The Chase Is the Curriculum, the Capture Anchors the Credit: Pursuit-Evasion Self-Play for Zero-Data LLM Reasoning

• URL: http://arxiv.org/abs/2608.21871v1
• Date: Sat, 22 Aug 2026 09:30:29 GMT
• Title: The Chase Is the Curriculum, the Capture Anchors the Credit: Pursuit-Evasion Self-Play for Zero-Data LLM Reasoning
• Abstract summary: In LURE, an LLM evader positions tasks along each environment's difficulty axis to stay one step ahead of a pursuer that hunts it down through verifiable interaction.<n>The pursuer earns capture-anchored dense process credit, in which monotone verifier progress is group-normalized jointly with the terminal capture under a round-anchored KL that keeps the co-evolution stable.
• Score: 6.195031716121927
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning with verifiable rewards has become the dominant recipe for improving large language model reasoning, yet it presumes large human-curated task collections. Zero-data self-play removes this dependency, but existing methods vet learnability only by probing candidates and rejecting post hoc, never learning where along an environment's difficulty axis to place a task, and credit the solver with sparse terminal rewards alone. We recast zero-data self-play as a pursuit-evasion game: in LURE, an LLM evader positions tasks along each environment's difficulty axis to stay one step ahead of a planner-executor pursuer that hunts it down through verifiable interaction. The evader is trained on a capture-frontier reward that peaks when the solver captures it on exactly half of its rollouts, turning barely catchable into a learned positioning strategy rather than a hand-tuned rejection band. The pursuer earns capture-anchored dense process credit, in which monotone verifier progress is group-normalized jointly with the terminal capture under a round-anchored KL that keeps the co-evolution stable. Across three verifiable reasoning environments and three backbone families, LURE outperforms advanced baselines under unified/specialist settings, while the unified model attains stronger aggregate OOD zero-shot accuracy than all trained baselines across nine held-out benchmarks from three task families.

Related papers

• Explore More, Drift Less: Outcome-Only Reinforcement Learning Can Suffice for Long-Horizon Interactive Agents [3.3656546156010942]
  Reinforcement learning is a natural way to post-train agents for long-horizon interactive tasks judged only by end-of-task verification.<n>Recent work compensates around the training with denser rewards, SFT priors, skill libraries, curated memory, or multi-agent orchestration.<n>We present CANOPY, a minimalist protocol attacking both directly: scale same-task exploration until the natural signal reappears, keep every update on-policy, KL-anchored, and confined to the agent's own action tokens.
  arXiv  Detail & Related papers  (2026-09-01T13:44:40Z)
• ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning [74.19730275669227]
  ARISE-RL is a novel full-cycle self-evolution framework for training open-ended agents.<n>We present Reward-Gated Self-Evolution Distillation (RG-SED), which distills a memory-augmented variant of the same policy back into itself.<n>We also present ECR-Bench, an expert-calibrated rubric benchmark suite covering single-tool deep research and multi-tool travel planning.
  arXiv  Detail & Related papers  (2026-09-01T10:54:13Z)
• Rolling With Resistance: Preference-Optimized LLM Counselors Can Trade Goal Persistence for Relational Attunement in Motivational Interviewing [0.6372261626436676]
  In Motivational Interviewing (MI), a client's sustain talk (arguments for the status quo) calls for the counselor to roll with resistance, a move that can fail in two ways.<n>We introduce a two-axis evaluation of counselor responses of Motivational Interviewing Treatment Integrity (MITI) code, Goal Persistence (GP) and Attunement (RA)<n>We ask whether penalizing one failure through preference optimization teaches rolling resistance provokes its opposite.
  arXiv  Detail & Related papers  (2026-07-30T20:16:03Z)
• Group-Reflective Self-Distillation for Agentic Reinforcement Learning [8.041052886037766]
  Group-Reflective Self-Distillation (GRSD) derives capability-aligned and outcome-discriminative guidance from the policy's own verified rollouts.<n>GRSD consistently outperforms competitive baselines and generalizes more effectively to unseen tasks.
  arXiv  Detail & Related papers  (2026-07-30T11:49:46Z)
• Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills [53.15216425100295]
  We introduce Skill Self-Play (Skill-SP), a co-evolutionary framework comprising a proposer, a solver, and a skill controller.<n>The proposer generates challenging tasks conditioned on dynamically sampled skills; the solver explores candidate solutions to push its capability boundaries; and the skill controller collects execution feedback to update and expand the skill library.<n>This interactive co-evolution effectively bridges the gap between structured verification and open-ended exploration.
  arXiv  Detail & Related papers  (2026-07-24T17:59:22Z)
• Localizing Credit at the Divergence: Path-Conditioned Self-Distillation for LLM Reasoning [12.363923974156636]
  Reinforcement learning from verifiable rewards assigns a single scalar to each rollout.<n>On-policy self-distillation addresses this by letting the same model act as a teacher conditioned on privileged information.<n>We propose Hindsight Self-Distillation (HSD), which conditions the teacher on a successful peer rollout.
  arXiv  Detail & Related papers  (2026-06-14T03:37:27Z)
• HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-Distillation [50.53459634301361]
  HERO is a hindsight-enhanced self-distillation framework that uses next environment observations as locally aligned feedback.<n> HERO improves task success and reduces unnecessary turns over environment-feedback-only self-distillation and GRPO.
  arXiv  Detail & Related papers  (2026-06-10T01:35:34Z)
• Self-evolving LLM agents with in-distribution Optimization [60.05867547965365]
  Large Language Models (LLMs) have recently emerged as powerful controllers for interactive agents in complex environments.<n>We propose Q-Evolve, a self-evolving framework for LLM agents that unifies automatic process-reward labeling and policy learning.<n>We evaluate our method on AlfWorld, WebShop, and ScienceWorld, showing Q-Evolve outperforms strong baselines in sample efficiency, robustness, and overall task performance.
  arXiv  Detail & Related papers  (2026-06-05T15:09:52Z)
• Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RL [76.45061154544568]
  Self-play reinforcement learning trains language models on their own generated tasks, co-evolving a proposer and solver without human labels.<n>Recent systems report strong reasoning gains, but collapse and instability are widely observed and poorly understood.<n>We argue instead that self-play stability is governed by two distinct levers: a data-level gate that decides which proposer-generated tasks enter the training pool, and the reward signal that updates the policy on tasks already admitted.
  arXiv  Detail & Related papers  (2026-05-21T09:19:23Z)
• R$^3$L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification [44.99719889905381]
  Reinforcement learning drives recent advances in reasoning and agentic capabilities, yet current approaches struggle with both exploration and exploitation.<n>We propose R$3$L, Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification.<n>Experiments on agentic and reasoning tasks demonstrate 5% to 52% relative improvements over baselines while maintaining training stability.
  arXiv  Detail & Related papers  (2026-01-07T09:04:52Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning [87.7836502955847]
  We propose a novel self-rewarding reinforcement learning framework to enhance Large Language Model (LLM) reasoning.<n>Our key insight is that correct responses often exhibit consistent trajectory patterns in terms of model likelihood.<n>We introduce CoVo, an intrinsic reward mechanism that integrates Consistency and Volatility via a robust vector-space aggregation strategy.
  arXiv  Detail & Related papers  (2025-06-10T12:40:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.