages for LLM agents — producing separate capability and bounded-behavior tracks that support natural-language corrections, rollback, and cross-host installation. Ships with an open system and a skills gallery.

agent-skills skillkit LLM nlp paper+3

LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards

2026

Nianyi Lin, Jiajie Zhang +2

Uses search-agent reading traces and tiered distractors to train LLMs for long-context, multi-hop reasoning, and introduces a rubric reward that supervises entity-level steps (applied only to correct finals). Improves evidence-grounded reasoning and resists reward hacking across 4B–30B models.

RL LLM NLP paper code+1

Trust Region On-Policy Distillation

2026

Xingrun Xing, Haoqing Wang +3

Proposes TrOPD, a method that restricts token-level on-policy distillation to regions where teacher supervision is reliable to stabilize training under teacher–student distribution mismatch. Adds outlier handling (clipping, masking, forward-KL) and off-policy guidance; shows consistent gains on math reasoning, code generation and general benchmarks.

LLM NLP paper RL foundation-model+2

On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters

2026

Mind Lab, : +53

Studies small trainable adapters (PEFT) used as persistent personal models on top of large foundation models, analyzing three scaling axes—Scale Up, Scale Down, Scale Out—and introducing MinT, an infrastructure for adapter identity, provenance, evaluation, and serving.

foundation-model llm nlp paper ai-train

K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts

2026

Nahyun Lee, Dongkeun Yoon +13

A benchmark for evaluating web-browsing agents in Korean contexts, composed of 400 tasks (300 manually verified by native speakers). Includes a human-verified split and an adversarial synthetic split to probe failure modes; reveals large performance gaps for both frontier and Korean models.

paper NLP ai-agent agent-skills multilingual+1

Neural Machine Translation by Jointly Learning to Align and Translate

2014

Dzmitry Bahdanau, Kyunghyun Cho +1

This paper introduces an attention-based encoder–decoder NMT architecture that learns soft alignments between source and target words while translating, eliminating the fixed-length bottleneck of earlier seq2seq models. The approach substantially improves BLEU, especially on long sentences, and matches phrase-based SMT on English-French without additional hand-engineered features. The attention mechanism it proposes became the foundation for virtually all subsequent NMT systems and inspired attention-centric models like the Transformer, reshaping machine translation and sequence modeling across NLP.

30u30 paper NLP translation

Category

Explore by categories

All Categories

AI Leaderboard

AI Agent Tutorials

AI Coding Tutorials

AI Model

AI Agent Papers

Chatbot

AI Dataset

Machine Learning Foundation Books

AI Train

AI Deploy

AI Client

Machine Learning Foundation Papers

Machine Learning Foundation Tutorials

AI Image Demos

AI Agent

Large Language Model Tutorials

Large Language Model Papers

Machine Learning Engineering Papers

Computer Vision Tutorials

Computer Vision Papers

Natural Language Processing Papers

Reinforcement Learning Papers

Speech Technology Papers

AI API

AI Coding

AI Image

AI Video

MLOps

MCP Client

MCP Server

AI Video Papers

AI Audio

AI Others

AI Infra

Embodied AI

ReAct: Synergizing Reasoning and Acting in Language Models

LightRAG

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM Steering

Draft-OPD: On-Policy Distillation for Speculative Draft Models

Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism

COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation

LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric Rewards

Trust Region On-Policy Distillation

On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters

K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts

Neural Machine Translation by Jointly Learning to Align and Translate