Papers115

#GRPO

PaperSearchQA: Learning to Search and Reason over Scientific Papers with RLVR

James Burgess, Jan N. Hansen et al.Jan 26arXiv

This paper teaches a language-model agent to look up facts in millions of scientific paper summaries and answer clear, single-answer questions.

#RLVR#search agents#PaperSearchQA

The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation

Intermediate

Chenyu Mu, Xin He et al.Jan 25arXiv

This paper teaches AI to turn simple dialogue into full movie scenes by first writing a detailed script and then filming it step by step.

#dialogue-to-video#cinematic script generation#ScripterAgent

SAMTok: Representing Any Mask with Two Words

Intermediate

Yikang Zhou, Tao Zhang et al.Jan 22arXiv

SAMTok turns any object’s mask in an image into just two special “words” so language models can handle pixels like they handle text.

#SAMTok#mask tokenizer#residual vector quantization

InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning

Intermediate

Matthew Y. R. Yang, Hao Bai et al.Jan 20arXiv

The paper introduces Intervention Training (InT), a simple way for a language model to find and fix the first wrong step in its own reasoning using a short, targeted correction.

#Intervention Training#credit assignment#LLM reasoning

DARC: Decoupled Asymmetric Reasoning Curriculum for LLM Evolution

Intermediate

Shengda Fan, Xuyan Ye et al.Jan 20arXiv

DARC teaches big language models to get smarter by splitting training into two calm, well-organized steps instead of one chaotic loop.

#DARC#self-play#curriculum learning

ToolPRMBench: Evaluating and Advancing Process Reward Models for Tool-using Agents

Intermediate

Dawei Li, Yuguang Yao et al.Jan 18arXiv

ToolPRMBench is a new benchmark that checks, step by step, whether an AI agent using tools picks the right next action.

#process reward model#tool-using agents#offline sampling

PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models

Intermediate

Qiyuan Zhang, Biao Gong et al.Jan 16arXiv

This paper teaches video-making AIs to follow real-world physics, so rolling balls roll right and collisions look believable.

#physics-aware video generation#rigid body motion#reinforcement learning

MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching

Intermediate

Changle Qu, Sunhao Dai et al.Jan 15arXiv

MatchTIR teaches AI agents to judge each tool call step-by-step instead of giving the same reward to every step.

#Tool-Integrated Reasoning#Credit Assignment#Bipartite Matching

PRL: Process Reward Learning Improves LLMs' Reasoning Ability and Broadens the Reasoning Boundary

Intermediate

Jiarui Yao, Ruida Wang et al.Jan 15arXiv

Large language models usually get only a final thumbs-up or thumbs-down at the end of their answer, which is too late to fix mistakes made in the middle.

#Process Reward Learning#PRL#Reasoning LLMs

ToolSafe: Enhancing Tool Invocation Safety of LLM-based agents via Proactive Step-level Guardrail and Feedback

Intermediate

Yutao Mou, Zhangchi Xue et al.Jan 15arXiv

ToolSafe is a new way to keep AI agents safe when they use external tools, by checking each action before it runs.

#step-level safety#tool invocation#LLM agents

M^4olGen: Multi-Agent, Multi-Stage Molecular Generation under Precise Multi-Property Constraints

Intermediate

Yizhan Li, Florence Cloutier et al.Jan 15arXiv

The paper introduces M^4olGen, a two-stage system that designs new molecules to match exact numbers for several properties (like QED, LogP, MW, HOMO, LUMO) at the same time.

#molecular generation#multi-property optimization#fragment-level editing

Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning

Intermediate

Chi-Pin Huang, Yunze Man et al.Jan 14arXiv

Fast-ThinkAct teaches a robot to plan with a few tiny hidden "thought tokens" instead of long paragraphs, making it much faster while staying smart.

#Vision-Language-Action#latent reasoning#verbalizable planning

2 3 4 5 6