We have 4 of 14 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Long-horizon research agents must decide both how to investigate and what to investigate next as evidence accumulates. This is hard to learn because such decisions are sparse in long execution traces, and their consequences may emerge several investigations later. We introduce Meta-reasoning for Iterative Research Agen...
Practical LLM agents often operate over multi-turn conversations where success is determined only after the full interaction ends. Most multi-turn RL methods train via on-policy rollouts, but unlike in single-turn RLHF, the policy cannot produce a trajectory alone, since an external environment must respond after each...
Off-Context GRPO (OC-GRPO), a minimally modified variant of GRPO that uses guided rollouts but applies an importance-corrected objective to steer the update back toward the original unguided objective, avoiding the mismatch that destabilizes uncorrected guided training.
This work develops a black-box method for learning a single context-independent logit-bias vector, added at every decoding step, without modifying model weights or requiring gradients, and suggests that learned logit bias is a lightweight mechanism for adapting language models under minimal access requirements.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
