arXiv AI
Jun 16
Auditing Reward Hackability in Code RL Training Environments
arXiv:2606. 16062v1 Announce Type: new Abstract: We measure the rate at which code RL environments accept incorrect solutions as correct.
When the Reward Suite Is Leaky: A Preregistered Causal Contrast of Natural Verifier False Positives in RLVR
arXiv:2607. 11022v1 Announce Type: new Abstract: The test suites used as RLVR rewards for code have natural false positives: per-task, persistent, asymmetric errors that accept the same wrong programs every time they appear, unlike the symmetric or resampled noise assumed by existing noise-robustness analyses.
Related stories
arXiv AI
Aug 3
Validation Evidence in LLM Repair Agents: How Much of What Passes Actually Tests the Bug?
arXiv:2607. 28871v1 Announce Type: cross Abstract: When a repair agent runs a test and sees it pass, the result is treated as evidence about the reported defect.
arXiv AI
Jul 9
The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents
arXiv:2607. 07436v1 Announce Type: new Abstract: A self-evolving agent retires its bad skills by watching them fail, so what happens when the judge cannot see the failures?
arXiv AI
Aug 21
Phantom Gains: Auditing Self-Improvement Against a Measured Null
arXiv:2608. 20290v1 Announce Type: new Abstract: Whether a language model has improved itself is increasingly judged not by mean accuracy but by which individual problems it gains and loses.
arXiv Machine Learning
Jul 1
Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models
arXiv:2606. 31511v1 Announce Type: cross Abstract: In deployment settings where retraining is infeasible, small frozen code models are routinely asked to repair a failed program after seeing their own failing output, usually treated as a retry mechanism.
arXiv Machine Learning
Aug 11
Quality-Diversity Stress Tests for Process Reward Models:What Archive Coverage Can and Cannot Certify
arXiv:2608. 08008v1 Announce Type: new Abstract: Process reward models (PRMs) score intermediate reasoning steps and are widely used for search, ranking, and training, but optimization can exploit these learned proxies by increasing reward while turning correct reasoning into incorrect reasoning.
Hugging Face Trending Papers
Aug 20
Phantom Gains: Auditing Self-Improvement Against a Measured Null
Whether a language model has improved itself is increasingly judged not by mean accuracy but by which individual problems it gains and loses. Tracking these transitions means differencing two noisy estimates, leaving them vulnerable to measurement artifacts.
arXiv AI
Jul 15
Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models
arXiv:2607. 12962v1 Announce Type: cross Abstract: Frozen small code LLMs are deployed locally, yet the information guiding a retry after a failed attempt is still measured without placebo controls in the self-repair literature.
arXiv AI
Sep 3
Coverage, Not Targeting: A Structural Regime in Multi-Turn Agent Credit Assignment
The paper argues that in multi‑turn agentic reinforcement learning, credit assignment should be viewed as a coverage problem rather than a targeting problem. It introduces verifier information density (V_d) as a structural metric, showing that terminal‑state verifiers operate in a low‑V_d regime where targeting fails. Experiments on tau^2‑bench, BFCL, and ToolACE‑2‑8B demonstrate that uniformly distributing reward across all turns outperforms sparse, targeted rewards, and that full chain coverage is necessary for optimal performance.
arXiv AI
Aug 21
Credit Without Ground Truth: Auditing Step-Level Credit Assignment in LLM Agents Against Executed Replay
arXiv:2608. 19760v1 Announce Type: cross Abstract: Audited against causal ground truth from executed replay in a single-agent tool environment (ALFWorld), none of the step-level credit signals used to train LLM agents -- LLM-judge scores, outcome-conditioned logprob ratios, or the policy's own confidence -- identifies which steps causally matter better than chance.
arXiv Machine Learning
Jun 5
A Pre-Registered Causal Partition of Self-Consistency Elicitation and Reward Design in RLVR
arXiv:2606. 05932v1 Announce Type: cross Abstract: Reinforcement learning from verifiable rewards (RLVR) improves reasoning even when the reward signal is spurious -- assigning credit to the group-plurality answer rather than a ground-truth verifier.
arXiv AI
Aug 18
No Task Fails Every Time: Why One-Shot Audits Are Structurally Blind to Agent Damage
arXiv:2608. 15286v1 Announce Type: cross Abstract: We introduce AgentRelBench, an environment-agnostic reliability instrument that computes ground-truth, severity-priced damage from database state diffs across repeated runs, with no LLM in the measurement path, demonstrated on EnterpriseOps-Gym.