SCOUT achieves state-of-the-art long-text understanding with up to 8x lower token use by actively foraging for sparse query-relevant information and updating a compact provenance-grounded epistemic state.
hub Canonical reference
Chain-of-agents: End-to-endagentfoundationmodelsviamulti-agentdistillation andagenticRL.arXivpreprint
Canonical reference. 80% of citing Pith papers cite this work as background.
14
Pith papers citing it
Background
80% of classified citations
abstract
Recent advances in large language models (LLMs) and multi-agent systems have demonstrated remarkable capabilities in complex problem-solving tasks such as deep research, vibe coding, and mathematical reasoning. However, most existing multi-agent systems are built upon manual prompt/workflow engineering with sophisticated agent frameworks, making them computationally inefficient, less capable, and can not benefit from data-centric learning. In this work, we introduce Chain-of-Agents (CoA), a novel paradigm of LLM reasoning that enables native end-to-end complex problem-solving in the same way as a multi-agent system (i.e., multi-turn problem solving with multiple tools and multiple agents) within one model. In chain-of-agents problem-solving, the model dynamically activates different tool agents and role-playing agents to simulate multi-agent collaboration in an end-to-end fashion. To elicit end-to-end chain-of-agents problem-solving abilities in LLMs, we introduce a multi-agent distillation framework to distill state-of-the-art multi-agent systems into chain-of-agents trajectories for agentic supervised fine-tuning. We then use agentic reinforcement learning on verifiable agentic tasks to further improve the models' capabilities on chain-of-agents problem solving. We call the resulting models Agent Foundation Models (AFMs). Our empirical studies demonstrate that AFM establishes new state-of-the-art performance across diverse benchmarks in both web agent and code agent settings. We make the entire research, including the model weights, code for training and evaluation, and the training data, fully open-sourced, which offers a solid starting point for future research on agent models and agentic RL.
hub tools
citation-role summary
background 4
baseline 1
citation-polarity summary
representative citing papers
MAD-OPD recasts on-policy distillation teachers as a debating collective to supply better supervision, lifting agentic and code performance over single-teacher OPD across multiple model sizes.
SR²AM achieves competitive Pass@1 accuracy on diverse tasks with 25.8-95.3% fewer reasoning tokens than much larger models by using self-regulated simulative planning trained via supervised learning and RL.
ICRL uses joint RL training of solver and critic with distribution-calibration re-weighting and role-wise advantage estimation to internalize critique into unassisted LLM performance, yielding 6.4-point gains on agentic tasks and 7.0 on math reasoning with Qwen3 models.
SOD reweights on-policy distillation strength step-by-step using divergence to stabilize tool use in small language model agents, yielding up to 20.86% gains and 26.13% on AIME 2025 for a 0.6B model.
Agent-World autonomously synthesizes verifiable real-world tasks and uses continuous self-evolution to train 8B and 14B agents that outperform proprietary models on 23 benchmarks.
Paper Circle is an open-source multi-agent system that retrieves papers via offline and online sources, applies multi-criteria scoring and diversity ranking, and converts papers into typed knowledge graphs for structured analysis and question answering.
MiroThinker shows that scaling agent-environment interactions via reinforcement learning lets a 72B open-source model reach up to 81.9% on GAIA and approach commercial performance on research benchmarks.
Injecting 1% targeted synthetic data into GPT-2's pre-training substantially improves performance on 8 of 9 failing BLiMP grammatical paradigms, indicating data scarcity causes formal linguistic failures.
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
Claw-R1 provides a Gateway Server and Data Pool to manage step-level agent interaction traces as structured data assets for agentic RL training.
A vision paper outlining a two-pronged research agenda for scaling mobile agents from isolated devices to distributed intelligent systems.
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.
A survey unifying the operator-theoretic, probabilistic, and optimization-based mathematical structures underlying modern reinforcement learning algorithms.
citing papers explorer
-
SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States
SCOUT achieves state-of-the-art long-text understanding with up to 8x lower token use by actively foraging for sparse query-relevant information and updating a compact provenance-grounded epistemic state.
-
MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate
MAD-OPD recasts on-policy distillation teachers as a debating collective to supply better supervision, lifting agentic and code performance over single-teacher OPD across multiple model sizes.
-
Efficient Agentic Reasoning Through Self-Regulated Simulative Planning
SR²AM achieves competitive Pass@1 accuracy on diverse tasks with 25.8-95.3% fewer reasoning tokens than much larger models by using self-regulated simulative planning trained via supervised learning and RL.
-
ICRL: Learning to Internalize Self-Critique with Reinforcement Learning
ICRL uses joint RL training of solver and critic with distribution-calibration re-weighting and role-wise advantage estimation to internalize critique into unassisted LLM performance, yielding 6.4-point gains on agentic tasks and 7.0 on math reasoning with Qwen3 models.
-
SOD: Step-wise On-policy Distillation for Small Language Model Agents
SOD reweights on-policy distillation strength step-by-step using divergence to stabilize tool use in small language model agents, yielding up to 20.86% gains and 26.13% on AIME 2025 for a 0.6B model.
-
Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence
Agent-World autonomously synthesizes verifiable real-world tasks and uses continuous self-evolution to train 8B and 14B agents that outperform proprietary models on 23 benchmarks.
-
Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework
Paper Circle is an open-source multi-agent system that retrieves papers via offline and online sources, applies multi-criteria scoring and diversity ranking, and converts papers into typed knowledge graphs for structured analysis and question answering.
-
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
MiroThinker shows that scaling agent-environment interactions via reinforcement learning lets a 72B open-source model reach up to 81.9% on GAIA and approach commercial performance on research benchmarks.
-
LiteResearcher: A Scalable Agentic RL Training Framework for Deep Research Agent
Injecting 1% targeted synthetic data into GPT-2's pre-training substantially improves performance on 8 of 9 failing BLiMP grammatical paradigms, indicating data scarcity causes formal linguistic failures.
-
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
-
Claw-R1: A Step-Level Data Middleware System for Agentic Reinforcement Learning
Claw-R1 provides a Gateway Server and Data Pool to manage step-level agent interaction traces as structured data assets for agentic RL training.
-
Scaling Mobile Agent Systems: From Capability Density to Collective Intelligence
A vision paper outlining a two-pronged research agenda for scaling mobile agents from isolated devices to distributed intelligent systems.
-
A Survey of Reinforcement Learning for Large Reasoning Models
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.
-
Mathematical methods of reinforcement learning
A survey unifying the operator-theoretic, probabilistic, and optimization-based mathematical structures underlying modern reinforcement learning algorithms.