Papers by Songyang Han

5 papers
CodeScout: Contextual Problem Statement Enhancement for Software Agents (2026.findings-acl)

Copied to clipboard

Challenge: Current AI-powered code assistance tools struggle with ambiguous problem statements . failures on such ambiguously requests are highly correlated with longer trajectories .
Approach: They propose a contextual query refinement approach that transforms ambiguous user requests into comprehensive, actionable problem statements through lightweight pre-exploration of the target codebase.
Outcome: Empirical results show that CodeScout improves resolution rates with 27 additional issues resolved compared to baseline method.
RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents (2026.acl-long)

Copied to clipboard

Challenge: Existing methods for mixing-of-agents (MoA) lack model selection criteria and struggle with large model pools.
Approach: They propose a mixture-of-agents framework with dynamic routing that uses a lightweight scorer to perform initial screening and refines the model scores through self- and cross-assessment.
Outcome: The proposed framework outperforms existing methods for large model pools and tasks . it reduces cost by 89.8% and latency by 63.6% in the large-scale model pool.
LawBench: Benchmarking Legal Knowledge of Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: LegalBench evaluated 20 LLMs in 162 legal tasks in 20 countries and jurisdictions.
Approach: They present a comprehensive evaluation of 21 popular Large Language Models and the first comparative analysis of the empirical results.
Outcome: The proposed benchmarks are based on the Bloom’s cognitive taxonomy and are compared to 21 popular LLMs.
Empowering Multi-Turn Tool-Integrated Agentic Reasoning with Group Turn Policy Optimization (2026.acl-long)

Copied to clipboard

Challenge: Current reinforcement learning methods suffer from coarse-grained, trajectory-level rewards that provide insufficient learning signals for complex multi-turn interactions, leading to training stagnation.
Approach: They propose a novel RL algorithm for training large language models for multi-turn tool-integrated reasoning (TIR) that incorporates three innovations: turn-level reward assignment that provides fine-grained feedback for individual turns, return-based advantage estimation where normalized discounted returns are calculated as advantages, and self-supervised reward shaping that exploits self-supervision signals from generated code to densify sparse binary outcome-based rewards.
Outcome: The proposed algorithm outperforms GRPO by 3.0% across diverse math reasoning benchmarks and improves grepo by 3.9% on commonsense reasoning and program synthesis tasks.
Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data (2024.findings-emnlp)

Copied to clipboard

Challenge: Reinforcement Learning from Human Feedback (RLHF) relies on complex methodologies like Proximal Policy Optimization (PPO) that require extensive hyper-parameter tuning and pose challenges in sample efficiency and stability.
Approach: They propose an innovative framework that leverages direct preference optimization techniques but extends them by estimating the conditionally optimal policy directly from the model’s responses.
Outcome: The proposed framework matches and exceeds the effectiveness of Proximal Policy Optimization (PPO) in terms of convergence speed and alignment of model responses with human preferences.

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