Challenge: Existing benchmarks focus on single-turn or single-step tasks, failing to capture iterative reasoning in real-world settings.
Approach: They propose a benchmark that evaluates multi-turn, multi-step reasoning through an interactive code-breaking task inspired by the "Turing Machine Board Game" the best model achieves 84% accuracy in Classic mode, but performance drops to 18% in Nightmare mode.
Outcome: The new benchmark evaluates multi-turn, multi-step reasoning through an interactive code-breaking task inspired by the "Turing Machine Board Game" the best model achieves 84% accuracy in Classic mode, but performance drops to 18% in Nightmare mode.

Similar Papers

MTR-Bench: A Comprehensive Benchmark for Multi-Turn Reasoning Evaluation (2026.acl-long)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) have shown promising results in complex reasoning tasks.
Approach: They propose to use a multi-turn reasoning evaluation framework to cover multi-turn interactions with the environments of large language models.
Outcome: The proposed framework covers diverse reasoning capabilities, fine-grained difficulty granularity, and necessitates multi-turn interactions with the environments.
MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues (2024.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have greatly enhanced dialogue systems, but evaluation of their capabilities remains a challenge.
Approach: They propose a model to evaluate the fine-grained abilities of Large Language Models in multi-turn dialogues.
Outcome: The proposed model evaluates 21 popular chatbots based on MT-Bench-101 . it includes 3 overarching abilities and 13 distinct tasks within multi-turn dialogue scenarios.
RiddleBench: A New Generative Reasoning Benchmark for LLMs (2026.findings-eacl)

Copied to clipboard

Challenge: Large Language Models (LLMs) show remarkable capabilities, but complex reasoning skills require deeper investigation.
Approach: They propose a benchmark of 1,737 puzzles to test reasoning beyond simple pattern matching.
Outcome: The proposed model performs poorly when faced with reordered constraints or irrelevant information.
MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification (2025.findings-acl)

Copied to clipboard

Challenge: Existing benchmarks of large language models focus on error detection, neglecting other scenarios like reasoning search.
Approach: et al. propose a multi-task, multimodal benchmark to assess effectiveness of PRMs . step correctness, answers aggregation and reasoning process search are evaluated . ethical principles of MPBench are based on a set of evaluation paradigms based in a text-based benchmark .
Outcome: a new benchmark assesses the effectiveness of large language models (LLMs) in multiple scenarios . it uses three evaluation paradigms to assess the effectiveness and compares them with existing models . a the proposed model improves reasoning accuracy by providing stepwise feedback for multi-step reasoning results .
Metric Calculating Benchmark: Code-Verifiable Complicate Instruction Following Benchmark for Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Recent frontier-level LLMs have saturated many previously difficult benchmarks, leaving little room for further differentiation.
Approach: They propose a benchmark to evaluate whether LLMs can execute string-matching NLP metrics by strictly following step-by-step instructions.
Outcome: The proposed benchmarks show that they can perform step-by-step execution, instruction adherence, numerical computation, and long-range consistency in handling intermediate results.
ACEBench: A Comprehensive Evaluation of LLM Tool Usage (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing benchmarks for evaluating LLMs’ tool usage face several limitations: limited evaluation scenarios, lacking assessments in real multi-turn dialogue contexts; narrow evaluation dimensions, with insufficient detailed assessments of how LLM use tools; and reliance on LLM or real API executions for evaluation, which introduces significant overhead.
Approach: ACEBench is a benchmark for evaluating tool usage in Large Language Models . it categorizes data into three primary types based on evaluation methodology: Normal, Special, and Agent.
Outcome: ACEBench categorizes data into three primary types based on evaluation methodology: Normal, Special, and Agent.
TRUEBench: Can LLM Response Meet Real-world Constraints as Productivity Assistant? (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing benchmarks fail to evaluate large language models' instruction-following capabilities . current benchmarks lack multilinguality, implicit constraints and multi-turn dialogue .
Approach: a new benchmark is designed to evaluate large language models' instruction-following capabilities . the benchmark features input prompts across 12 languages and includes inter-instance multilingual instructions .
Outcome: a new benchmark for large language models (LLMs) is designed to assess their performance in real-world settings.
MT-Eval: A Multi-Turn Capabilities Evaluation Benchmark for Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing evaluation frameworks focus on single-turn evaluations, overlooking the models’ capabilities in multi-turn interactions.
Approach: They propose a benchmark to evaluate the multi-turn conversational abilities of large language models (LLMs) by analyzing human-LLM conversations and constructing multi-turned queries for each category using GPT-4.
Outcome: The proposed model outperforms open-source models in multi-turn tasks while retaining and recalling historical information.
MDBench: A Synthetic Multi-Document Reasoning Benchmark Generated with Knowledge Guidance (2025.findings-acl)

Copied to clipboard

Challenge: Multi-document reasoning is an area of increasing relevance given LLM capabilities in handling longer-context inputs, but few benchmarks exist to rigorously examine model behavior in this setting.
Approach: They propose a new dataset for evaluating LLMs on the task of multi-document reasoning that uses condensed structured seed knowledge to modify it through LLM-assisted edits.
Outcome: The proposed method generates document sets and QA examples on a multi-document reasoning task using a synthetic generation process.
Can LLMs Reason About Program Semantics? A Comprehensive Evaluation of LLMs on Formal Specification Inference (2025.acl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) are increasingly being used to automate programming tasks.
Approach: They propose a benchmark to evaluate LLMs' reasoning abilities on program semantics.
Outcome: The proposed benchmark shows that LLMs perform well with simple control flows but struggle with more complex structures, especially loops, even with advanced prompting.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations