Coverage, Not Targeting: A Structural Regime in Multi-Turn Agent Credit Assignment

• URL: http://arxiv.org/abs/2609.02417v1
• Date: Wed, 02 Sep 2026 10:37:12 GMT
• Title: Coverage, Not Targeting: A Structural Regime in Multi-Turn Agent Credit Assignment
• Abstract summary: Multi-turn agentic RL increasingly treats credit assignment as a targeting problem.<n>We show that terminal-state verifiers sit deep in a low-V_d regime where targeting is the wrong axis.
• Score: 5.864346468963738
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multi-turn agentic RL increasingly treats credit assignment as a targeting problem: given a terminal verifiable reward, per-turn methods localize credit onto the turns that mattered. We identify the structural quantity that predicts when this is the right move, the verifier information density V_d = k/C (the fraction of an agent's C-step causal chain whose per-turn correctness the verifier exposes), and show that terminal-state verifiers sit deep in a low-V_d regime where targeting is the wrong axis. In controlled shared-rollout comparisons on tau^2-bench that separate reward density from credit geometry, a continuous dense reward spread uniformly beats the sparse binary outcome reward (net-harmful on 4/5 seeds), while concentrating the same advantage on progress turns or on random turns is equally harmful: targeting is second-order. The mechanism is coverage: terminal-state verification collapses the observable signal to a single final-write turn (k=1 in 98% of rollouts) while success requires a 5-8 step chain of prerequisite tool calls. A synthetic phase boundary places the crossover at V_d* ~ 0.8, whereas measured V_d is ~0.15 on tau^2-bench and ~0.4 on BFCL V3; uniform also wins on BFCL, where a matched-concentration shuffled control is negative on 8/8 seeds. The effect reproduces across model families on ToolACE-2-8B (Delta = -0.048 over 32 pre-registered seeds; an independent 20-seed replication is itself significant), and a pre-registered matched-budget breadth sweep traces a monotone dose-response whose deficit vanishes only at full chain coverage, with a reward-to-go arm reaching full-coverage parity. Uniform redistribution is the zero-information coverage default that per-turn schemes must beat; we contribute the matched-concentration shuffled control that any targeting claim should clear.

