9 papers
Toward Robust Open-set Adaptation: Synapse Consolidation Inspired by Rac1/MAPK Pathways
Xiao Zhang, Tianyu Hu, Juntao Lyu +2
Large Language Models (LLMs) generalize across tasks through reusable representations and flexible reasoning, yet remain brittle in real deployment when faced with evolving tasks a…
GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent Systems
Yiqin Yang, Xu Yang, Yuhua Jiang +8
In the realm of multi-agent systems, the challenge of \emph{partial observability} is a critical barrier to effective coordination and decision-making. Existing approaches, such as…
DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning
Runpeng Xie, Quanwei Wang, Hao Hu +7
Comprehending natural language and following human instructions are critical capabilities for intelligent agents. However, the flexibility of linguistic instructions induces substa…
Risk-Sensitive RL for Alleviating Exploration Dilemmas in Large Language Models
Yuhua Jiang, Jiawei Huang, Yufeng Yuan +4
Reinforcement Learning with Verifiable Rewards (RLVR) has proven effective for enhancing Large Language Models (LLMs) on complex reasoning tasks. However, existing methods suffer f…
DSAC: Distributional Soft Actor-Critic for Risk-Sensitive Reinforcement Learning
Xiaoteng Ma, Junyao Chen, Li Xia +3
We present Distributional Soft Actor-Critic (DSAC), a distributional reinforcement learning (RL) algorithm that combines the strengths of distributional information of accumulated…
PAG: Multi-Turn Reinforced LLM Self-Correction with Policy as Generative Verifier
Yuhua Jiang, Yuwen Xiong, Yufeng Yuan +5
Large Language Models (LLMs) have demonstrated impressive capabilities in complex reasoning tasks, yet they still struggle to reliably verify the correctness of their own outputs.…