Search

"benchmarks"20 resultsKeyword

Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data

Beginner

Emre Can Acikgoz, Cheng Qian et al.Feb 24arXiv

Tool-R0 teaches a language model to use software tools (like APIs) with zero human-made training data.

#self-play reinforcement learning#tool calling#function calling

Not triaged yet

Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models

Intermediate

Junru Lu, Jiarui Qin et al.Dec 31arXiv

Youtu-LLM is a small (1.96B) language model that was trained from scratch to think, plan, and act like an agent instead of just copying bigger models.

#lightweight LLM#agentic mid-training#trajectory data

Not triaged yet

SwimBird: Eliciting Switchable Reasoning Mode in Hybrid Autoregressive MLLMs

Intermediate

Jintao Tong, Shilin Yan et al.Feb 5arXiv

SwimBird is a multimodal AI that can switch how it thinks: only in text, only in vision (with hidden picture-like thoughts), or a mix of both.

#SwimBird#switchable reasoning#hybrid autoregressive

Not triaged yet

CAR-bench: Evaluating the Consistency and Limit-Awareness of LLM Agents under Real-World Uncertainty

Intermediate

Johannes Kirmayr, Lukas Stappen et al.Jan 29arXiv

CAR-bench is a new 'driving test' for AI assistants that checks if they can stay careful, honest, and consistent during real back-and-forth conversations in a car.

#LLM agents#benchmarking#consistency

Not triaged yet

V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal Retrieval

Intermediate

Dongyang Chen, Chaoyang Wang et al.Feb 5arXiv

V-Retrver is a new way for AI to search across text and images by double-checking tiny visual details instead of only guessing from words.

#V-Retrver#multimodal retrieval#agentic reasoning

Not triaged yet

LatentMem: Customizing Latent Memory for Multi-Agent Systems

Intermediate

Muxin Fu, Guibin Zhang et al.Feb 3arXiv

LatentMem is a new memory system that helps teams of AI agents remember the right things for their specific jobs without overloading them with text.

#multi-agent systems#latent memory#role-aware memory

Not triaged yet

SocialVeil: Probing Social Intelligence of Language Agents under Communication Barriers

Intermediate

Keyang Xuan, Pengda Wang et al.Feb 4arXiv

This paper builds SocialVeil, a testing world where AI chat agents must talk to each other even when communication is messy, not perfect.

#social intelligence#communication barriers#semantic vagueness

Not triaged yet

Reinforced Attention Learning

Intermediate

Bangzheng Li, Jianmo Ni et al.Feb 4arXiv

This paper teaches AI to pay attention better by training its focus, not just its words.

#Reinforced Attention Learning#attention policy#multimodal LLM

Not triaged yet

Length-Unbiased Sequence Policy Optimization: Revealing and Controlling Response Length Variation in RLVR

Intermediate

Fanfan Liu, Youyang Yin et al.Feb 5arXiv

The paper discovers that popular RLVR methods for training language and vision-language models secretly prefer certain answer lengths, which can hurt learning.

#LUSPO#RLVR#GRPO

Not triaged yet

TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows

Intermediate

Zhenglin Cheng, Peng Sun et al.Dec 3arXiv

TwinFlow is a new way to make big image models draw great pictures in just one step instead of 40–100 steps.

#TwinFlow#one-step generation#twin trajectories

Not triaged yet

D-CORE: Incentivizing Task Decomposition in Large Reasoning Models for Complex Tool Use

Intermediate

Bowen Xu, Shaoyu Wu et al.Feb 2arXiv

This paper fixes a common problem in reasoning AIs called Lazy Reasoning, where the model rambles instead of making a good plan.

#task decomposition#tool use#large reasoning models

Not triaged yet

A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces

Intermediate

Mingxuan Du, Benfeng Xu et al.Feb 3arXiv

A-RAG lets the AI choose how to search, what to read, and when to stop, instead of following a fixed recipe.

#Agentic RAG#Hierarchical Retrieval Interfaces#Keyword Search

Not triaged yet

CoBA-RL: Capability-Oriented Budget Allocation for Reinforcement Learning in LLMs

Intermediate

Zhiyuan Yao, Yi-Kai Zhang et al.Feb 3arXiv

Large language models learn better when we spend more practice time on the right questions at the right moments.

#Reinforcement Learning#RLVR#GRPO

Not triaged yet

Self-Hinting Language Models Enhance Reinforcement Learning

Intermediate

Baohao Liao, Hanze Dong et al.Feb 3arXiv

When rewards are rare, a popular training method for language models (GRPO) often stops learning because every try in a group gets the same score, so there is nothing to compare.

#reinforcement learning#GRPO#self-hinting

Not triaged yet

Balancing Understanding and Generation in Discrete Diffusion Models

Intermediate

Yue Liu, Yuzhong Zhao et al.Feb 1arXiv

This paper introduces XDLM, a single model that blends two popular diffusion styles (masked and uniform) so it both understands and generates text and images well.

#XDLM#discrete diffusion#stationary noise kernel

Not triaged yet

LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents

Intermediate

Hyesung Jeon, Hyeongju Ha et al.Feb 1arXiv

Multi-agent LLM systems often use LoRA adapters so each agent has a special role, but they all rebuild almost the same KV cache, wasting memory and time.

#LoRA#Multi-LoRA#KV cache

Not triaged yet

LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse Decoding

Intermediate

Gang Lin, Dongfang Li et al.Feb 4arXiv

Long texts make language models slow because they must keep and re-check a huge memory called the KV cache for every new word they write.

#long-context LLM#sparse attention#head specialization

Not triaged yet

FIRE-Bench: Evaluating Agents on the Rediscovery of Scientific Insights

Intermediate

Zhen Wang, Fan Bai et al.Feb 2arXiv

FIRE-Bench is a new test that checks whether AI agents can fully redo real scientific discoveries, step by step, not just guess answers.

#FIRE-Bench#scientific agents#rediscovery benchmark

Not triaged yet

Residual Context Diffusion Language Models

Intermediate

Yuezhou Hu, Harman Singh et al.Jan 30arXiv

Diffusion language models (dLLMs) generate several tokens at once but usually throw away lots of helpful clues each step—RCD keeps and reuses those clues.

#diffusion language models#residual context diffusion#soft tokens

Not triaged yet

PromptRL: Prompt Matters in RL for Flow-Based Image Generation

Intermediate

Fu-Yun Wang, Han Zhang et al.Feb 1arXiv

PromptRL teaches a language model to rewrite prompts while a flow-based image model learns to draw, and both are trained together using the same rewards.

#PromptRL#flow matching#reinforcement learning

Not triaged yet