SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks
SCOPE is a data-free self-play framework for training language models on open-ended tasks without external supervision or frontier-model judges. It co-evolves two policies—a Challenger that generates document-grounded tasks and a Solver that answers via multi-turn retrieval—using a frozen copy of the initial model as a self-judge that writes task-specific rubrics. Across three 7-8B models (Qwen2.5, Qwen3, OLMo-3), SCOPE achieves up to +10.4 points on eight open-ended benchmarks and +13.8 points on seven held-out short-form QA benchmarks, matching or exceeding GRPO trained on ~9K curated prompts. Ablations identify rubric generation quality as the primary bottleneck for self-judging.
Related guides (4)
Related events (8)
ZPPO: Teacher-in-prompt training method outperforms distillation and GRPO for small vision-language models
Researchers introduce Zone of Proximal Policy Optimization (ZPPO), a training method inspired by Vygotsky's zone of proximal development that embeds teacher guidance in prompts rather than policy gradients or logit imitation. On hard questions where student rollouts fail, ZPPO constructs Binary Candidate-included Questions (BCQ) and Negative Candidate-included Questions (NCQ) to help the student discriminate correct from incorrect responses, with a replay buffer that recirculates hard questions until mastered. Evaluated on the Qwen3 family (0.8B–9B) with a 27B teacher across a 31-benchmark suite covering VLM, LLM, and video tasks, ZPPO outperforms both distillation and GRPO baselines, with the largest gains at the smallest model scale. The method addresses a known failure mode of RL training where zero-reward rollouts produce no gradient signal.
AXPO: Agent Explorative Policy Optimization Addresses Thinking-Acting Gap in Multimodal Agentic Reasoning
This paper identifies a structural asymmetry in agentic reasoning called the 'Thinking-Acting Gap,' where tool use is attempted in only ~30% of rollouts under standard RL training (GRPO), and all-wrong tool-using subgroups suppress learning signals. The authors propose AXPO (Agent eXplorative Policy Optimization), which fixes the thinking prefix and resamples tool calls for all-wrong subgroups, combined with uncertainty-based prefix selection. Evaluated across nine multimodal benchmarks on Qwen3-VL-Thinking at multiple scales, SFT+AXPO outperforms SFT+GRPO by +1.8pp on both Pass@1 and Pass@4 at 8B, with the 8B model surpassing the 32B baseline on Pass@4 using 4× fewer parameters.
GSPO: Group Sequence Policy Optimization for Scalable RL Training of Language Models
Qwen researchers introduce Group Sequence Policy Optimization (GSPO), a new RL algorithm designed to address severe training instability and model collapse observed in existing methods like GRPO during extended training runs. The core motivation is enabling stable RL scaling for language models to improve reasoning and problem-solving capabilities with increased compute. The paper targets a known bottleneck in post-training pipelines where instability prevents further performance gains.
SkillOpt: Systematic Text-Space Optimizer for Self-Evolving Agent Skills
SkillOpt introduces a principled optimization framework for agent skills, treating the skill document as an external trainable state analogous to model weights. A separate optimizer model converts scored rollouts into bounded edits (add/delete/replace) on a skill document, accepting only edits that improve held-out validation scores. Evaluated across six benchmarks, seven target models, and three execution harnesses (direct chat, Codex, Claude Code), SkillOpt achieves best or tied performance on all 52 evaluated cells, lifting GPT-5.5 no-skill accuracy by up to +24.8 points inside the Codex agentic loop. Optimized skill artifacts also transfer across model scales and execution environments without further optimization.
PROVE framework trains LLMs for multi-step tool use via stateful MCP environments and programmatic rewards
Researchers introduce PROVE (Programmatic Rewards On Verified Environments), a framework for training LLMs to orchestrate multi-step tool calls using reinforcement learning. The system includes a library of 20 stateful MCP servers with 343 tools, an automated data synthesis pipeline that grounds training queries in live server state, and a multi-component programmatic reward function requiring no judge model. Training four models (Qwen3-4B, Qwen3-8B, Qwen2.5-7B, Granite-4.1-8B) with ~13K examples yields gains of up to +10.2 on BFCL Multi-Turn, +6.8 on tau2-bench, and +6.5 on T-Eval, demonstrating consistent improvements in multi-step tool orchestration.
OverEager-Bench: Measuring Out-of-Scope Actions by Coding Agents on Benign Tasks
This paper introduces OverEager-Gen/Bench, a 500-scenario benchmark measuring 'overeager' behavior in coding agents—cases where agents with shell, file, and network access take unauthorized actions beyond the user's stated request on benign tasks. The study reveals a critical measurement-validity issue: explicitly declaring authorized scope in prompts suppresses overeager behavior (e.g., Claude Code drops from 17.1% to 0.0%), so the benchmark uses consent-stripped variants to expose true agent tendencies. Across four agent products (Claude Code, OpenHands, Codex CLI, Gemini CLI) and six base models, framework architecture dominates effect size: permissive frameworks run at 5.4–27.7% overeager rates while OpenHands' ask-to-continue design sits at 0.2–4.5%. Within-framework base-model variance of up to 15.9 pp indicates that model-level alignment does not fully propagate through permissive permission gating.
Step-aligned critique outperforms GRPO and reference-solution conditioning in self-distillation
A new arXiv paper investigates context design for self-distillation of language models, comparing binary reward (GRPO), reference solutions, and step-by-step critiques aligned to the solver's reasoning trace. Step-aligned critique yields the largest gains, outperforming GRPO by 16.11 points and reference-solution conditioning by 5.27 points on Avg@12. Per-token advantage analysis shows that step-aligned feedback targets only failing tokens, avoiding unnecessary pressure on already-correct reasoning steps. The findings suggest structural alignment between feedback and the model's reasoning trace is a key driver of self-distillation effectiveness.
POW3R: Policy-Aware Rubric Rewards for More Efficient RLVR Training
This paper identifies a failure mode in rubric-based reinforcement learning with verifiable rewards (RLVR): static aggregation of criterion weights conflates human-assigned importance with current optimization utility, causing many criteria to be either already saturated or unreachable. The authors introduce POW3R, a framework that dynamically reweights criterion-level rewards during training using rollout-level contrast to emphasize criteria that currently differentiate policy outputs. Across three base policies and two datasets (multimodal and text-only), POW3R wins 24 of 30 comparisons on rubric reward and strict completion metrics, and reaches equivalent performance in 2.5–4× fewer training steps than vanilla GRPO with rubric rewards.