Papers6

All Beginner Intermediate Advanced

All Sources arXiv

#function calling

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

ASA: Training-Free Representation Engineering for Tool-Calling Agents

Intermediate

Youjin Wang, Run Zhou et al.Feb 4arXiv

The paper finds a strange gap: the model’s hidden thoughts almost perfectly show when it should use a tool, but its actual words often don’t trigger the tool under strict rules.

#activation steering#representation engineering#tool calling

Not triaged yet

Behavior Knowledge Merge in Reinforced Agentic Models

Intermediate

Xiangchi Yuan, Dachuan Shi et al.Jan 20arXiv

The paper solves a big problem: when you merge several reinforcement-learned models, their special skills get watered down by simple averaging.

#reinforcement learning#model merging#task vectors

Not triaged yet

Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text

Intermediate

Zhihao Xu, Rumei Li et al.Jan 15arXiv

The paper shows a new way to teach AI assistants how to use tools in many-step conversations by mining ordinary text on the internet for step-by-step “how-to” knowledge.

#GEM pipeline#text-based trajectory generation#tool-use data synthesis

Not triaged yet

GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators

Intermediate

Jiacheng Guo, Ling Yang et al.Dec 22arXiv

GenEnv is a training system where a student AI and a teacher simulator grow together by exchanging tasks and feedback.

#GenEnv#co-evolutionary learning#difficulty-aligned curriculum

Not triaged yet

Olmo 3

Beginner

Team Olmo, : et al.Dec 15arXiv

Olmo 3 is a family of fully-open AI language models (7B and 32B) where every step—from raw data to training code and checkpoints—is released.

#fully-open language models#model flow#long-context reasoning

Not triaged yet