Home Knowledge Base GSPO

GSPO

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

The Flip Side of RLHF: On-Policy Feedback for Reward Model Self-Supervised Improvement

arXiv:2605.30888v1 Announce Type: new Abstract: Building strong reward models (RMs) for language model alignment is bottlenecked by the cost and difficulty of acquiring diverse and reliable preference data from human annotation or judge models. It is dramatically worse as the policy evolves beyond the static RM training. Therefore, we propose SAVE (Self-supervised reward model improvement via Value-Anchored On-policy feedback), a framework that grades on-policy responses as feedback by using...

arXiv CS 9d ago

Improving Small Language Models for Code Generation with Reinforcement Learning from Verification Feedback

arXiv:2605.30478v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) trains language models using programmatically checkable signals such as unit-test outcomes, enabling direct optimization for functional correctness in code generation. We conduct an empirical study of RLVR for Python code generation on the MBPP benchmark using two small models (Qwen3-0.6B and Llama3.2-1B) with LoRA fine-tuning. Across multiple reward formulations such as: unit-test-only...

arXiv CS 9d ago

TAPO: Tool-Aware Policy Optimization via Credit Transfer for Multimodal Search Agents

arXiv:2606.05784v1 Announce Type: new Abstract: We identify and formally characterize credit misassignment as a systematic failure mode of GRPO in tool-augmented multimodal search agents: its uniform broadcast of trajectory-level advantages to all tokens causes valuable tool-use steps in failing trajectories to be penalized no differently from valueless ones. We further empirically quantify the scale of this phenomenon. Over half of failing trajectories and failing tool-use actions exhibit...

arXiv CS 5d ago

Counterfactual Credit Policy Optimization for Multi-Agent Collaboration

arXiv:2603.21563v3 Announce Type: replace Abstract: Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assignment: shared terminal rewards obscure individual contributions and can encourage free-riding. We introduce Collaborative Credit Policy Optimization (CCPO), an optimizer-agnostic credit assignment layer that converts team-level outcomes into agent-specific...

arXiv CS 9d ago

Translate-R1: Cost-Aware Translation Tool Use via Reinforcement Learning

new Abstract: The performance gap across languages in LLMs is well documented, and closing it natively requires pretraining or fine-tuning on corpora that, for most languages, do not exist. Translation offers an alternative: converting an input into the model's dominant language unlocks its full capabilities at once. Applying translation to every input, however, is wasteful for languages the model already handles, while leaving the choice to the model fails in the opposite way, as LLMs are...

arXiv CS 2d ago

MedForge: Interpretable Medical Deepfake Detection via Forgery-aware Reasoning

arXiv:2603.18577v2 Announce Type: replace Abstract: Text-guided image editors can now manipulate authentic medical scans with high fidelity, enabling lesion implantation/removal that threatens clinical trust and safety. Existing defenses are inadequate for healthcare. Medical detectors are largely black-box, while MLLM-based explainers are typically post-hoc, lack medical expertise, and may hallucinate evidence on ambiguous cases.

arXiv CS 6d ago

PInVerify: An Offline Embodied Benchmark for Active Instance Verification

arXiv:2605.30639v1 Announce Type: new Abstract: Embodied agents have made strong progress in navigating to target objects, but reaching the goal vicinity does not guarantee that the agent has found the correct instance: subtle attribute differences (e.g., "white floral" vs. "white striped") often require close-range, multi-view inspection. We address this gap with Active Instance Verification (AIV), a task in which an agent actively selects viewpoints around a candidate object to decide...

arXiv CS 9d ago

Counterfactual Credit Policy Optimization for Multi-Agent Collaboration

Announce Type: replace Abstract: Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assignment: shared terminal rewards obscure individual contributions and can encourage free-riding. We introduce Collaborative Credit Policy Optimization (CCPO), an optimizer-agnostic credit assignment layer that converts team-level outcomes into agent-specific learning signals. CCPO...

arXiv CS 1d ago

CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents

Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven breakthroughs in domains such as math, tool-use, and software engineering, yet its extension to computer-use agents (CUAs) has been bottlenecked by the scarcity of scalable training data with deterministic rewards. Constructing such data for CUAs requires consistent task instruction, executable environment, and verifiable reward. However, hand-curated benchmarks achieve high reward fidelity but...

arXiv CS 1d ago