CL-Bench is the first expert-validated benchmark for continual learning in frontier LLMs across six real-world domains, showing limited gains and that naive in-context learning outperforms dedicated memory systems.
SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Software development is iterative, yet agentic coding benchmarks hide design issues through their single-shot setup. Recent iterative benchmarks attempt to remedy this but heavily constrain an agent's design decision space, making it impossible to faithfully measure how their decisions shape future extensions. We introduce SlopCodeBench, a benchmark of 36 problems and 196 checkpoints where agents repeatedly extend their own solutions. Unlike prior iterative benchmarks, our evolving specifications demand architectural decisions but leave internal structure to the agent. We measure two forms of degradation: structural erosion (concentrated complexity) and verbosity (redundant code). Evaluating 15 coding agents across open and closed models, we find that no agent fully solves any problem end-to-end, and the best agent passes 14.8% of checkpoints. Quality degrades across checkpoints, with structural erosion rising in 77% of trajectories and verbosity in 75.5%. Compared to 473 open-source Python repositories, agent code is 2.3x more verbose and 2.0x more eroded, and the human repositories degrade less often and by smaller margins across their git histories. Explicit quality guidance reduces initial verbosity and erosion by up to a third, without affecting degradation rates. SlopCodeBench provides the first measurement of code degradation under iterative extension, revealing that agents pass checkpoints while producing code that erodes and bloats with each turn.
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Agent-generated code produces up to 13.1% lower follow-on task resolution rates than human code in chained repository-level experiments, with differences linked to behavioral patterns rather than conventional metrics.
EvoPolicyGym is a new benchmark suite of 16 compact RL environments that evaluates autonomous policy evolution, with GPT-5.5 achieving the top aggregate rank and top-two performance on all tasks.
citing papers explorer
-
Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments
CL-Bench is the first expert-validated benchmark for continual learning in frontier LLMs across six real-world domains, showing limited gains and that naive in-context learning outperforms dedicated memory systems.
-
Is Agent Code Less Maintainable Than Human Code?
Agent-generated code produces up to 13.1% lower follow-on task resolution rates than human code in chained repository-level experiments, with differences linked to behavioral patterns rather than conventional metrics.
-
EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments
EvoPolicyGym is a new benchmark suite of 16 compact RL environments that evaluates autonomous policy evolution, with GPT-5.5 achieving the top aggregate rank and top-two performance on all tasks.