7 papers
GEAR: Granularity-Adaptive Advantage Reweighting for LLM Agents via Self-Distillation
Sijia Li, Yuchen Huang, Zifan Liu +7
Reinforcement learning has become a widely used post-training approach for LLM agents, where training commonly relies on outcome-level rewards that provide only coarse supervision.…
GAS: Enhancing Reward-Cost Balance of Generative Model-assisted Offline Safe RL
Zifan Liu, Xinran Li, Shibo Chen +1
Offline Safe Reinforcement Learning (OSRL) aims to learn a policy to achieve high performance in sequential decision-making while satisfying constraints, using only pre-collected d…
Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory
Sijia Li, Yuchen Huang, Zifan Liu +6
As intents unfold and environments change, multi-turn agents face continuously shifting decision contexts. Although reusing past experience is intuitively appealing, existing appro…
TSDS: Data Selection for Task-Specific Model Finetuning
Zifan Liu, Amin Karbasi, Theodoros Rekatsinas
Finetuning foundation models for specific tasks is an emerging paradigm in modern machine learning. The efficacy of task-specific finetuning largely depends on the selection of app…
Reinforcement Learning with Intrinsically Motivated Feedback Graph for Lost-sales Inventory Control
Zifan Liu, Xinran Li, Shibo Chen +3
Reinforcement learning (RL) has proven to be well-performed and general-purpose in the inventory control (IC). However, further improvement of RL algorithms in the IC domain is imp…
Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning
Xinran Li, Zifan Liu, Shibo Chen +1
In multi-agent reinforcement learning (MARL), effective exploration is critical, especially in sparse reward environments. Although introducing global intrinsic rewards can foster…