Teach the Magnitude, Not the Direction: Verifier-Bounded Credit Assignment for Multi-Turn Multi-step LLM Agents

• URL: http://arxiv.org/abs/2608.13179v1
• Date: Thu, 13 Aug 2026 12:44:37 GMT
• Title: Teach the Magnitude, Not the Direction: Verifier-Bounded Credit Assignment for Multi-Turn Multi-step LLM Agents
• Abstract summary: Reinforcement learning with verifiable rewards conflates heterogeneous per-turn outcomes into a single reward signal.<n>On-policy distillation provides dense per-token supervision but is either teacher-bounded or prone to gradient concentration collapse.<n>We introduce $textbfCrEST$, a hierarchical credit assignment framework that retains RL's verifier-bounded ceiling while incorporating dense token-level signals from a privileged self-teacher.
• Score: 15.12019413574721
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Reinforcement learning with verifiable rewards (RLVR) offers a verifier-bounded performance ceiling for training multi-turn tool-use agents, yet its trajectory-level credit assignment conflates heterogeneous per-turn outcomes into a single reward signal. On-policy distillation provides dense per-token supervision but is either teacher-bounded or prone to gradient concentration collapse. We introduce $\textbf{CrEST}$, a hierarchical credit assignment framework that retains RL's verifier-bounded ceiling while incorporating dense token-level signals from a privileged self-teacher. $\textbf{CrEST}$ resolves credit at two levels: turn-segmented verified advantages address inter-turn dilution, while entropy-gated self-teacher modulation refines intra-turn token contributions. Experiments on BFCL V3 and WildToolBench show that $\textbf{CrEST}$ consistently outperforms both RL and distillation baselines across two model scales, with the largest gains on long-trajectory and strict session-level metrics. Our work demonstrates that the teacher's role in policy optimization can be reduced from determining update directions to modulating update magnitudes, unlocking dense credit assignment without sacrificing the verifier-bounded ceiling.

Related papers

• How Much, Then Where: Credit-Conserving Action-to-Token Allocation for Multi-Turn Agent Reinforcement Learning [10.15294517210249]
  We introduce FACTOR, which separates the decision to assign trajectory-level credit to actions and distributing each action's credit across its tokens.<n>FACTOR consistently improves over competitive baselines across ALFWorld, WebShop, and ScienceWorld.
  arXiv  Detail & Related papers  (2026-08-07T11:22:09Z)
• AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning [58.76655851910778]
  AgentOPSD is a critic-free, recursive method for turn-level credit assignment in agentic reinforcement learning.<n>We evaluate AgentOPSD on ALFWorld, WebShop, and Search-QA using Qwen2.5 models at two scales (3B and 7B)
  arXiv  Detail & Related papers  (2026-08-06T13:00:59Z)
• Agentic Reinforcement Learning with Self-Distilled Reward Shaping [12.091871903119698]
  Agentic reinforcement learning enables LLM agents to learn through interaction, but sparse trajectory-level rewards reveal success without identifying which intermediate decisions deserve credit.<n>We introduce Agentic Reinforcement Learning with Self-Distilled Reward Shaping, a framework for constructing return-associated token-level credit for language agents.<n>Experiments show that ADRS consistently improves performance on long-horizon tasks, with gains persisting across RL backbones, reduced-data settings, unseen tasks, and extended training.
  arXiv  Detail & Related papers  (2026-08-04T06:56:47Z)
• H$^2$SD: Hybrid Hindsight Self-Distillation [61.71131241473028]
  Reinforcement learning with verifiable rewards (RLVR) provides reliable outcome supervision for language model reasoning.<n>Existing self-distillation methods add a privileged teacher but typically assign it a fixed role.<n>We introduce Hybrid Hindsight Self-Distillation ($mathrmH2mathrmSD$), which jointly adapts teacher context and update strategy to trajectory correctness.
  arXiv  Detail & Related papers  (2026-07-21T10:47:27Z)
• TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents [51.523913302114266]
  TRACE (Turn-level Reward Assignment via Credit Estimation) is a dense credit-assignment method for agentic reinforcement learning.<n>It represents rollouts as state transitions at tool-call boundaries, obtains gold-answer log-probabilities from a frozen reference model, transforms them into log-ratio state values, and derives per-action rewards as Temporal-Difference changes in those values.<n>It substantially improves base-model tool-use ability using pure RL, without a cold-start supervised fine-tuning stage, an agentic mid-training stage, or training on live-web data.
  arXiv  Detail & Related papers  (2026-07-15T16:16:42Z)
• CRAFT: Counterfactual Credit Assignment from Free Sibling Rollouts for Self-Distilled Agentic Reinforcement Learning [4.663685189987781]
  Self-distilled agentic reinforcement learning augments trajectory-level reward with a token-level distillation loss.<n>The prevailing recipe gates this loss by a single scalar, the teacher-student log-probability gap.<n>We introduce CRAFT, a threepillar credit-assignment scheme that addresses both limitations.
  arXiv  Detail & Related papers  (2026-06-28T16:11:47Z)
• OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification [21.095025092772257]
  On-Policy Distillation (OPD) trains a student model on its own generative trajectories under dense token-level feedback from a stronger teacher.<n>We introduce OmniOPD, a novel framework that addresses both limitations through a logit-free, chunk-level supervision signal.
  arXiv  Detail & Related papers  (2026-05-31T22:31:15Z)
• Self-Distilled Agentic Reinforcement Learning [65.24201057390938]
  Self-Distilled Agentic Reinforcement Learning maps detached token-level signals into a sigmoid gate.<n>SDAR consistently outperforms hybrid RL--OPSD baselines across model scales.
  arXiv  Detail & Related papers  (2026-05-14T17:51:26Z)
• Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense Supervision [50.61441331643804]
  Reinforcement learning (RLVR) relies on binary rewards, which are broadly applicable and powerful, but provide only sparse supervision during training.<n>Distillation provides dense token-level supervision, typically obtained from an external teacher or using high-quality demonstrations.<n>We propose Self-Distillation Zero (SD-Zero), a method that is substantially more training sample-efficient than RL and does not require an external teacher or high-quality demonstrations.
  arXiv  Detail & Related papers  (2026-04-13T19:46:55Z)
• Self-Distilled RLVR [57.37526213765131]
  We show that learning signals solely derived from the privileged teacher result in severe information leakage and unstable long-term training.<n>We propose textbfRLSD (textbfRLVR with textbfSelf-textbfDistillation)<n>This enables RLSD to simultaneously harness the strengths of both RLVR and OPSD, achieving a higher convergence ceiling and superior training stability.
  arXiv  Detail & Related papers  (2026-04-03T15:50:07Z)

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.