HFEPX · Eval paper review
Shouli Wang, Yanfeng Jia, Zhihao Ou, Zitao Su +5 more
Published
Sep 30, 2026
Citations
0
Trust level
Low
Usefulness score
0/100 (Low)
Extraction confidence
15% (Low)
Derived from extracted protocol signals and abstract evidence.
Rater population
Not reported
Signals refreshed
Oct 2, 2026
This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.
Use this as background context only. Do not make protocol decisions from this page alone.
All signals on this page are inferred from the abstract only and may be inaccurate. Do not use this page as a primary protocol reference.
Best use
Background context only
Use if you need
Background context only.
What to verify
Read the full paper before copying any benchmark, metric, or protocol choices.
Main weakness
This paper looks adjacent to evaluation work, but not like a strong protocol reference.
Treat as adjacent context, not a core eval-method reference.
If you are doing eval pipeline work, start here
During reinforcement learning with verifiable rewards (RLVR), large language models (LLMs) can exploit loopholes in their environments to obtain high rewards without improving the intended capabilities, i.e., reward hacking. Despite its risks to training efficiency and safety, monitoring and mitigating reward hacking during training remain challenging, which is limited by a lack of testbeds that reproduce hacking and reliably identify it. We introduce CATCH, a controllable testbed for studying reward hacking in coding RL. CATCH deliberately exposes environmental loopholes and provides execution-based gold labels by comparing success under a vulnerable evaluator with task correctness under an independent audit. It also can control the model's initial hacking tendency through supervised fine-tuning data mixtures and the difficulty of earning rewards through reward designing, enabling systematic comparisons of hacking dynamics and interventions. Experiments show that CATCH can produce diverse RL training trajectories with clear reward hacking, and analyses demonstrate that both initial models and reward difficulties shape the emergence of reward hacking. We further evaluate the effectiveness of different reward hacking detection and mitigation methods. A key finding is that a chain-of-thought monitor initially suppresses hacking, but this protection erodes as the policy model learn to mislead the monitor with code comments. This highlights the need to evaluate hacking mitigations throughout training with CATCH. The source code and resources are publicly released at https://github.com/THUAIS-Lab/CATCH.
These are the protocol signals we could actually recover from the available paper metadata. Use them to decide whether this paper is worth deeper reading.
None explicit
No explicit feedback protocol extracted.
"During reinforcement learning with verifiable rewards (RLVR), large language models (LLMs) can exploit loopholes in their environments to obtain high rewards without improving the intended capabilities, i.e., reward hacking."
None explicit
Validate eval design from full paper text.
"During reinforcement learning with verifiable rewards (RLVR), large language models (LLMs) can exploit loopholes in their environments to obtain high rewards without improving the intended capabilities, i.e., reward hacking."
Not reported
No explicit QC controls found.
"During reinforcement learning with verifiable rewards (RLVR), large language models (LLMs) can exploit loopholes in their environments to obtain high rewards without improving the intended capabilities, i.e., reward hacking."
Not extracted
No benchmark anchors detected.
"During reinforcement learning with verifiable rewards (RLVR), large language models (LLMs) can exploit loopholes in their environments to obtain high rewards without improving the intended capabilities, i.e., reward hacking."
Not extracted
No metric anchors detected.
"During reinforcement learning with verifiable rewards (RLVR), large language models (LLMs) can exploit loopholes in their environments to obtain high rewards without improving the intended capabilities, i.e., reward hacking."
No benchmark or dataset names were extracted from the available abstract.
No metric terms were extracted from the available abstract.
During reinforcement learning with verifiable rewards (RLVR), large language models (LLMs) can exploit loopholes in their environments to obtain high rewards without improving the intended capabilities, i.e., reward hacking.
Based on abstract + metadata only. Check the source paper before making high-confidence protocol decisions.
Human feedback protocol is explicit
No explicit human feedback protocol detected.
Evaluation mode is explicit
No clear evaluation mode extracted.
Quality control reporting appears
No calibration/adjudication/IAA control explicitly detected.
Benchmark or dataset anchors are present
No benchmark/dataset anchor extracted from abstract.
Metric reporting is present
No metric terms extracted.