Related papers

• WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training [48.290951447286744]
  WDL-OPD is a mixture-constrained co-training method with two trainable policies.<n>An anchor policy generates every rollout, an auxiliary policy evaluates the same visited states, and a geometric mixture of their token distributions is matched to a frozen teacher by reverse KL.<n>We show that freezing the auxiliary recovers an anchor-plus-contrast proxy target closely related to OPD$2$ and W2S-OPD, whereas joint training creates branch-level degrees of freedom that a static delta cannot express.
  arXiv  Detail & Related papers  (2026-08-10T11:22:53Z)
• Post-Hoc Trajectory-Risk Certification for Modular LLM-Based Security Agents [1.4915002678801434]
  We show that Bonferroni allocation is distribution-free but conservative under correlated errors.<n> coarse-to-fine label selection can create near-perfect measured correlation without learned dependence.<n>A modular certificate using per-stage certificates and a pairwise overlap bound yields a positive average gain of 0.6%.
  arXiv  Detail & Related papers  (2026-08-04T23:48:36Z)
• SMOPD: Selective Token-Entropy Masking for Dirty-History Multi-Turn On-Policy Self-Distillation [0.0]
  We introduce SMOPD (Selective Masking for On-Policy Distillation), a loss-only stabilization method for multi-turn OPSD.<n>For each generated middle-turn reply, SMOPD ranks token positions by student entropy and removes the lowest-entropy 20% from the clipped generalized Jensen-Shannon distillation loss.<n>This design targets token-level uncertainty rather than coarse trajectory outcomes, adds no parameters, and has zero inference-time overhead.
  arXiv  Detail & Related papers  (2026-07-30T08:40:30Z)
• The Dark Room in the Reward Channel: Dense Prediction Rewards Collapse GRPO-Trained LLM Agents -- and What Actually Works [3.040305634723913]
  We show that under group-normalized RL, a potential-based prediction reward drives every run into a degenerate absorbing state.<n>A single-episode ablation ablations the cause -- removing only GRPO's normalization turns the same reward from catastrophic into baseline parity.<n>Our central insight generalizes this: what z-scoring amplifies is a dense signal's within-group variance while all-fail groups dominate.
  arXiv  Detail & Related papers  (2026-07-23T12:50:18Z)
• CADENCE: Closing the Reasoning Gap via Coverage-Adaptive On-Policy Distillation [2.587194279527956]
  CADENCE is a unified framework with a targeted fix for each failure mode.<n>DRIFT schedules a per-token convex mixture of forward-KL and reverse-KL surrogate objectives on student-sampled trajectories.<n>Six components extend it: (A) COVA, a coverage-adaptive schedule accelerating the forward-to-reverse transition; (B) FTB, a forking-token boost concentrating gradient at high-entropy positions via a globally-normalized entropy reference; (D) LAP, brevity-preferential correct-rollout reinforcement; (E) EMR, an entropy-gnostic calibration
  arXiv  Detail & Related papers  (2026-07-18T20:16:26Z)
• Layer-Isolated Evaluation: Gating the Deterministic Scaffold of a Production LLM Agent with a No-LLM, Regression-Locked Test Harness [45.148328075418156]
  A deployed ordering agent is decomposed into a fixed taxonomy of layers.<n>The pure suite runs in CI on every change against a locked per-slice baseline.<n>We validate by controlled regression injection, degrading one layer at a time across seven non-safety layers.
  arXiv  Detail & Related papers  (2026-06-10T05:55:13Z)
• Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning [55.264863369127774]
  Current methods reduce each correct rollout to a single reward bit, ignoring the geometric structure shared among their hidden states.<n>We propose Hidden-Align, an auxiliary loss function that aligns the last-layer hidden states of correct rollouts at the anchor token during RL training, with zero overhead in both training and inference.<n>On eight mathematical reasoning benchmarks, Hidden-Align improves average pass@1 over the DAPO baseline by 3.8, 6.2, and 5.4 percentage points on Qwen3-1.7B, 4B, and 14B respectively, with consistent pass@k gains across all three scales.
  arXiv  Detail & Related papers  (2026-06-02T06:51:15Z)
• Stochastic Estimation of the Layer-wise Hessian Trace for Monitoring Neural-network Training [45.88028371034407]
  We present a parameter estimator of the trace of the diagonal blocks of the Hessian matrix of the empirical risk of a neural network.<n>The procedure combines the Hutchinson trace estimator with a single Hessian-vector product over the whole parameter vector.<n>We show that correctness under weight sharing requires the layer-wise Hessian to be assembled before the second differentiation.
  arXiv  Detail & Related papers  (2026-05-25T10:24:32Z)
• 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)
• Quantile Advantage Estimation for Entropy-Safe Reasoning [44.192277495613695]
  Reinforcement Learning with Verifiable Rewards (RLVR) strengthens LLM reasoning, but training often oscillates between entropy collapse and entropy explosion<n>We trace both hazards to the mean baseline used in value-free RL, which improperly penalizes negative-advantage samples under reward outliers.<n>We propose Quantile Advantage Estimation (QAE), replacing the mean with a group-wise K-quantile baseline.
  arXiv  Detail & Related papers  (2025-09-26T17:37:52Z)
• Clustered Switchback Designs for Experimentation Under Spatio-temporal Interference [44.644520116360106]
  We estimate the global average treatment effect (GATE), the difference between average outcomes having exposed all units at all times to treatment or to control.<n>We propose a clustered switchback design, where units are grouped into clusters and time steps are grouped into blocks.<n>We show that for graphs that admit good clustering, a truncated Horvitz-Thompson estimator achieves a $tilde O(1/NT)$ mean squared error (MSE)<n>Our results simultaneously generalize the results from citethu2022switchback,ugander2013graph and citetleung2022rate
  arXiv  Detail & Related papers  (2023-12-25T01:00:58Z)

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.