The Morning
From the arXiv
COMAP: Co-Evolving World Models and Agent Policies for LLM Agents
OMAP co-evolves textual world models and agent policies in a closed loop. The world model predicts future feedback for candidate actions, which the agent uses to refine its choices by assessing feedback reliability. This process allows the world model to adapt to the agent's evolving behavior through self-distillation, improving its accuracy in predicting on-policy trajectories.
MOC: Multi-Order Communication in LLM-based Multi-Agent Systems
This paper introduces Multi-Order Communication (MOC) for LLM-based multi-agent systems. MOC addresses the limitation of current methods by reconstructing communication to capture multi-hop dependencies and employing a structural message consolidation strategy…
Policy and World Modeling Co-Training for Language Agents
This paper proposes PaW, a framework that co-trains a language agent's policy and world model simultaneously during reinforcement learning. By leveraging on-policy rollouts, PaW adds auxiliary world modeling supervision without requiring separate simulators or…
SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training
SIRI trains LLM agents to develop reusable skills internally, eliminating the need for external skill generators or inference-time skill banks. It achieves this through a three-phase process: initial policy warmup, self-skill discovery and validation using the…
ResMerge: Residual-based Spectral Merging of Large Language Models
ResMerge addresses the challenge of merging large language models trained with reinforcement learning (RL). Unlike previous methods that focus on high-energy spectral components, ResMerge recognizes that RL task vectors have both a concentrated "head" and a di…
TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation
This paper introduces TVIR, a benchmark and agent framework for generating research reports that integrate text and visuals. TVIR-Bench comprises 100 tasks requiring visually suppo…
Unified Context Evolution for LLM Agents
This paper introduces Unified Context Evolution (UCE), a framework for LLM agents that addresses the loss of learned strategies between tasks. UCE externalizes agent experience int…
AGENTCL: Toward Rigorous Evaluation of Continual Learning in Language Agents
This paper introduces AgentCL, a rigorous evaluation framework for continual learning in language agents. Its core method involves constructing controlled, compositional task strea…
AgentPLM: Agentic Protein Language Models with Reasoning-Augmented Decoding for Protein Sequence Design
AgentPLM introduces a novel approach to protein sequence design by augmenting traditional language models with a reasoning and feedback loop. Its core method, Reasoning-Augmented D…
Bridging the Last Mile of Time Series Forecasting with LLM Agents
This paper addresses the "last-mile forecasting" problem, where raw statistical forecasts are revised with unstructured business context. The core method is an LLM-agent framework …
The Town Square
This tech news story describes a humorous Instagram "exploit" that allows attackers to take over user accounts through a series of seemingly nonsensical actions.
Workshops
Hermes WebUI provides a user-friendly web and mobile interface for interacting with the Hermes Agent, simplifying its usage from any device.
SuperMemory is an extremely fast and scalable memory engine and app designed as a robust API for the AI era, enabling efficient data storage and retrieval.
